Initial commit

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

Desktop.ini

@@ -0,0 +1,3 @@
+[.ShellClassInfo]
+IconFile=C:\Program Files (x86)\FolderPainter\Icons\03.ico
+IconIndex=0

IKEA_scrapper/.venv/Lib/site-packages/_distutils_hack/__init__.py

@@ -0,0 +1,128 @@
+import sys
+import os
+import re
+import importlib
+import warnings
+
+
+is_pypy = '__pypy__' in sys.builtin_module_names
+
+
+warnings.filterwarnings('ignore',
+                        '.+ distutils .+ deprecated',
+                        DeprecationWarning)
+
+
+def warn_distutils_present():
+    if 'distutils' not in sys.modules:
+        return
+    if is_pypy and sys.version_info < (3, 7):
+        # PyPy for 3.6 unconditionally imports distutils, so bypass the warning
+        # https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
+        return
+    warnings.warn(
+        "Distutils was imported before Setuptools, but importing Setuptools "
+        "also replaces the `distutils` module in `sys.modules`. This may lead "
+        "to undesirable behaviors or errors. To avoid these issues, avoid "
+        "using distutils directly, ensure that setuptools is installed in the "
+        "traditional way (e.g. not an editable install), and/or make sure "
+        "that setuptools is always imported before distutils.")
+
+
+def clear_distutils():
+    if 'distutils' not in sys.modules:
+        return
+    warnings.warn("Setuptools is replacing distutils.")
+    mods = [name for name in sys.modules if re.match(r'distutils\b', name)]
+    for name in mods:
+        del sys.modules[name]
+
+
+def enabled():
+    """
+    Allow selection of distutils by environment variable.
+    """
+    which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'stdlib')
+    return which == 'local'
+
+
+def ensure_local_distutils():
+    clear_distutils()
+    distutils = importlib.import_module('setuptools._distutils')
+    distutils.__name__ = 'distutils'
+    sys.modules['distutils'] = distutils
+
+    # sanity check that submodules load as expected
+    core = importlib.import_module('distutils.core')
+    assert '_distutils' in core.__file__, core.__file__
+
+
+def do_override():
+    """
+    Ensure that the local copy of distutils is preferred over stdlib.
+
+    See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
+    for more motivation.
+    """
+    if enabled():
+        warn_distutils_present()
+        ensure_local_distutils()
+
+
+class DistutilsMetaFinder:
+    def find_spec(self, fullname, path, target=None):
+        if path is not None:
+            return
+
+        method_name = 'spec_for_{fullname}'.format(**locals())
+        method = getattr(self, method_name, lambda: None)
+        return method()
+
+    def spec_for_distutils(self):
+        import importlib.abc
+        import importlib.util
+
+        class DistutilsLoader(importlib.abc.Loader):
+
+            def create_module(self, spec):
+                return importlib.import_module('setuptools._distutils')
+
+            def exec_module(self, module):
+                pass
+
+        return importlib.util.spec_from_loader('distutils', DistutilsLoader())
+
+    def spec_for_pip(self):
+        """
+        Ensure stdlib distutils when running under pip.
+        See pypa/pip#8761 for rationale.
+        """
+        if self.pip_imported_during_build():
+            return
+        clear_distutils()
+        self.spec_for_distutils = lambda: None
+
+    @staticmethod
+    def pip_imported_during_build():
+        """
+        Detect if pip is being imported in a build script. Ref #2355.
+        """
+        import traceback
+        return any(
+            frame.f_globals['__file__'].endswith('setup.py')
+            for frame, line in traceback.walk_stack(None)
+        )
+
+
+DISTUTILS_FINDER = DistutilsMetaFinder()
+
+
+def add_shim():
+    sys.meta_path.insert(0, DISTUTILS_FINDER)
+
+
+def remove_shim():
+    try:
+        sys.meta_path.remove(DISTUTILS_FINDER)
+    except ValueError:
+        pass

IKEA_scrapper/.venv/Lib/site-packages/_distutils_hack/override.py

@@ -0,0 +1 @@
+__import__('_distutils_hack').do_override()

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/AUTHORS

@@ -0,0 +1,49 @@
+Behold, mortal, the origins of Beautiful Soup...
+================================================
+
+Leonard Richardson is the primary maintainer.
+
+Aaron DeVore and Isaac Muse have made significant contributions to the
+code base.
+
+Mark Pilgrim provided the encoding detection code that forms the base
+of UnicodeDammit.
+
+Thomas Kluyver and Ezio Melotti finished the work of getting Beautiful
+Soup 4 working under Python 3.
+
+Simon Willison wrote soupselect, which was used to make Beautiful Soup
+support CSS selectors. Isaac Muse wrote SoupSieve, which made it
+possible to _remove_ the CSS selector code from Beautiful Soup.
+
+Sam Ruby helped with a lot of edge cases.
+
+Jonathan Ellis was awarded the prestigious Beau Potage D'Or for his
+work in solving the nestable tags conundrum.
+
+An incomplete list of people have contributed patches to Beautiful
+Soup:
+
+ Istvan Albert, Andrew Lin, Anthony Baxter, Oliver Beattie, Andrew
+Boyko, Tony Chang, Francisco Canas, "Delong", Zephyr Fang, Fuzzy,
+Roman Gaufman, Yoni Gilad, Richie Hindle, Toshihiro Kamiya, Peteris
+Krumins, Kent Johnson, Marek Kapolka, Andreas Kostyrka, Roel Kramer,
+Ben Last, Robert Leftwich, Stefaan Lippens, "liquider", Staffan
+Malmgren, Ksenia Marasanova, JP Moins, Adam Monsen, John Nagle, "Jon",
+Ed Oskiewicz, Martijn Peters, Greg Phillips, Giles Radford, Stefano
+Revera, Arthur Rudolph, Marko Samastur, James Salter, Jouni Seppänen,
+Alexander Schmolck, Tim Shirley, Geoffrey Sneddon, Ville Skyttä,
+"Vikas", Jens Svalgaard, Andy Theyers, Eric Weiser, Glyn Webster, John
+Wiseman, Paul Wright, Danny Yoo
+
+An incomplete list of people who made suggestions or found bugs or
+found ways to break Beautiful Soup:
+
+ Hanno Böck, Matteo Bertini, Chris Curvey, Simon Cusack, Bruce Eckel,
+ Matt Ernst, Michael Foord, Tom Harris, Bill de hOra, Donald Howes,
+ Matt Patterson, Scott Roberts, Steve Strassmann, Mike Williams,
+ warchild at redho dot com, Sami Kuisma, Carlos Rocha, Bob Hutchison,
+ Joren Mc, Michal Migurski, John Kleven, Tim Heaney, Tripp Lilley, Ed
+ Summers, Dennis Sutch, Chris Smith, Aaron Swartz, Stuart
+ Turner, Greg Edwards, Kevin J Kalupson, Nikos Kouremenos, Artur de
+ Sousa Rocha, Yichun Wei, Per Vognsen

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/COPYING.txt

@@ -0,0 +1,27 @@
+Beautiful Soup is made available under the MIT license:
+
+ Copyright (c) 2004-2017 Leonard Richardson
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to
+ permit persons to whom the Software is furnished to do so, subject to
+ the following conditions:
+
+ The above copyright notice and this permission notice shall be
+ included in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ SOFTWARE.
+
+Beautiful Soup incorporates code from the html5lib library, which is
+also made available under the MIT license. Copyright (c) 2006-2013
+James Graham and other contributors

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/LICENSE

@@ -0,0 +1,30 @@
+Beautiful Soup is made available under the MIT license:
+
+ Copyright (c) 2004-2019 Leonard Richardson
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to
+ permit persons to whom the Software is furnished to do so, subject to
+ the following conditions:
+
+ The above copyright notice and this permission notice shall be
+ included in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ SOFTWARE.
+
+Beautiful Soup incorporates code from the html5lib library, which is
+also made available under the MIT license. Copyright (c) 2006-2013
+James Graham and other contributors
+
+Beautiful Soup depends on the soupsieve library, which is also made
+available under the MIT license. Copyright (c) 2018 Isaac Muse

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/METADATA

@@ -0,0 +1,120 @@
+Metadata-Version: 2.1
+Name: beautifulsoup4
+Version: 4.10.0
+Summary: Screen-scraping library
+Home-page: http://www.crummy.com/software/BeautifulSoup/bs4/
+Author: Leonard Richardson
+Author-email: leonardr@segfault.org
+License: MIT
+Download-URL: http://www.crummy.com/software/BeautifulSoup/bs4/download/
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: XML
+Classifier: Topic :: Text Processing :: Markup :: SGML
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >3.0.0
+Description-Content-Type: text/markdown
+Requires-Dist: soupsieve (>1.2)
+Provides-Extra: html5lib
+Requires-Dist: html5lib ; extra == 'html5lib'
+Provides-Extra: lxml
+Requires-Dist: lxml ; extra == 'lxml'
+
+Beautiful Soup is a library that makes it easy to scrape information
+from web pages. It sits atop an HTML or XML parser, providing Pythonic
+idioms for iterating, searching, and modifying the parse tree.
+
+# Quick start
+
+```
+>>> from bs4 import BeautifulSoup
+>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
+>>> print(soup.prettify())
+<html>
+ <body>
+  <p>
+   Some
+   <b>
+    bad
+    <i>
+     HTML
+    </i>
+   </b>
+  </p>
+ </body>
+</html>
+>>> soup.find(text="bad")
+'bad'
+>>> soup.i
+<i>HTML</i>
+#
+>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
+#
+>>> print(soup.prettify())
+<?xml version="1.0" encoding="utf-8"?>
+<tag1>
+ Some
+ <tag2/>
+ bad
+ <tag3>
+  XML
+ </tag3>
+</tag1>
+```
+
+To go beyond the basics, [comprehensive documentation is available](http://www.crummy.com/software/BeautifulSoup/bs4/doc/).
+
+# Links
+
+* [Homepage](http://www.crummy.com/software/BeautifulSoup/bs4/)
+* [Documentation](http://www.crummy.com/software/BeautifulSoup/bs4/doc/)
+* [Discussion group](http://groups.google.com/group/beautifulsoup/)
+* [Development](https://code.launchpad.net/beautifulsoup/)
+* [Bug tracker](https://bugs.launchpad.net/beautifulsoup/)
+* [Complete changelog](https://bazaar.launchpad.net/~leonardr/beautifulsoup/bs4/view/head:/CHANGELOG)
+
+# Note on Python 2 sunsetting
+
+Beautiful Soup's support for Python 2 was discontinued on December 31,
+2020: one year after the sunset date for Python 2 itself. From this
+point onward, new Beautiful Soup development will exclusively target
+Python 3. The final release of Beautiful Soup 4 to support Python 2
+was 4.9.3.
+
+# Supporting the project
+
+If you use Beautiful Soup as part of your professional work, please consider a
+[Tidelift subscription](https://tidelift.com/subscription/pkg/pypi-beautifulsoup4?utm_source=pypi-beautifulsoup4&utm_medium=referral&utm_campaign=readme).
+This will support many of the free software projects your organization
+depends on, not just Beautiful Soup.
+
+If you use Beautiful Soup for personal projects, the best way to say
+thank you is to read
+[Tool Safety](https://www.crummy.com/software/BeautifulSoup/zine/), a zine I
+wrote about what Beautiful Soup has taught me about software
+development.
+
+# Building the documentation
+
+The bs4/doc/ directory contains full documentation in Sphinx
+format. Run `make html` in that directory to create HTML
+documentation.
+
+# Running the unit tests
+
+Beautiful Soup supports unit test discovery from the project root directory:
+
+```
+$ nosetests
+```
+
+```
+$ python3 -m unittest discover -s bs4
+```
+
+

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/RECORD

@@ -0,0 +1,28 @@
+beautifulsoup4-4.10.0.dist-info/AUTHORS,sha256=uSIdbrBb1sobdXl7VrlUvuvim2dN9kF3MH4Edn0WKGE,2176
+beautifulsoup4-4.10.0.dist-info/COPYING.txt,sha256=pH6lEjYJhGT-C09Vl0NZC1MwVtngD0nsv4Apn6tH4jE,1315
+beautifulsoup4-4.10.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+beautifulsoup4-4.10.0.dist-info/LICENSE,sha256=ynIn3bnu1syAnhV_Z7Ag543eBjJAAB0RhW-FxJy25CM,1447
+beautifulsoup4-4.10.0.dist-info/METADATA,sha256=xXGta_JNOdH5pvsMsrB1-MPPjMDhfi5q22-8r-iTMkg,3542
+beautifulsoup4-4.10.0.dist-info/RECORD,,
+beautifulsoup4-4.10.0.dist-info/WHEEL,sha256=g4nMs7d-Xl9-xC9XovUrsDHGXt-FT0E17Yqo92DEfvY,92
+beautifulsoup4-4.10.0.dist-info/top_level.txt,sha256=H8VT-IuPWLzQqwG9_eChjXDJ1z0H9RRebdSR90Bjnkw,4
+bs4/__init__.py,sha256=kZ9EDFbdsNtqNkUL95_7epbnZCO7HKgW-s2ukdAXXY0,32673
+bs4/__pycache__/__init__.cpython-39.pyc,,
+bs4/__pycache__/dammit.cpython-39.pyc,,
+bs4/__pycache__/diagnose.cpython-39.pyc,,
+bs4/__pycache__/element.cpython-39.pyc,,
+bs4/__pycache__/formatter.cpython-39.pyc,,
+bs4/__pycache__/testing.cpython-39.pyc,,
+bs4/builder/__init__.py,sha256=FP2SbcvOUZWk8a84wc9-K90F2YA2--nQpxm-GK0G8Gc,19870
+bs4/builder/__pycache__/__init__.cpython-39.pyc,,
+bs4/builder/__pycache__/_html5lib.cpython-39.pyc,,
+bs4/builder/__pycache__/_htmlparser.cpython-39.pyc,,
+bs4/builder/__pycache__/_lxml.cpython-39.pyc,,
+bs4/builder/_html5lib.py,sha256=hDxlzVrAku_eU7zEt4gZ-sAXzG58GvkLfMz6P4zUqoA,18748
+bs4/builder/_htmlparser.py,sha256=KjnSpA8C8-_yX4nFd_UwCB4SGO9pzqR05WjjbuZjzH4,18933
+bs4/builder/_lxml.py,sha256=h20vsAgSkeiIPiCKwJ-ggajeaxra7bicCtQSOoinUTc,12699
+bs4/dammit.py,sha256=lMWxYrl9VeLqEgXvk4MJK8isKPgNF_yQXk8B9R4UxXE,98709
+bs4/diagnose.py,sha256=WOzytCTkvqh_fGhqYlMyaYVjtH50w4jbdf1Fd0iundE,7755
+bs4/element.py,sha256=noCV6m4euxWVo3I1Bjh9SYDgG_VNu7oGoWLB0XlCldc,85238
+bs4/formatter.py,sha256=wAuETtbENr2HP-ZiR6WRu4_bLFY8ALRV_BPqWhhr7HA,6385
+bs4/testing.py,sha256=6leLHpE7mHFV7W8SqR3vRvsgEVR3eqxprJVIf8W_bgY,47412

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.34.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

IKEA_scrapper/.venv/Lib/site-packages/beautifulsoup4-4.10.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+bs4

IKEA_scrapper/.venv/Lib/site-packages/bs4-0.0.1-py3.9.egg-info/PKG-INFO

@@ -0,0 +1,21 @@
+Metadata-Version: 1.1
+Name: bs4
+Version: 0.0.1
+Summary: Screen-scraping library
+Home-page: https://pypi.python.org/pypi/beautifulsoup4
+Author: Leonard Richardson
+Author-email: leonardr@segfault.org
+License: MIT
+Download-URL: http://www.crummy.com/software/BeautifulSoup/bs4/download/
+Description: Use `beautifulsoup4 <https://pypi.python.org/pypi/beautifulsoup4>`_ instead.
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: XML
+Classifier: Topic :: Text Processing :: Markup :: SGML
+Classifier: Topic :: Software Development :: Libraries :: Python Modules

IKEA_scrapper/.venv/Lib/site-packages/bs4-0.0.1-py3.9.egg-info/SOURCES.txt

@@ -0,0 +1,7 @@
+setup.cfg
+setup.py
+bs4.egg-info/PKG-INFO
+bs4.egg-info/SOURCES.txt
+bs4.egg-info/dependency_links.txt
+bs4.egg-info/requires.txt
+bs4.egg-info/top_level.txt

IKEA_scrapper/.venv/Lib/site-packages/bs4-0.0.1-py3.9.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

IKEA_scrapper/.venv/Lib/site-packages/bs4-0.0.1-py3.9.egg-info/installed-files.txt

@@ -0,0 +1,5 @@
+PKG-INFO
+SOURCES.txt
+dependency_links.txt
+requires.txt
+top_level.txt

IKEA_scrapper/.venv/Lib/site-packages/bs4-0.0.1-py3.9.egg-info/requires.txt

@@ -0,0 +1 @@
+beautifulsoup4

IKEA_scrapper/.venv/Lib/site-packages/bs4-0.0.1-py3.9.egg-info/top_level.txt

@@ -0,0 +1 @@
+

IKEA_scrapper/.venv/Lib/site-packages/bs4/__init__.py

@@ -0,0 +1,804 @@
+"""Beautiful Soup Elixir and Tonic - "The Screen-Scraper's Friend".
+
+http://www.crummy.com/software/BeautifulSoup/
+
+Beautiful Soup uses a pluggable XML or HTML parser to parse a
+(possibly invalid) document into a tree representation. Beautiful Soup
+provides methods and Pythonic idioms that make it easy to navigate,
+search, and modify the parse tree.
+
+Beautiful Soup works with Python 3.5 and up. It works better if lxml
+and/or html5lib is installed.
+
+For more than you ever wanted to know about Beautiful Soup, see the
+documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
+"""
+
+__author__ = "Leonard Richardson (leonardr@segfault.org)"
+__version__ = "4.10.0"
+__copyright__ = "Copyright (c) 2004-2021 Leonard Richardson"
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+__all__ = ['BeautifulSoup']
+
+
+from collections import Counter
+import os
+import re
+import sys
+import traceback
+import warnings
+
+# The very first thing we do is give a useful error if someone is
+# running this code under Python 2.
+if sys.version_info.major < 3:
+    raise ImportError('You are trying to use a Python 3-specific version of Beautiful Soup under Python 2. This will not work. The final version of Beautiful Soup to support Python 2 was 4.9.3.')
+
+from .builder import builder_registry, ParserRejectedMarkup
+from .dammit import UnicodeDammit
+from .element import (
+    CData,
+    Comment,
+    DEFAULT_OUTPUT_ENCODING,
+    Declaration,
+    Doctype,
+    NavigableString,
+    PageElement,
+    ProcessingInstruction,
+    PYTHON_SPECIFIC_ENCODINGS,
+    ResultSet,
+    Script,
+    Stylesheet,
+    SoupStrainer,
+    Tag,
+    TemplateString,
+    )
+
+# Define some custom warnings.
+class GuessedAtParserWarning(UserWarning):
+    """The warning issued when BeautifulSoup has to guess what parser to
+    use -- probably because no parser was specified in the constructor.
+    """
+
+class MarkupResemblesLocatorWarning(UserWarning):
+    """The warning issued when BeautifulSoup is given 'markup' that
+    actually looks like a resource locator -- a URL or a path to a file
+    on disk.
+    """
+
+
+class BeautifulSoup(Tag):
+    """A data structure representing a parsed HTML or XML document.
+
+    Most of the methods you'll call on a BeautifulSoup object are inherited from
+    PageElement or Tag.
+
+    Internally, this class defines the basic interface called by the
+    tree builders when converting an HTML/XML document into a data
+    structure. The interface abstracts away the differences between
+    parsers. To write a new tree builder, you'll need to understand
+    these methods as a whole.
+
+    These methods will be called by the BeautifulSoup constructor:
+      * reset()
+      * feed(markup)
+
+    The tree builder may call these methods from its feed() implementation:
+      * handle_starttag(name, attrs) # See note about return value
+      * handle_endtag(name)
+      * handle_data(data) # Appends to the current data node
+      * endData(containerClass) # Ends the current data node
+
+    No matter how complicated the underlying parser is, you should be
+    able to build a tree using 'start tag' events, 'end tag' events,
+    'data' events, and "done with data" events.
+
+    If you encounter an empty-element tag (aka a self-closing tag,
+    like HTML's <br> tag), call handle_starttag and then
+    handle_endtag.
+    """
+
+    # Since BeautifulSoup subclasses Tag, it's possible to treat it as
+    # a Tag with a .name. This name makes it clear the BeautifulSoup
+    # object isn't a real markup tag.
+    ROOT_TAG_NAME = '[document]'
+
+    # If the end-user gives no indication which tree builder they
+    # want, look for one with these features.
+    DEFAULT_BUILDER_FEATURES = ['html', 'fast']
+
+    # A string containing all ASCII whitespace characters, used in
+    # endData() to detect data chunks that seem 'empty'.
+    ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
+
+    NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, pass the additional argument 'features=\"%(parser)s\"' to the BeautifulSoup constructor.\n"
+    
+    def __init__(self, markup="", features=None, builder=None,
+                 parse_only=None, from_encoding=None, exclude_encodings=None,
+                 element_classes=None, **kwargs):
+        """Constructor.
+
+        :param markup: A string or a file-like object representing
+         markup to be parsed.
+
+        :param features: Desirable features of the parser to be
+         used. This may be the name of a specific parser ("lxml",
+         "lxml-xml", "html.parser", or "html5lib") or it may be the
+         type of markup to be used ("html", "html5", "xml"). It's
+         recommended that you name a specific parser, so that
+         Beautiful Soup gives you the same results across platforms
+         and virtual environments.
+
+        :param builder: A TreeBuilder subclass to instantiate (or
+         instance to use) instead of looking one up based on
+         `features`. You only need to use this if you've implemented a
+         custom TreeBuilder.
+
+        :param parse_only: A SoupStrainer. Only parts of the document
+         matching the SoupStrainer will be considered. This is useful
+         when parsing part of a document that would otherwise be too
+         large to fit into memory.
+
+        :param from_encoding: A string indicating the encoding of the
+         document to be parsed. Pass this in if Beautiful Soup is
+         guessing wrongly about the document's encoding.
+
+        :param exclude_encodings: A list of strings indicating
+         encodings known to be wrong. Pass this in if you don't know
+         the document's encoding but you know Beautiful Soup's guess is
+         wrong.
+
+        :param element_classes: A dictionary mapping BeautifulSoup
+         classes like Tag and NavigableString, to other classes you'd
+         like to be instantiated instead as the parse tree is
+         built. This is useful for subclassing Tag or NavigableString
+         to modify default behavior.
+
+        :param kwargs: For backwards compatibility purposes, the
+         constructor accepts certain keyword arguments used in
+         Beautiful Soup 3. None of these arguments do anything in
+         Beautiful Soup 4; they will result in a warning and then be
+         ignored.
+         
+         Apart from this, any keyword arguments passed into the
+         BeautifulSoup constructor are propagated to the TreeBuilder
+         constructor. This makes it possible to configure a
+         TreeBuilder by passing in arguments, not just by saying which
+         one to use.
+        """
+        if 'convertEntities' in kwargs:
+            del kwargs['convertEntities']
+            warnings.warn(
+                "BS4 does not respect the convertEntities argument to the "
+                "BeautifulSoup constructor. Entities are always converted "
+                "to Unicode characters.")
+
+        if 'markupMassage' in kwargs:
+            del kwargs['markupMassage']
+            warnings.warn(
+                "BS4 does not respect the markupMassage argument to the "
+                "BeautifulSoup constructor. The tree builder is responsible "
+                "for any necessary markup massage.")
+
+        if 'smartQuotesTo' in kwargs:
+            del kwargs['smartQuotesTo']
+            warnings.warn(
+                "BS4 does not respect the smartQuotesTo argument to the "
+                "BeautifulSoup constructor. Smart quotes are always converted "
+                "to Unicode characters.")
+
+        if 'selfClosingTags' in kwargs:
+            del kwargs['selfClosingTags']
+            warnings.warn(
+                "BS4 does not respect the selfClosingTags argument to the "
+                "BeautifulSoup constructor. The tree builder is responsible "
+                "for understanding self-closing tags.")
+
+        if 'isHTML' in kwargs:
+            del kwargs['isHTML']
+            warnings.warn(
+                "BS4 does not respect the isHTML argument to the "
+                "BeautifulSoup constructor. Suggest you use "
+                "features='lxml' for HTML and features='lxml-xml' for "
+                "XML.")
+
+        def deprecated_argument(old_name, new_name):
+            if old_name in kwargs:
+                warnings.warn(
+                    'The "%s" argument to the BeautifulSoup constructor '
+                    'has been renamed to "%s."' % (old_name, new_name))
+                value = kwargs[old_name]
+                del kwargs[old_name]
+                return value
+            return None
+
+        parse_only = parse_only or deprecated_argument(
+            "parseOnlyThese", "parse_only")
+
+        from_encoding = from_encoding or deprecated_argument(
+            "fromEncoding", "from_encoding")
+
+        if from_encoding and isinstance(markup, str):
+            warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
+            from_encoding = None
+
+        self.element_classes = element_classes or dict()
+
+        # We need this information to track whether or not the builder
+        # was specified well enough that we can omit the 'you need to
+        # specify a parser' warning.
+        original_builder = builder
+        original_features = features
+            
+        if isinstance(builder, type):
+            # A builder class was passed in; it needs to be instantiated.
+            builder_class = builder
+            builder = None
+        elif builder is None:
+            if isinstance(features, str):
+                features = [features]
+            if features is None or len(features) == 0:
+                features = self.DEFAULT_BUILDER_FEATURES
+            builder_class = builder_registry.lookup(*features)
+            if builder_class is None:
+                raise FeatureNotFound(
+                    "Couldn't find a tree builder with the features you "
+                    "requested: %s. Do you need to install a parser library?"
+                    % ",".join(features))
+
+        # At this point either we have a TreeBuilder instance in
+        # builder, or we have a builder_class that we can instantiate
+        # with the remaining **kwargs.
+        if builder is None:
+            builder = builder_class(**kwargs)
+            if not original_builder and not (
+                    original_features == builder.NAME or
+                    original_features in builder.ALTERNATE_NAMES
+            ) and markup:
+                # The user did not tell us which TreeBuilder to use,
+                # and we had to guess. Issue a warning.
+                if builder.is_xml:
+                    markup_type = "XML"
+                else:
+                    markup_type = "HTML"
+
+                # This code adapted from warnings.py so that we get the same line
+                # of code as our warnings.warn() call gets, even if the answer is wrong
+                # (as it may be in a multithreading situation).
+                caller = None
+                try:
+                    caller = sys._getframe(1)
+                except ValueError:
+                    pass
+                if caller:
+                    globals = caller.f_globals
+                    line_number = caller.f_lineno
+                else:
+                    globals = sys.__dict__
+                    line_number= 1                    
+                filename = globals.get('__file__')
+                if filename:
+                    fnl = filename.lower()
+                    if fnl.endswith((".pyc", ".pyo")):
+                        filename = filename[:-1]
+                if filename:
+                    # If there is no filename at all, the user is most likely in a REPL,
+                    # and the warning is not necessary.
+                    values = dict(
+                        filename=filename,
+                        line_number=line_number,
+                        parser=builder.NAME,
+                        markup_type=markup_type
+                    )
+                    warnings.warn(
+                        self.NO_PARSER_SPECIFIED_WARNING % values,
+                        GuessedAtParserWarning, stacklevel=2
+                    )
+        else:
+            if kwargs:
+                warnings.warn("Keyword arguments to the BeautifulSoup constructor will be ignored. These would normally be passed into the TreeBuilder constructor, but a TreeBuilder instance was passed in as `builder`.")
+                    
+        self.builder = builder
+        self.is_xml = builder.is_xml
+        self.known_xml = self.is_xml
+        self._namespaces = dict()
+        self.parse_only = parse_only
+
+        self.builder.initialize_soup(self)
+
+        if hasattr(markup, 'read'):        # It's a file-type object.
+            markup = markup.read()
+        elif len(markup) <= 256 and (
+                (isinstance(markup, bytes) and not b'<' in markup)
+                or (isinstance(markup, str) and not '<' in markup)
+        ):
+            # Print out warnings for a couple beginner problems
+            # involving passing non-markup to Beautiful Soup.
+            # Beautiful Soup will still parse the input as markup,
+            # just in case that's what the user really wants.
+            if (isinstance(markup, str)
+                and not os.path.supports_unicode_filenames):
+                possible_filename = markup.encode("utf8")
+            else:
+                possible_filename = markup
+            is_file = False
+            is_directory = False
+            try:
+                is_file = os.path.exists(possible_filename)
+                if is_file:
+                    is_directory = os.path.isdir(possible_filename)
+            except Exception as e:
+                # This is almost certainly a problem involving
+                # characters not valid in filenames on this
+                # system. Just let it go.
+                pass
+            if is_directory:
+                warnings.warn(
+                    '"%s" looks like a directory name, not markup. You may'
+                    ' want to open a file found in this directory and pass'
+                    ' the filehandle into Beautiful Soup.' % (
+                        self._decode_markup(markup)
+                    ),
+                    MarkupResemblesLocatorWarning
+                )
+            elif is_file:
+                warnings.warn(
+                    '"%s" looks like a filename, not markup. You should'
+                    ' probably open this file and pass the filehandle into'
+                    ' Beautiful Soup.' % self._decode_markup(markup),
+                    MarkupResemblesLocatorWarning
+                )
+            self._check_markup_is_url(markup)
+
+        rejections = []
+        success = False
+        for (self.markup, self.original_encoding, self.declared_html_encoding,
+         self.contains_replacement_characters) in (
+             self.builder.prepare_markup(
+                 markup, from_encoding, exclude_encodings=exclude_encodings)):
+            self.reset()
+            try:
+                self._feed()
+                success = True
+                break
+            except ParserRejectedMarkup as e:
+                rejections.append(e)
+                pass
+
+        if not success:
+            other_exceptions = [str(e) for e in rejections]
+            raise ParserRejectedMarkup(
+                "The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help.\n\nOriginal exception(s) from parser:\n " + "\n ".join(other_exceptions)
+            )
+
+        # Clear out the markup and remove the builder's circular
+        # reference to this object.
+        self.markup = None
+        self.builder.soup = None
+
+    def __copy__(self):
+        """Copy a BeautifulSoup object by converting the document to a string and parsing it again."""
+        copy = type(self)(
+            self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
+        )
+
+        # Although we encoded the tree to UTF-8, that may not have
+        # been the encoding of the original markup. Set the copy's
+        # .original_encoding to reflect the original object's
+        # .original_encoding.
+        copy.original_encoding = self.original_encoding
+        return copy
+
+    def __getstate__(self):
+        # Frequently a tree builder can't be pickled.
+        d = dict(self.__dict__)
+        if 'builder' in d and not self.builder.picklable:
+            d['builder'] = None
+        return d
+
+    @classmethod
+    def _decode_markup(cls, markup):
+        """Ensure `markup` is bytes so it's safe to send into warnings.warn.
+
+        TODO: warnings.warn had this problem back in 2010 but it might not
+        anymore.
+        """
+        if isinstance(markup, bytes):
+            decoded = markup.decode('utf-8', 'replace')
+        else:
+            decoded = markup
+        return decoded
+
+    @classmethod
+    def _check_markup_is_url(cls, markup):
+        """Error-handling method to raise a warning if incoming markup looks
+        like a URL.
+
+        :param markup: A string.
+        """
+        if isinstance(markup, bytes):
+            space = b' '
+            cant_start_with = (b"http:", b"https:")
+        elif isinstance(markup, str):
+            space = ' '
+            cant_start_with = ("http:", "https:")
+        else:
+            return
+
+        if any(markup.startswith(prefix) for prefix in cant_start_with):
+            if not space in markup:
+                warnings.warn(
+                    '"%s" looks like a URL. Beautiful Soup is not an'
+                    ' HTTP client. You should probably use an HTTP client like'
+                    ' requests to get the document behind the URL, and feed'
+                    ' that document to Beautiful Soup.' % cls._decode_markup(
+                        markup
+                    ),
+                    MarkupResemblesLocatorWarning
+                )
+
+    def _feed(self):
+        """Internal method that parses previously set markup, creating a large
+        number of Tag and NavigableString objects.
+        """
+        # Convert the document to Unicode.
+        self.builder.reset()
+
+        self.builder.feed(self.markup)
+        # Close out any unfinished strings and close all the open tags.
+        self.endData()
+        while self.currentTag.name != self.ROOT_TAG_NAME:
+            self.popTag()
+
+    def reset(self):
+        """Reset this object to a state as though it had never parsed any
+        markup.
+        """
+        Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
+        self.hidden = 1
+        self.builder.reset()
+        self.current_data = []
+        self.currentTag = None
+        self.tagStack = []
+        self.open_tag_counter = Counter()
+        self.preserve_whitespace_tag_stack = []
+        self.string_container_stack = []
+        self.pushTag(self)
+
+    def new_tag(self, name, namespace=None, nsprefix=None, attrs={},
+                sourceline=None, sourcepos=None, **kwattrs):
+        """Create a new Tag associated with this BeautifulSoup object.
+
+        :param name: The name of the new Tag.
+        :param namespace: The URI of the new Tag's XML namespace, if any.
+        :param prefix: The prefix for the new Tag's XML namespace, if any.
+        :param attrs: A dictionary of this Tag's attribute values; can
+            be used instead of `kwattrs` for attributes like 'class'
+            that are reserved words in Python.
+        :param sourceline: The line number where this tag was
+            (purportedly) found in its source document.
+        :param sourcepos: The character position within `sourceline` where this
+            tag was (purportedly) found.
+        :param kwattrs: Keyword arguments for the new Tag's attribute values.
+
+        """
+        kwattrs.update(attrs)
+        return self.element_classes.get(Tag, Tag)(
+            None, self.builder, name, namespace, nsprefix, kwattrs,
+            sourceline=sourceline, sourcepos=sourcepos
+        )
+
+    def string_container(self, base_class=None):
+        container = base_class or NavigableString
+        
+        # There may be a general override of NavigableString.
+        container = self.element_classes.get(
+            container, container
+        )
+
+        # On top of that, we may be inside a tag that needs a special
+        # container class.
+        if self.string_container_stack and container is NavigableString:
+            container = self.builder.string_containers.get(
+                self.string_container_stack[-1].name, container
+            )
+        return container
+        
+    def new_string(self, s, subclass=None):
+        """Create a new NavigableString associated with this BeautifulSoup
+        object.
+        """
+        container = self.string_container(subclass)
+        return container(s)
+
+    def insert_before(self, *args):
+        """This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
+        it because there is nothing before or after it in the parse tree.
+        """
+        raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
+
+    def insert_after(self, *args):
+        """This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
+        it because there is nothing before or after it in the parse tree.
+        """
+        raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
+
+    def popTag(self):
+        """Internal method called by _popToTag when a tag is closed."""
+        tag = self.tagStack.pop()
+        if tag.name in self.open_tag_counter:
+            self.open_tag_counter[tag.name] -= 1
+        if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
+            self.preserve_whitespace_tag_stack.pop()
+        if self.string_container_stack and tag == self.string_container_stack[-1]:
+            self.string_container_stack.pop()
+        #print("Pop", tag.name)
+        if self.tagStack:
+            self.currentTag = self.tagStack[-1]
+        return self.currentTag
+
+    def pushTag(self, tag):
+        """Internal method called by handle_starttag when a tag is opened."""
+        #print("Push", tag.name)
+        if self.currentTag is not None:
+            self.currentTag.contents.append(tag)
+        self.tagStack.append(tag)
+        self.currentTag = self.tagStack[-1]
+        if tag.name != self.ROOT_TAG_NAME:
+            self.open_tag_counter[tag.name] += 1
+        if tag.name in self.builder.preserve_whitespace_tags:
+            self.preserve_whitespace_tag_stack.append(tag)
+        if tag.name in self.builder.string_containers:
+            self.string_container_stack.append(tag)
+
+    def endData(self, containerClass=None):
+        """Method called by the TreeBuilder when the end of a data segment
+        occurs.
+        """       
+        if self.current_data:
+            current_data = ''.join(self.current_data)
+            # If whitespace is not preserved, and this string contains
+            # nothing but ASCII spaces, replace it with a single space
+            # or newline.
+            if not self.preserve_whitespace_tag_stack:
+                strippable = True
+                for i in current_data:
+                    if i not in self.ASCII_SPACES:
+                        strippable = False
+                        break
+                if strippable:
+                    if '\n' in current_data:
+                        current_data = '\n'
+                    else:
+                        current_data = ' '
+
+            # Reset the data collector.
+            self.current_data = []
+
+            # Should we add this string to the tree at all?
+            if self.parse_only and len(self.tagStack) <= 1 and \
+                   (not self.parse_only.text or \
+                    not self.parse_only.search(current_data)):
+                return
+
+            containerClass = self.string_container(containerClass)
+            o = containerClass(current_data)
+            self.object_was_parsed(o)
+
+    def object_was_parsed(self, o, parent=None, most_recent_element=None):
+        """Method called by the TreeBuilder to integrate an object into the parse tree."""
+        if parent is None:
+            parent = self.currentTag
+        if most_recent_element is not None:
+            previous_element = most_recent_element
+        else:
+            previous_element = self._most_recent_element
+
+        next_element = previous_sibling = next_sibling = None
+        if isinstance(o, Tag):
+            next_element = o.next_element
+            next_sibling = o.next_sibling
+            previous_sibling = o.previous_sibling
+            if previous_element is None:
+                previous_element = o.previous_element
+
+        fix = parent.next_element is not None
+
+        o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
+
+        self._most_recent_element = o
+        parent.contents.append(o)
+
+        # Check if we are inserting into an already parsed node.
+        if fix:
+            self._linkage_fixer(parent)
+
+    def _linkage_fixer(self, el):
+        """Make sure linkage of this fragment is sound."""
+
+        first = el.contents[0]
+        child = el.contents[-1]
+        descendant = child
+
+        if child is first and el.parent is not None:
+            # Parent should be linked to first child
+            el.next_element = child
+            # We are no longer linked to whatever this element is
+            prev_el = child.previous_element
+            if prev_el is not None and prev_el is not el:
+                prev_el.next_element = None
+            # First child should be linked to the parent, and no previous siblings.
+            child.previous_element = el
+            child.previous_sibling = None
+
+        # We have no sibling as we've been appended as the last.
+        child.next_sibling = None
+
+        # This index is a tag, dig deeper for a "last descendant"
+        if isinstance(child, Tag) and child.contents:
+            descendant = child._last_descendant(False)
+
+        # As the final step, link last descendant. It should be linked
+        # to the parent's next sibling (if found), else walk up the chain
+        # and find a parent with a sibling. It should have no next sibling.
+        descendant.next_element = None
+        descendant.next_sibling = None
+        target = el
+        while True:
+            if target is None:
+                break
+            elif target.next_sibling is not None:
+                descendant.next_element = target.next_sibling
+                target.next_sibling.previous_element = child
+                break
+            target = target.parent
+
+    def _popToTag(self, name, nsprefix=None, inclusivePop=True):
+        """Pops the tag stack up to and including the most recent
+        instance of the given tag.
+
+        If there are no open tags with the given name, nothing will be
+        popped.
+
+        :param name: Pop up to the most recent tag with this name.
+        :param nsprefix: The namespace prefix that goes with `name`.
+        :param inclusivePop: It this is false, pops the tag stack up
+          to but *not* including the most recent instqance of the
+          given tag.
+
+        """
+        #print("Popping to %s" % name)
+        if name == self.ROOT_TAG_NAME:
+            # The BeautifulSoup object itself can never be popped.
+            return
+
+        most_recently_popped = None
+
+        stack_size = len(self.tagStack)
+        for i in range(stack_size - 1, 0, -1):
+            if not self.open_tag_counter.get(name):
+                break
+            t = self.tagStack[i]
+            if (name == t.name and nsprefix == t.prefix):
+                if inclusivePop:
+                    most_recently_popped = self.popTag()
+                break
+            most_recently_popped = self.popTag()
+
+        return most_recently_popped
+
+    def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
+                        sourcepos=None):
+        """Called by the tree builder when a new tag is encountered.
+
+        :param name: Name of the tag.
+        :param nsprefix: Namespace prefix for the tag.
+        :param attrs: A dictionary of attribute values.
+        :param sourceline: The line number where this tag was found in its
+            source document.
+        :param sourcepos: The character position within `sourceline` where this
+            tag was found.
+
+        If this method returns None, the tag was rejected by an active
+        SoupStrainer. You should proceed as if the tag had not occurred
+        in the document. For instance, if this was a self-closing tag,
+        don't call handle_endtag.
+        """
+        # print("Start tag %s: %s" % (name, attrs))
+        self.endData()
+
+        if (self.parse_only and len(self.tagStack) <= 1
+            and (self.parse_only.text
+                 or not self.parse_only.search_tag(name, attrs))):
+            return None
+
+        tag = self.element_classes.get(Tag, Tag)(
+            self, self.builder, name, namespace, nsprefix, attrs,
+            self.currentTag, self._most_recent_element,
+            sourceline=sourceline, sourcepos=sourcepos
+        )
+        if tag is None:
+            return tag
+        if self._most_recent_element is not None:
+            self._most_recent_element.next_element = tag
+        self._most_recent_element = tag
+        self.pushTag(tag)
+        return tag
+
+    def handle_endtag(self, name, nsprefix=None):
+        """Called by the tree builder when an ending tag is encountered.
+
+        :param name: Name of the tag.
+        :param nsprefix: Namespace prefix for the tag.
+        """
+        #print("End tag: " + name)
+        self.endData()
+        self._popToTag(name, nsprefix)
+
+    def handle_data(self, data):
+        """Called by the tree builder when a chunk of textual data is encountered."""
+        self.current_data.append(data)
+       
+    def decode(self, pretty_print=False,
+               eventual_encoding=DEFAULT_OUTPUT_ENCODING,
+               formatter="minimal"):
+        """Returns a string or Unicode representation of the parse tree
+            as an HTML or XML document.
+
+        :param pretty_print: If this is True, indentation will be used to
+            make the document more readable.
+        :param eventual_encoding: The encoding of the final document.
+            If this is None, the document will be a Unicode string.
+        """
+        if self.is_xml:
+            # Print the XML declaration
+            encoding_part = ''
+            if eventual_encoding in PYTHON_SPECIFIC_ENCODINGS:
+                # This is a special Python encoding; it can't actually
+                # go into an XML document because it means nothing
+                # outside of Python.
+                eventual_encoding = None
+            if eventual_encoding != None:
+                encoding_part = ' encoding="%s"' % eventual_encoding
+            prefix = '<?xml version="1.0"%s?>\n' % encoding_part
+        else:
+            prefix = ''
+        if not pretty_print:
+            indent_level = None
+        else:
+            indent_level = 0
+        return prefix + super(BeautifulSoup, self).decode(
+            indent_level, eventual_encoding, formatter)
+
+# Aliases to make it easier to get started quickly, e.g. 'from bs4 import _soup'
+_s = BeautifulSoup
+_soup = BeautifulSoup
+
+class BeautifulStoneSoup(BeautifulSoup):
+    """Deprecated interface to an XML parser."""
+
+    def __init__(self, *args, **kwargs):
+        kwargs['features'] = 'xml'
+        warnings.warn(
+            'The BeautifulStoneSoup class is deprecated. Instead of using '
+            'it, pass features="xml" into the BeautifulSoup constructor.')
+        super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
+
+
+class StopParsing(Exception):
+    """Exception raised by a TreeBuilder if it's unable to continue parsing."""
+    pass
+
+class FeatureNotFound(ValueError):
+    """Exception raised by the BeautifulSoup constructor if no parser with the
+    requested features is found.
+    """
+    pass
+
+
+#If this file is run as a script, act as an HTML pretty-printer.
+if __name__ == '__main__':
+    import sys
+    soup = BeautifulSoup(sys.stdin)
+    print((soup.prettify()))

IKEA_scrapper/.venv/Lib/site-packages/bs4/builder/__init__.py

@@ -0,0 +1,520 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+from collections import defaultdict
+import itertools
+import sys
+from bs4.element import (
+    CharsetMetaAttributeValue,
+    ContentMetaAttributeValue,
+    Stylesheet,
+    Script,
+    TemplateString,
+    nonwhitespace_re
+)
+
+__all__ = [
+    'HTMLTreeBuilder',
+    'SAXTreeBuilder',
+    'TreeBuilder',
+    'TreeBuilderRegistry',
+    ]
+
+# Some useful features for a TreeBuilder to have.
+FAST = 'fast'
+PERMISSIVE = 'permissive'
+STRICT = 'strict'
+XML = 'xml'
+HTML = 'html'
+HTML_5 = 'html5'
+
+
+class TreeBuilderRegistry(object):
+    """A way of looking up TreeBuilder subclasses by their name or by desired
+    features.
+    """
+    
+    def __init__(self):
+        self.builders_for_feature = defaultdict(list)
+        self.builders = []
+
+    def register(self, treebuilder_class):
+        """Register a treebuilder based on its advertised features.
+
+        :param treebuilder_class: A subclass of Treebuilder. its .features
+           attribute should list its features.
+        """
+        for feature in treebuilder_class.features:
+            self.builders_for_feature[feature].insert(0, treebuilder_class)
+        self.builders.insert(0, treebuilder_class)
+
+    def lookup(self, *features):
+        """Look up a TreeBuilder subclass with the desired features.
+
+        :param features: A list of features to look for. If none are
+            provided, the most recently registered TreeBuilder subclass
+            will be used.
+        :return: A TreeBuilder subclass, or None if there's no
+            registered subclass with all the requested features.
+        """
+        if len(self.builders) == 0:
+            # There are no builders at all.
+            return None
+
+        if len(features) == 0:
+            # They didn't ask for any features. Give them the most
+            # recently registered builder.
+            return self.builders[0]
+
+        # Go down the list of features in order, and eliminate any builders
+        # that don't match every feature.
+        features = list(features)
+        features.reverse()
+        candidates = None
+        candidate_set = None
+        while len(features) > 0:
+            feature = features.pop()
+            we_have_the_feature = self.builders_for_feature.get(feature, [])
+            if len(we_have_the_feature) > 0:
+                if candidates is None:
+                    candidates = we_have_the_feature
+                    candidate_set = set(candidates)
+                else:
+                    # Eliminate any candidates that don't have this feature.
+                    candidate_set = candidate_set.intersection(
+                        set(we_have_the_feature))
+
+        # The only valid candidates are the ones in candidate_set.
+        # Go through the original list of candidates and pick the first one
+        # that's in candidate_set.
+        if candidate_set is None:
+            return None
+        for candidate in candidates:
+            if candidate in candidate_set:
+                return candidate
+        return None
+
+# The BeautifulSoup class will take feature lists from developers and use them
+# to look up builders in this registry.
+builder_registry = TreeBuilderRegistry()
+
+class TreeBuilder(object):
+    """Turn a textual document into a Beautiful Soup object tree."""
+
+    NAME = "[Unknown tree builder]"
+    ALTERNATE_NAMES = []
+    features = []
+
+    is_xml = False
+    picklable = False
+    empty_element_tags = None # A tag will be considered an empty-element
+                              # tag when and only when it has no contents.
+    
+    # A value for these tag/attribute combinations is a space- or
+    # comma-separated list of CDATA, rather than a single CDATA.
+    DEFAULT_CDATA_LIST_ATTRIBUTES = {}
+
+    # Whitespace should be preserved inside these tags.
+    DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
+
+    # The textual contents of tags with these names should be
+    # instantiated with some class other than NavigableString.
+    DEFAULT_STRING_CONTAINERS = {}
+    
+    USE_DEFAULT = object()
+
+    # Most parsers don't keep track of line numbers.
+    TRACKS_LINE_NUMBERS = False
+    
+    def __init__(self, multi_valued_attributes=USE_DEFAULT,
+                 preserve_whitespace_tags=USE_DEFAULT,
+                 store_line_numbers=USE_DEFAULT,
+                 string_containers=USE_DEFAULT,
+    ):
+        """Constructor.
+
+        :param multi_valued_attributes: If this is set to None, the
+         TreeBuilder will not turn any values for attributes like
+         'class' into lists. Setting this to a dictionary will
+         customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
+         for an example.
+
+         Internally, these are called "CDATA list attributes", but that
+         probably doesn't make sense to an end-user, so the argument name
+         is `multi_valued_attributes`.
+
+        :param preserve_whitespace_tags: A list of tags to treat
+         the way <pre> tags are treated in HTML. Tags in this list
+         are immune from pretty-printing; their contents will always be
+         output as-is.
+
+        :param string_containers: A dictionary mapping tag names to
+        the classes that should be instantiated to contain the textual
+        contents of those tags. The default is to use NavigableString
+        for every tag, no matter what the name. You can override the
+        default by changing DEFAULT_STRING_CONTAINERS.
+
+        :param store_line_numbers: If the parser keeps track of the
+         line numbers and positions of the original markup, that
+         information will, by default, be stored in each corresponding
+         `Tag` object. You can turn this off by passing
+         store_line_numbers=False. If the parser you're using doesn't 
+         keep track of this information, then setting store_line_numbers=True
+         will do nothing.
+        """
+        self.soup = None
+        if multi_valued_attributes is self.USE_DEFAULT:
+            multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
+        self.cdata_list_attributes = multi_valued_attributes
+        if preserve_whitespace_tags is self.USE_DEFAULT:
+            preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
+        self.preserve_whitespace_tags = preserve_whitespace_tags
+        if store_line_numbers == self.USE_DEFAULT:
+            store_line_numbers = self.TRACKS_LINE_NUMBERS
+        self.store_line_numbers = store_line_numbers 
+        if string_containers == self.USE_DEFAULT:
+            string_containers = self.DEFAULT_STRING_CONTAINERS
+        self.string_containers = string_containers
+        
+    def initialize_soup(self, soup):
+        """The BeautifulSoup object has been initialized and is now
+        being associated with the TreeBuilder.
+
+        :param soup: A BeautifulSoup object.
+        """
+        self.soup = soup
+        
+    def reset(self):
+        """Do any work necessary to reset the underlying parser
+        for a new document.
+
+        By default, this does nothing.
+        """
+        pass
+
+    def can_be_empty_element(self, tag_name):
+        """Might a tag with this name be an empty-element tag?
+
+        The final markup may or may not actually present this tag as
+        self-closing.
+
+        For instance: an HTMLBuilder does not consider a <p> tag to be
+        an empty-element tag (it's not in
+        HTMLBuilder.empty_element_tags). This means an empty <p> tag
+        will be presented as "<p></p>", not "<p/>" or "<p>".
+
+        The default implementation has no opinion about which tags are
+        empty-element tags, so a tag will be presented as an
+        empty-element tag if and only if it has no children.
+        "<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will
+        be left alone.
+
+        :param tag_name: The name of a markup tag.
+        """
+        if self.empty_element_tags is None:
+            return True
+        return tag_name in self.empty_element_tags
+    
+    def feed(self, markup):
+        """Run some incoming markup through some parsing process,
+        populating the `BeautifulSoup` object in self.soup.
+
+        This method is not implemented in TreeBuilder; it must be
+        implemented in subclasses.
+
+        :return: None.
+        """
+        raise NotImplementedError()
+
+    def prepare_markup(self, markup, user_specified_encoding=None,
+                       document_declared_encoding=None, exclude_encodings=None):
+        """Run any preliminary steps necessary to make incoming markup
+        acceptable to the parser.
+
+        :param markup: Some markup -- probably a bytestring.
+        :param user_specified_encoding: The user asked to try this encoding.
+        :param document_declared_encoding: The markup itself claims to be
+            in this encoding. NOTE: This argument is not used by the
+            calling code and can probably be removed.
+        :param exclude_encodings: The user asked _not_ to try any of
+            these encodings.
+
+        :yield: A series of 4-tuples:
+         (markup, encoding, declared encoding,
+          has undergone character replacement)
+
+         Each 4-tuple represents a strategy for converting the
+         document to Unicode and parsing it. Each strategy will be tried 
+         in turn.
+
+         By default, the only strategy is to parse the markup
+         as-is. See `LXMLTreeBuilderForXML` and
+         `HTMLParserTreeBuilder` for implementations that take into
+         account the quirks of particular parsers.
+        """
+        yield markup, None, None, False
+
+    def test_fragment_to_document(self, fragment):
+        """Wrap an HTML fragment to make it look like a document.
+
+        Different parsers do this differently. For instance, lxml
+        introduces an empty <head> tag, and html5lib
+        doesn't. Abstracting this away lets us write simple tests
+        which run HTML fragments through the parser and compare the
+        results against other HTML fragments.
+
+        This method should not be used outside of tests.
+
+        :param fragment: A string -- fragment of HTML.
+        :return: A string -- a full HTML document.
+        """
+        return fragment
+
+    def set_up_substitutions(self, tag):
+        """Set up any substitutions that will need to be performed on 
+        a `Tag` when it's output as a string.
+
+        By default, this does nothing. See `HTMLTreeBuilder` for a
+        case where this is used.
+
+        :param tag: A `Tag`
+        :return: Whether or not a substitution was performed.
+        """
+        return False
+
+    def _replace_cdata_list_attribute_values(self, tag_name, attrs):
+        """When an attribute value is associated with a tag that can
+        have multiple values for that attribute, convert the string
+        value to a list of strings.
+
+        Basically, replaces class="foo bar" with class=["foo", "bar"]
+
+        NOTE: This method modifies its input in place.
+
+        :param tag_name: The name of a tag.
+        :param attrs: A dictionary containing the tag's attributes.
+           Any appropriate attribute values will be modified in place.
+        """
+        if not attrs:
+            return attrs
+        if self.cdata_list_attributes:
+            universal = self.cdata_list_attributes.get('*', [])
+            tag_specific = self.cdata_list_attributes.get(
+                tag_name.lower(), None)
+            for attr in list(attrs.keys()):
+                if attr in universal or (tag_specific and attr in tag_specific):
+                    # We have a "class"-type attribute whose string
+                    # value is a whitespace-separated list of
+                    # values. Split it into a list.
+                    value = attrs[attr]
+                    if isinstance(value, str):
+                        values = nonwhitespace_re.findall(value)
+                    else:
+                        # html5lib sometimes calls setAttributes twice
+                        # for the same tag when rearranging the parse
+                        # tree. On the second call the attribute value
+                        # here is already a list.  If this happens,
+                        # leave the value alone rather than trying to
+                        # split it again.
+                        values = value
+                    attrs[attr] = values
+        return attrs
+
+class SAXTreeBuilder(TreeBuilder):
+    """A Beautiful Soup treebuilder that listens for SAX events.
+
+    This is not currently used for anything, but it demonstrates
+    how a simple TreeBuilder would work.
+    """
+
+    def feed(self, markup):
+        raise NotImplementedError()
+
+    def close(self):
+        pass
+
+    def startElement(self, name, attrs):
+        attrs = dict((key[1], value) for key, value in list(attrs.items()))
+        #print("Start %s, %r" % (name, attrs))
+        self.soup.handle_starttag(name, attrs)
+
+    def endElement(self, name):
+        #print("End %s" % name)
+        self.soup.handle_endtag(name)
+
+    def startElementNS(self, nsTuple, nodeName, attrs):
+        # Throw away (ns, nodeName) for now.
+        self.startElement(nodeName, attrs)
+
+    def endElementNS(self, nsTuple, nodeName):
+        # Throw away (ns, nodeName) for now.
+        self.endElement(nodeName)
+        #handler.endElementNS((ns, node.nodeName), node.nodeName)
+
+    def startPrefixMapping(self, prefix, nodeValue):
+        # Ignore the prefix for now.
+        pass
+
+    def endPrefixMapping(self, prefix):
+        # Ignore the prefix for now.
+        # handler.endPrefixMapping(prefix)
+        pass
+
+    def characters(self, content):
+        self.soup.handle_data(content)
+
+    def startDocument(self):
+        pass
+
+    def endDocument(self):
+        pass
+
+
+class HTMLTreeBuilder(TreeBuilder):
+    """This TreeBuilder knows facts about HTML.
+
+    Such as which tags are empty-element tags.
+    """
+
+    empty_element_tags = set([
+        # These are from HTML5.
+        'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+        
+        # These are from earlier versions of HTML and are removed in HTML5.
+        'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
+    ])
+
+    # The HTML standard defines these as block-level elements. Beautiful
+    # Soup does not treat these elements differently from other elements,
+    # but it may do so eventually, and this information is available if
+    # you need to use it.
+    block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
+
+    # The HTML standard defines an unusual content model for these tags.
+    # We represent this by using a string class other than NavigableString
+    # inside these tags.
+    #
+    # I made this list by going through the HTML spec
+    # (https://html.spec.whatwg.org/#metadata-content) and looking for
+    # "metadata content" elements that can contain strings.
+    #
+    # TODO: Arguably <noscript> could go here but it seems
+    # qualitatively different from the other tags.
+    DEFAULT_STRING_CONTAINERS = {
+        'style': Stylesheet,
+        'script': Script,
+        'template': TemplateString,
+    }    
+    
+    # The HTML standard defines these attributes as containing a
+    # space-separated list of values, not a single value. That is,
+    # class="foo bar" means that the 'class' attribute has two values,
+    # 'foo' and 'bar', not the single value 'foo bar'.  When we
+    # encounter one of these attributes, we will parse its value into
+    # a list of values if possible. Upon output, the list will be
+    # converted back into a string.
+    DEFAULT_CDATA_LIST_ATTRIBUTES = {
+        "*" : ['class', 'accesskey', 'dropzone'],
+        "a" : ['rel', 'rev'],
+        "link" :  ['rel', 'rev'],
+        "td" : ["headers"],
+        "th" : ["headers"],
+        "td" : ["headers"],
+        "form" : ["accept-charset"],
+        "object" : ["archive"],
+
+        # These are HTML5 specific, as are *.accesskey and *.dropzone above.
+        "area" : ["rel"],
+        "icon" : ["sizes"],
+        "iframe" : ["sandbox"],
+        "output" : ["for"],
+        }
+
+    DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
+    
+    def set_up_substitutions(self, tag):
+        """Replace the declared encoding in a <meta> tag with a placeholder,
+        to be substituted when the tag is output to a string.
+
+        An HTML document may come in to Beautiful Soup as one
+        encoding, but exit in a different encoding, and the <meta> tag
+        needs to be changed to reflect this.
+
+        :param tag: A `Tag`
+        :return: Whether or not a substitution was performed.
+        """
+        # We are only interested in <meta> tags
+        if tag.name != 'meta':
+            return False
+
+        http_equiv = tag.get('http-equiv')
+        content = tag.get('content')
+        charset = tag.get('charset')
+
+        # We are interested in <meta> tags that say what encoding the
+        # document was originally in. This means HTML 5-style <meta>
+        # tags that provide the "charset" attribute. It also means
+        # HTML 4-style <meta> tags that provide the "content"
+        # attribute and have "http-equiv" set to "content-type".
+        #
+        # In both cases we will replace the value of the appropriate
+        # attribute with a standin object that can take on any
+        # encoding.
+        meta_encoding = None
+        if charset is not None:
+            # HTML 5 style:
+            # <meta charset="utf8">
+            meta_encoding = charset
+            tag['charset'] = CharsetMetaAttributeValue(charset)
+
+        elif (content is not None and http_equiv is not None
+              and http_equiv.lower() == 'content-type'):
+            # HTML 4 style:
+            # <meta http-equiv="content-type" content="text/html; charset=utf8">
+            tag['content'] = ContentMetaAttributeValue(content)
+
+        return (meta_encoding is not None)
+
+def register_treebuilders_from(module):
+    """Copy TreeBuilders from the given module into this module."""
+    this_module = sys.modules[__name__]
+    for name in module.__all__:
+        obj = getattr(module, name)
+
+        if issubclass(obj, TreeBuilder):
+            setattr(this_module, name, obj)
+            this_module.__all__.append(name)
+            # Register the builder while we're at it.
+            this_module.builder_registry.register(obj)
+
+class ParserRejectedMarkup(Exception):
+    """An Exception to be raised when the underlying parser simply
+    refuses to parse the given markup.
+    """
+    def __init__(self, message_or_exception):
+        """Explain why the parser rejected the given markup, either
+        with a textual explanation or another exception.
+        """
+        if isinstance(message_or_exception, Exception):
+            e = message_or_exception
+            message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
+        super(ParserRejectedMarkup, self).__init__(message_or_exception)
+            
+# Builders are registered in reverse order of priority, so that custom
+# builder registrations will take precedence. In general, we want lxml
+# to take precedence over html5lib, because it's faster. And we only
+# want to use HTMLParser as a last resort.
+from . import _htmlparser
+register_treebuilders_from(_htmlparser)
+try:
+    from . import _html5lib
+    register_treebuilders_from(_html5lib)
+except ImportError:
+    # They don't have html5lib installed.
+    pass
+try:
+    from . import _lxml
+    register_treebuilders_from(_lxml)
+except ImportError:
+    # They don't have lxml installed.
+    pass

IKEA_scrapper/.venv/Lib/site-packages/bs4/builder/_html5lib.py

@@ -0,0 +1,467 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+__all__ = [
+    'HTML5TreeBuilder',
+    ]
+
+import warnings
+import re
+from bs4.builder import (
+    PERMISSIVE,
+    HTML,
+    HTML_5,
+    HTMLTreeBuilder,
+    )
+from bs4.element import (
+    NamespacedAttribute,
+    nonwhitespace_re,
+)
+import html5lib
+from html5lib.constants import (
+    namespaces,
+    prefixes,
+    )
+from bs4.element import (
+    Comment,
+    Doctype,
+    NavigableString,
+    Tag,
+    )
+
+try:
+    # Pre-0.99999999
+    from html5lib.treebuilders import _base as treebuilder_base
+    new_html5lib = False
+except ImportError as e:
+    # 0.99999999 and up
+    from html5lib.treebuilders import base as treebuilder_base
+    new_html5lib = True
+
+class HTML5TreeBuilder(HTMLTreeBuilder):
+    """Use html5lib to build a tree.
+
+    Note that this TreeBuilder does not support some features common
+    to HTML TreeBuilders. Some of these features could theoretically
+    be implemented, but at the very least it's quite difficult,
+    because html5lib moves the parse tree around as it's being built.
+
+    * This TreeBuilder doesn't use different subclasses of NavigableString
+      based on the name of the tag in which the string was found.
+
+    * You can't use a SoupStrainer to parse only part of a document.
+    """
+
+    NAME = "html5lib"
+
+    features = [NAME, PERMISSIVE, HTML_5, HTML]
+
+    # html5lib can tell us which line number and position in the
+    # original file is the source of an element.
+    TRACKS_LINE_NUMBERS = True
+    
+    def prepare_markup(self, markup, user_specified_encoding,
+                       document_declared_encoding=None, exclude_encodings=None):
+        # Store the user-specified encoding for use later on.
+        self.user_specified_encoding = user_specified_encoding
+
+        # document_declared_encoding and exclude_encodings aren't used
+        # ATM because the html5lib TreeBuilder doesn't use
+        # UnicodeDammit.
+        if exclude_encodings:
+            warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
+        yield (markup, None, None, False)
+
+    # These methods are defined by Beautiful Soup.
+    def feed(self, markup):
+        if self.soup.parse_only is not None:
+            warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
+        parser = html5lib.HTMLParser(tree=self.create_treebuilder)
+        self.underlying_builder.parser = parser
+        extra_kwargs = dict()
+        if not isinstance(markup, str):
+            if new_html5lib:
+                extra_kwargs['override_encoding'] = self.user_specified_encoding
+            else:
+                extra_kwargs['encoding'] = self.user_specified_encoding
+        doc = parser.parse(markup, **extra_kwargs)
+        
+        # Set the character encoding detected by the tokenizer.
+        if isinstance(markup, str):
+            # We need to special-case this because html5lib sets
+            # charEncoding to UTF-8 if it gets Unicode input.
+            doc.original_encoding = None
+        else:
+            original_encoding = parser.tokenizer.stream.charEncoding[0]
+            if not isinstance(original_encoding, str):
+                # In 0.99999999 and up, the encoding is an html5lib
+                # Encoding object. We want to use a string for compatibility
+                # with other tree builders.
+                original_encoding = original_encoding.name
+            doc.original_encoding = original_encoding
+        self.underlying_builder.parser = None
+            
+    def create_treebuilder(self, namespaceHTMLElements):
+        self.underlying_builder = TreeBuilderForHtml5lib(
+            namespaceHTMLElements, self.soup,
+            store_line_numbers=self.store_line_numbers
+        )
+        return self.underlying_builder
+
+    def test_fragment_to_document(self, fragment):
+        """See `TreeBuilder`."""
+        return '<html><head></head><body>%s</body></html>' % fragment
+
+
+class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
+    
+    def __init__(self, namespaceHTMLElements, soup=None,
+                 store_line_numbers=True, **kwargs):
+        if soup:
+            self.soup = soup
+        else:
+            from bs4 import BeautifulSoup
+            # TODO: Why is the parser 'html.parser' here? To avoid an
+            # infinite loop?
+            self.soup = BeautifulSoup(
+                "", "html.parser", store_line_numbers=store_line_numbers,
+                **kwargs
+            )
+        # TODO: What are **kwargs exactly? Should they be passed in
+        # here in addition to/instead of being passed to the BeautifulSoup
+        # constructor?
+        super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
+
+        # This will be set later to an html5lib.html5parser.HTMLParser
+        # object, which we can use to track the current line number.
+        self.parser = None
+        self.store_line_numbers = store_line_numbers
+        
+    def documentClass(self):
+        self.soup.reset()
+        return Element(self.soup, self.soup, None)
+
+    def insertDoctype(self, token):
+        name = token["name"]
+        publicId = token["publicId"]
+        systemId = token["systemId"]
+
+        doctype = Doctype.for_name_and_ids(name, publicId, systemId)
+        self.soup.object_was_parsed(doctype)
+
+    def elementClass(self, name, namespace):
+        kwargs = {}
+        if self.parser and self.store_line_numbers:
+            # This represents the point immediately after the end of the
+            # tag. We don't know when the tag started, but we do know
+            # where it ended -- the character just before this one.
+            sourceline, sourcepos = self.parser.tokenizer.stream.position()
+            kwargs['sourceline'] = sourceline
+            kwargs['sourcepos'] = sourcepos-1
+        tag = self.soup.new_tag(name, namespace, **kwargs)
+
+        return Element(tag, self.soup, namespace)
+
+    def commentClass(self, data):
+        return TextNode(Comment(data), self.soup)
+
+    def fragmentClass(self):
+        from bs4 import BeautifulSoup
+        # TODO: Why is the parser 'html.parser' here? To avoid an
+        # infinite loop?
+        self.soup = BeautifulSoup("", "html.parser")
+        self.soup.name = "[document_fragment]"
+        return Element(self.soup, self.soup, None)
+
+    def appendChild(self, node):
+        # XXX This code is not covered by the BS4 tests.
+        self.soup.append(node.element)
+
+    def getDocument(self):
+        return self.soup
+
+    def getFragment(self):
+        return treebuilder_base.TreeBuilder.getFragment(self).element
+
+    def testSerializer(self, element):
+        from bs4 import BeautifulSoup
+        rv = []
+        doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
+
+        def serializeElement(element, indent=0):
+            if isinstance(element, BeautifulSoup):
+                pass
+            if isinstance(element, Doctype):
+                m = doctype_re.match(element)
+                if m:
+                    name = m.group(1)
+                    if m.lastindex > 1:
+                        publicId = m.group(2) or ""
+                        systemId = m.group(3) or m.group(4) or ""
+                        rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
+                                  (' ' * indent, name, publicId, systemId))
+                    else:
+                        rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
+                else:
+                    rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
+            elif isinstance(element, Comment):
+                rv.append("|%s<!-- %s -->" % (' ' * indent, element))
+            elif isinstance(element, NavigableString):
+                rv.append("|%s\"%s\"" % (' ' * indent, element))
+            else:
+                if element.namespace:
+                    name = "%s %s" % (prefixes[element.namespace],
+                                      element.name)
+                else:
+                    name = element.name
+                rv.append("|%s<%s>" % (' ' * indent, name))
+                if element.attrs:
+                    attributes = []
+                    for name, value in list(element.attrs.items()):
+                        if isinstance(name, NamespacedAttribute):
+                            name = "%s %s" % (prefixes[name.namespace], name.name)
+                        if isinstance(value, list):
+                            value = " ".join(value)
+                        attributes.append((name, value))
+
+                    for name, value in sorted(attributes):
+                        rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
+                indent += 2
+                for child in element.children:
+                    serializeElement(child, indent)
+        serializeElement(element, 0)
+
+        return "\n".join(rv)
+
+class AttrList(object):
+    def __init__(self, element):
+        self.element = element
+        self.attrs = dict(self.element.attrs)
+    def __iter__(self):
+        return list(self.attrs.items()).__iter__()
+    def __setitem__(self, name, value):
+        # If this attribute is a multi-valued attribute for this element,
+        # turn its value into a list.
+        list_attr = self.element.cdata_list_attributes
+        if (name in list_attr['*']
+            or (self.element.name in list_attr
+                and name in list_attr[self.element.name])):
+            # A node that is being cloned may have already undergone
+            # this procedure.
+            if not isinstance(value, list):
+                value = nonwhitespace_re.findall(value)
+        self.element[name] = value
+    def items(self):
+        return list(self.attrs.items())
+    def keys(self):
+        return list(self.attrs.keys())
+    def __len__(self):
+        return len(self.attrs)
+    def __getitem__(self, name):
+        return self.attrs[name]
+    def __contains__(self, name):
+        return name in list(self.attrs.keys())
+
+
+class Element(treebuilder_base.Node):
+    def __init__(self, element, soup, namespace):
+        treebuilder_base.Node.__init__(self, element.name)
+        self.element = element
+        self.soup = soup
+        self.namespace = namespace
+
+    def appendChild(self, node):
+        string_child = child = None
+        if isinstance(node, str):
+            # Some other piece of code decided to pass in a string
+            # instead of creating a TextElement object to contain the
+            # string.
+            string_child = child = node
+        elif isinstance(node, Tag):
+            # Some other piece of code decided to pass in a Tag
+            # instead of creating an Element object to contain the
+            # Tag.
+            child = node
+        elif node.element.__class__ == NavigableString:
+            string_child = child = node.element
+            node.parent = self
+        else:
+            child = node.element
+            node.parent = self
+
+        if not isinstance(child, str) and child.parent is not None:
+            node.element.extract()
+
+        if (string_child is not None and self.element.contents
+            and self.element.contents[-1].__class__ == NavigableString):
+            # We are appending a string onto another string.
+            # TODO This has O(n^2) performance, for input like
+            # "a</a>a</a>a</a>..."
+            old_element = self.element.contents[-1]
+            new_element = self.soup.new_string(old_element + string_child)
+            old_element.replace_with(new_element)
+            self.soup._most_recent_element = new_element
+        else:
+            if isinstance(node, str):
+                # Create a brand new NavigableString from this string.
+                child = self.soup.new_string(node)
+
+            # Tell Beautiful Soup to act as if it parsed this element
+            # immediately after the parent's last descendant. (Or
+            # immediately after the parent, if it has no children.)
+            if self.element.contents:
+                most_recent_element = self.element._last_descendant(False)
+            elif self.element.next_element is not None:
+                # Something from further ahead in the parse tree is
+                # being inserted into this earlier element. This is
+                # very annoying because it means an expensive search
+                # for the last element in the tree.
+                most_recent_element = self.soup._last_descendant()
+            else:
+                most_recent_element = self.element
+
+            self.soup.object_was_parsed(
+                child, parent=self.element,
+                most_recent_element=most_recent_element)
+
+    def getAttributes(self):
+        if isinstance(self.element, Comment):
+            return {}
+        return AttrList(self.element)
+
+    def setAttributes(self, attributes):
+        if attributes is not None and len(attributes) > 0:
+            converted_attributes = []
+            for name, value in list(attributes.items()):
+                if isinstance(name, tuple):
+                    new_name = NamespacedAttribute(*name)
+                    del attributes[name]
+                    attributes[new_name] = value
+
+            self.soup.builder._replace_cdata_list_attribute_values(
+                self.name, attributes)
+            for name, value in list(attributes.items()):
+                self.element[name] = value
+
+            # The attributes may contain variables that need substitution.
+            # Call set_up_substitutions manually.
+            #
+            # The Tag constructor called this method when the Tag was created,
+            # but we just set/changed the attributes, so call it again.
+            self.soup.builder.set_up_substitutions(self.element)
+    attributes = property(getAttributes, setAttributes)
+
+    def insertText(self, data, insertBefore=None):
+        text = TextNode(self.soup.new_string(data), self.soup)
+        if insertBefore:
+            self.insertBefore(text, insertBefore)
+        else:
+            self.appendChild(text)
+
+    def insertBefore(self, node, refNode):
+        index = self.element.index(refNode.element)
+        if (node.element.__class__ == NavigableString and self.element.contents
+            and self.element.contents[index-1].__class__ == NavigableString):
+            # (See comments in appendChild)
+            old_node = self.element.contents[index-1]
+            new_str = self.soup.new_string(old_node + node.element)
+            old_node.replace_with(new_str)
+        else:
+            self.element.insert(index, node.element)
+            node.parent = self
+
+    def removeChild(self, node):
+        node.element.extract()
+
+    def reparentChildren(self, new_parent):
+        """Move all of this tag's children into another tag."""
+        # print("MOVE", self.element.contents)
+        # print("FROM", self.element)
+        # print("TO", new_parent.element)
+
+        element = self.element
+        new_parent_element = new_parent.element
+        # Determine what this tag's next_element will be once all the children
+        # are removed.
+        final_next_element = element.next_sibling
+
+        new_parents_last_descendant = new_parent_element._last_descendant(False, False)
+        if len(new_parent_element.contents) > 0:
+            # The new parent already contains children. We will be
+            # appending this tag's children to the end.
+            new_parents_last_child = new_parent_element.contents[-1]
+            new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
+        else:
+            # The new parent contains no children.
+            new_parents_last_child = None
+            new_parents_last_descendant_next_element = new_parent_element.next_element
+
+        to_append = element.contents
+        if len(to_append) > 0:
+            # Set the first child's previous_element and previous_sibling
+            # to elements within the new parent
+            first_child = to_append[0]
+            if new_parents_last_descendant is not None:
+                first_child.previous_element = new_parents_last_descendant
+            else:
+                first_child.previous_element = new_parent_element
+            first_child.previous_sibling = new_parents_last_child
+            if new_parents_last_descendant is not None:
+                new_parents_last_descendant.next_element = first_child
+            else:
+                new_parent_element.next_element = first_child
+            if new_parents_last_child is not None:
+                new_parents_last_child.next_sibling = first_child
+
+            # Find the very last element being moved. It is now the
+            # parent's last descendant. It has no .next_sibling and
+            # its .next_element is whatever the previous last
+            # descendant had.
+            last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
+
+            last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
+            if new_parents_last_descendant_next_element is not None:
+                # TODO: This code has no test coverage and I'm not sure
+                # how to get html5lib to go through this path, but it's
+                # just the other side of the previous line.
+                new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
+            last_childs_last_descendant.next_sibling = None
+
+        for child in to_append:
+            child.parent = new_parent_element
+            new_parent_element.contents.append(child)
+
+        # Now that this element has no children, change its .next_element.
+        element.contents = []
+        element.next_element = final_next_element
+
+        # print("DONE WITH MOVE")
+        # print("FROM", self.element)
+        # print("TO", new_parent_element)
+
+    def cloneNode(self):
+        tag = self.soup.new_tag(self.element.name, self.namespace)
+        node = Element(tag, self.soup, self.namespace)
+        for key,value in self.attributes:
+            node.attributes[key] = value
+        return node
+
+    def hasContent(self):
+        return self.element.contents
+
+    def getNameTuple(self):
+        if self.namespace == None:
+            return namespaces["html"], self.name
+        else:
+            return self.namespace, self.name
+
+    nameTuple = property(getNameTuple)
+
+class TextNode(Element):
+    def __init__(self, element, soup):
+        treebuilder_base.Node.__init__(self, None)
+        self.element = element
+        self.soup = soup
+
+    def cloneNode(self):
+        raise NotImplementedError

IKEA_scrapper/.venv/Lib/site-packages/bs4/builder/_htmlparser.py

@@ -0,0 +1,492 @@
+# encoding: utf-8
+"""Use the HTMLParser library to parse HTML files that aren't too bad."""
+
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+__all__ = [
+    'HTMLParserTreeBuilder',
+    ]
+
+from html.parser import HTMLParser
+
+try:
+    from html.parser import HTMLParseError
+except ImportError as e:
+    # HTMLParseError is removed in Python 3.5. Since it can never be
+    # thrown in 3.5, we can just define our own class as a placeholder.
+    class HTMLParseError(Exception):
+        pass
+
+import sys
+import warnings
+
+# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
+# argument, which we'd like to set to False. Unfortunately,
+# http://bugs.python.org/issue13273 makes strict=True a better bet
+# before Python 3.2.3.
+#
+# At the end of this file, we monkeypatch HTMLParser so that
+# strict=True works well on Python 3.2.2.
+major, minor, release = sys.version_info[:3]
+CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
+CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
+CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
+
+
+from bs4.element import (
+    CData,
+    Comment,
+    Declaration,
+    Doctype,
+    ProcessingInstruction,
+    )
+from bs4.dammit import EntitySubstitution, UnicodeDammit
+
+from bs4.builder import (
+    HTML,
+    HTMLTreeBuilder,
+    STRICT,
+    )
+
+
+HTMLPARSER = 'html.parser'
+
+class BeautifulSoupHTMLParser(HTMLParser):
+    """A subclass of the Python standard library's HTMLParser class, which
+    listens for HTMLParser events and translates them into calls
+    to Beautiful Soup's tree construction API.
+    """
+
+    # Strategies for handling duplicate attributes
+    IGNORE = 'ignore'
+    REPLACE = 'replace'
+    
+    def __init__(self, *args, **kwargs):
+        """Constructor.
+
+        :param on_duplicate_attribute: A strategy for what to do if a
+            tag includes the same attribute more than once. Accepted
+            values are: REPLACE (replace earlier values with later
+            ones, the default), IGNORE (keep the earliest value
+            encountered), or a callable. A callable must take three
+            arguments: the dictionary of attributes already processed,
+            the name of the duplicate attribute, and the most recent value
+            encountered.           
+        """
+        self.on_duplicate_attribute = kwargs.pop(
+            'on_duplicate_attribute', self.REPLACE
+        )
+        HTMLParser.__init__(self, *args, **kwargs)
+
+        # Keep a list of empty-element tags that were encountered
+        # without an explicit closing tag. If we encounter a closing tag
+        # of this type, we'll associate it with one of those entries.
+        #
+        # This isn't a stack because we don't care about the
+        # order. It's a list of closing tags we've already handled and
+        # will ignore, assuming they ever show up.
+        self.already_closed_empty_element = []
+
+    def error(self, msg):
+        """In Python 3, HTMLParser subclasses must implement error(), although
+        this requirement doesn't appear to be documented.
+
+        In Python 2, HTMLParser implements error() by raising an exception,
+        which we don't want to do.
+
+        In any event, this method is called only on very strange
+        markup and our best strategy is to pretend it didn't happen
+        and keep going.
+        """
+        warnings.warn(msg)
+        
+    def handle_startendtag(self, name, attrs):
+        """Handle an incoming empty-element tag.
+
+        This is only called when the markup looks like <tag/>.
+
+        :param name: Name of the tag.
+        :param attrs: Dictionary of the tag's attributes.
+        """
+        # is_startend() tells handle_starttag not to close the tag
+        # just because its name matches a known empty-element tag. We
+        # know that this is an empty-element tag and we want to call
+        # handle_endtag ourselves.
+        tag = self.handle_starttag(name, attrs, handle_empty_element=False)
+        self.handle_endtag(name)
+        
+    def handle_starttag(self, name, attrs, handle_empty_element=True):
+        """Handle an opening tag, e.g. '<tag>'
+
+        :param name: Name of the tag.
+        :param attrs: Dictionary of the tag's attributes.
+        :param handle_empty_element: True if this tag is known to be
+            an empty-element tag (i.e. there is not expected to be any
+            closing tag).
+        """
+        # XXX namespace
+        attr_dict = {}
+        for key, value in attrs:
+            # Change None attribute values to the empty string
+            # for consistency with the other tree builders.
+            if value is None:
+                value = ''
+            if key in attr_dict:
+                # A single attribute shows up multiple times in this
+                # tag. How to handle it depends on the
+                # on_duplicate_attribute setting.
+                on_dupe = self.on_duplicate_attribute
+                if on_dupe == self.IGNORE:
+                    pass
+                elif on_dupe in (None, self.REPLACE):
+                    attr_dict[key] = value
+                else:
+                    on_dupe(attr_dict, key, value)
+            else:
+                attr_dict[key] = value
+            attrvalue = '""'
+        #print("START", name)
+        sourceline, sourcepos = self.getpos()
+        tag = self.soup.handle_starttag(
+            name, None, None, attr_dict, sourceline=sourceline,
+            sourcepos=sourcepos
+        )
+        if tag and tag.is_empty_element and handle_empty_element:
+            # Unlike other parsers, html.parser doesn't send separate end tag
+            # events for empty-element tags. (It's handled in
+            # handle_startendtag, but only if the original markup looked like
+            # <tag/>.)
+            #
+            # So we need to call handle_endtag() ourselves. Since we
+            # know the start event is identical to the end event, we
+            # don't want handle_endtag() to cross off any previous end
+            # events for tags of this name.
+            self.handle_endtag(name, check_already_closed=False)
+
+            # But we might encounter an explicit closing tag for this tag
+            # later on. If so, we want to ignore it.
+            self.already_closed_empty_element.append(name)
+            
+    def handle_endtag(self, name, check_already_closed=True):
+        """Handle a closing tag, e.g. '</tag>'
+        
+        :param name: A tag name.
+        :param check_already_closed: True if this tag is expected to
+           be the closing portion of an empty-element tag,
+           e.g. '<tag></tag>'.
+        """
+        #print("END", name)
+        if check_already_closed and name in self.already_closed_empty_element:
+            # This is a redundant end tag for an empty-element tag.
+            # We've already called handle_endtag() for it, so just
+            # check it off the list.
+            #print("ALREADY CLOSED", name)
+            self.already_closed_empty_element.remove(name)
+        else:
+            self.soup.handle_endtag(name)
+
+    def handle_data(self, data):
+        """Handle some textual data that shows up between tags."""
+        self.soup.handle_data(data)
+
+    def handle_charref(self, name):
+        """Handle a numeric character reference by converting it to the
+        corresponding Unicode character and treating it as textual
+        data.
+
+        :param name: Character number, possibly in hexadecimal.
+        """
+        # XXX workaround for a bug in HTMLParser. Remove this once
+        # it's fixed in all supported versions.
+        # http://bugs.python.org/issue13633
+        if name.startswith('x'):
+            real_name = int(name.lstrip('x'), 16)
+        elif name.startswith('X'):
+            real_name = int(name.lstrip('X'), 16)
+        else:
+            real_name = int(name)
+
+        data = None
+        if real_name < 256:
+            # HTML numeric entities are supposed to reference Unicode
+            # code points, but sometimes they reference code points in
+            # some other encoding (ahem, Windows-1252). E.g. &#147;
+            # instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
+            # code tries to detect this situation and compensate.
+            for encoding in (self.soup.original_encoding, 'windows-1252'):
+                if not encoding:
+                    continue
+                try:
+                    data = bytearray([real_name]).decode(encoding)
+                except UnicodeDecodeError as e:
+                    pass
+        if not data:
+            try:
+                data = chr(real_name)
+            except (ValueError, OverflowError) as e:
+                pass
+        data = data or "\N{REPLACEMENT CHARACTER}"
+        self.handle_data(data)
+
+    def handle_entityref(self, name):
+        """Handle a named entity reference by converting it to the
+        corresponding Unicode character(s) and treating it as textual
+        data.
+
+        :param name: Name of the entity reference.
+        """
+        character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
+        if character is not None:
+            data = character
+        else:
+            # If this were XML, it would be ambiguous whether "&foo"
+            # was an character entity reference with a missing
+            # semicolon or the literal string "&foo". Since this is
+            # HTML, we have a complete list of all character entity references,
+            # and this one wasn't found, so assume it's the literal string "&foo".
+            data = "&%s" % name
+        self.handle_data(data)
+
+    def handle_comment(self, data):
+        """Handle an HTML comment.
+
+        :param data: The text of the comment.
+        """
+        self.soup.endData()
+        self.soup.handle_data(data)
+        self.soup.endData(Comment)
+
+    def handle_decl(self, data):
+        """Handle a DOCTYPE declaration.
+
+        :param data: The text of the declaration.
+        """
+        self.soup.endData()
+        data = data[len("DOCTYPE "):]
+        self.soup.handle_data(data)
+        self.soup.endData(Doctype)
+
+    def unknown_decl(self, data):
+        """Handle a declaration of unknown type -- probably a CDATA block.
+
+        :param data: The text of the declaration.
+        """
+        if data.upper().startswith('CDATA['):
+            cls = CData
+            data = data[len('CDATA['):]
+        else:
+            cls = Declaration
+        self.soup.endData()
+        self.soup.handle_data(data)
+        self.soup.endData(cls)
+
+    def handle_pi(self, data):
+        """Handle a processing instruction.
+
+        :param data: The text of the instruction.
+        """
+        self.soup.endData()
+        self.soup.handle_data(data)
+        self.soup.endData(ProcessingInstruction)
+
+
+class HTMLParserTreeBuilder(HTMLTreeBuilder):
+    """A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
+    found in the Python standard library.
+    """
+    is_xml = False
+    picklable = True
+    NAME = HTMLPARSER
+    features = [NAME, HTML, STRICT]
+
+    # The html.parser knows which line number and position in the
+    # original file is the source of an element.
+    TRACKS_LINE_NUMBERS = True
+
+    def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
+        """Constructor.
+
+        :param parser_args: Positional arguments to pass into 
+            the BeautifulSoupHTMLParser constructor, once it's
+            invoked.
+        :param parser_kwargs: Keyword arguments to pass into 
+            the BeautifulSoupHTMLParser constructor, once it's
+            invoked.
+        :param kwargs: Keyword arguments for the superclass constructor.
+        """
+        # Some keyword arguments will be pulled out of kwargs and placed
+        # into parser_kwargs.
+        extra_parser_kwargs = dict()
+        for arg in ('on_duplicate_attribute',):
+            if arg in kwargs:
+                value = kwargs.pop(arg)
+                extra_parser_kwargs[arg] = value
+        super(HTMLParserTreeBuilder, self).__init__(**kwargs)
+        parser_args = parser_args or []
+        parser_kwargs = parser_kwargs or {}
+        parser_kwargs.update(extra_parser_kwargs)
+        if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
+            parser_kwargs['strict'] = False
+        if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
+            parser_kwargs['convert_charrefs'] = False
+        self.parser_args = (parser_args, parser_kwargs)
+        
+    def prepare_markup(self, markup, user_specified_encoding=None,
+                       document_declared_encoding=None, exclude_encodings=None):
+
+        """Run any preliminary steps necessary to make incoming markup
+        acceptable to the parser.
+
+        :param markup: Some markup -- probably a bytestring.
+        :param user_specified_encoding: The user asked to try this encoding.
+        :param document_declared_encoding: The markup itself claims to be
+            in this encoding.
+        :param exclude_encodings: The user asked _not_ to try any of
+            these encodings.
+
+        :yield: A series of 4-tuples:
+         (markup, encoding, declared encoding,
+          has undergone character replacement)
+
+         Each 4-tuple represents a strategy for converting the
+         document to Unicode and parsing it. Each strategy will be tried 
+         in turn.
+        """
+        if isinstance(markup, str):
+            # Parse Unicode as-is.
+            yield (markup, None, None, False)
+            return
+
+        # Ask UnicodeDammit to sniff the most likely encoding.
+
+        # This was provided by the end-user; treat it as a known
+        # definite encoding per the algorithm laid out in the HTML5
+        # spec.  (See the EncodingDetector class for details.)
+        known_definite_encodings = [user_specified_encoding]
+
+        # This was found in the document; treat it as a slightly lower-priority
+        # user encoding.
+        user_encodings = [document_declared_encoding]
+
+        try_encodings = [user_specified_encoding, document_declared_encoding]
+        dammit = UnicodeDammit(
+            markup,
+            known_definite_encodings=known_definite_encodings,
+            user_encodings=user_encodings,
+            is_html=True,
+            exclude_encodings=exclude_encodings
+        )
+        yield (dammit.markup, dammit.original_encoding,
+               dammit.declared_html_encoding,
+               dammit.contains_replacement_characters)
+
+    def feed(self, markup):
+        """Run some incoming markup through some parsing process,
+        populating the `BeautifulSoup` object in self.soup.
+        """
+        args, kwargs = self.parser_args
+        parser = BeautifulSoupHTMLParser(*args, **kwargs)
+        parser.soup = self.soup
+        try:
+            parser.feed(markup)
+            parser.close()
+        except HTMLParseError as e:
+            warnings.warn(RuntimeWarning(
+                "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
+            raise e
+        parser.already_closed_empty_element = []
+
+# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
+# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
+# string.
+#
+# XXX This code can be removed once most Python 3 users are on 3.2.3.
+if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
+    import re
+    attrfind_tolerant = re.compile(
+        r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
+        r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
+    HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
+
+    locatestarttagend = re.compile(r"""
+  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
+  (?:\s+                             # whitespace before attribute name
+    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
+      (?:\s*=\s*                     # value indicator
+        (?:'[^']*'                   # LITA-enclosed value
+          |\"[^\"]*\"                # LIT-enclosed value
+          |[^'\">\s]+                # bare value
+         )
+       )?
+     )
+   )*
+  \s*                                # trailing whitespace
+""", re.VERBOSE)
+    BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
+
+    from html.parser import tagfind, attrfind
+
+    def parse_starttag(self, i):
+        self.__starttag_text = None
+        endpos = self.check_for_whole_start_tag(i)
+        if endpos < 0:
+            return endpos
+        rawdata = self.rawdata
+        self.__starttag_text = rawdata[i:endpos]
+
+        # Now parse the data between i+1 and j into a tag and attrs
+        attrs = []
+        match = tagfind.match(rawdata, i+1)
+        assert match, 'unexpected call to parse_starttag()'
+        k = match.end()
+        self.lasttag = tag = rawdata[i+1:k].lower()
+        while k < endpos:
+            if self.strict:
+                m = attrfind.match(rawdata, k)
+            else:
+                m = attrfind_tolerant.match(rawdata, k)
+            if not m:
+                break
+            attrname, rest, attrvalue = m.group(1, 2, 3)
+            if not rest:
+                attrvalue = None
+            elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
+                 attrvalue[:1] == '"' == attrvalue[-1:]:
+                attrvalue = attrvalue[1:-1]
+            if attrvalue:
+                attrvalue = self.unescape(attrvalue)
+            attrs.append((attrname.lower(), attrvalue))
+            k = m.end()
+
+        end = rawdata[k:endpos].strip()
+        if end not in (">", "/>"):
+            lineno, offset = self.getpos()
+            if "\n" in self.__starttag_text:
+                lineno = lineno + self.__starttag_text.count("\n")
+                offset = len(self.__starttag_text) \
+                         - self.__starttag_text.rfind("\n")
+            else:
+                offset = offset + len(self.__starttag_text)
+            if self.strict:
+                self.error("junk characters in start tag: %r"
+                           % (rawdata[k:endpos][:20],))
+            self.handle_data(rawdata[i:endpos])
+            return endpos
+        if end.endswith('/>'):
+            # XHTML-style empty tag: <span attr="value" />
+            self.handle_startendtag(tag, attrs)
+        else:
+            self.handle_starttag(tag, attrs)
+            if tag in self.CDATA_CONTENT_ELEMENTS:
+                self.set_cdata_mode(tag)
+        return endpos
+
+    def set_cdata_mode(self, elem):
+        self.cdata_elem = elem.lower()
+        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
+
+    BeautifulSoupHTMLParser.parse_starttag = parse_starttag
+    BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
+
+    CONSTRUCTOR_TAKES_STRICT = True

IKEA_scrapper/.venv/Lib/site-packages/bs4/builder/_lxml.py

@@ -0,0 +1,342 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+__all__ = [
+    'LXMLTreeBuilderForXML',
+    'LXMLTreeBuilder',
+    ]
+
+try:
+    from collections.abc import Callable # Python 3.6
+except ImportError as e:
+    from collections import Callable
+
+from io import BytesIO
+from io import StringIO
+from lxml import etree
+from bs4.element import (
+    Comment,
+    Doctype,
+    NamespacedAttribute,
+    ProcessingInstruction,
+    XMLProcessingInstruction,
+)
+from bs4.builder import (
+    FAST,
+    HTML,
+    HTMLTreeBuilder,
+    PERMISSIVE,
+    ParserRejectedMarkup,
+    TreeBuilder,
+    XML)
+from bs4.dammit import EncodingDetector
+
+LXML = 'lxml'
+
+def _invert(d):
+    "Invert a dictionary."
+    return dict((v,k) for k, v in list(d.items()))
+
+class LXMLTreeBuilderForXML(TreeBuilder):
+    DEFAULT_PARSER_CLASS = etree.XMLParser
+
+    is_xml = True
+    processing_instruction_class = XMLProcessingInstruction
+
+    NAME = "lxml-xml"
+    ALTERNATE_NAMES = ["xml"]
+
+    # Well, it's permissive by XML parser standards.
+    features = [NAME, LXML, XML, FAST, PERMISSIVE]
+
+    CHUNK_SIZE = 512
+
+    # This namespace mapping is specified in the XML Namespace
+    # standard.
+    DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
+
+    DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
+
+    # NOTE: If we parsed Element objects and looked at .sourceline,
+    # we'd be able to see the line numbers from the original document.
+    # But instead we build an XMLParser or HTMLParser object to serve
+    # as the target of parse messages, and those messages don't include
+    # line numbers.
+    # See: https://bugs.launchpad.net/lxml/+bug/1846906
+    
+    def initialize_soup(self, soup):
+        """Let the BeautifulSoup object know about the standard namespace
+        mapping.
+
+        :param soup: A `BeautifulSoup`.
+        """
+        super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
+        self._register_namespaces(self.DEFAULT_NSMAPS)
+
+    def _register_namespaces(self, mapping):
+        """Let the BeautifulSoup object know about namespaces encountered
+        while parsing the document.
+
+        This might be useful later on when creating CSS selectors.
+
+        :param mapping: A dictionary mapping namespace prefixes to URIs.
+        """
+        for key, value in list(mapping.items()):
+            if key and key not in self.soup._namespaces:
+                # Let the BeautifulSoup object know about a new namespace.
+                # If there are multiple namespaces defined with the same
+                # prefix, the first one in the document takes precedence.
+                self.soup._namespaces[key] = value
+
+    def default_parser(self, encoding):
+        """Find the default parser for the given encoding.
+
+        :param encoding: A string.
+        :return: Either a parser object or a class, which
+          will be instantiated with default arguments.
+        """
+        if self._default_parser is not None:
+            return self._default_parser
+        return etree.XMLParser(
+            target=self, strip_cdata=False, recover=True, encoding=encoding)
+
+    def parser_for(self, encoding):
+        """Instantiate an appropriate parser for the given encoding.
+
+        :param encoding: A string.
+        :return: A parser object such as an `etree.XMLParser`.
+        """
+        # Use the default parser.
+        parser = self.default_parser(encoding)
+
+        if isinstance(parser, Callable):
+            # Instantiate the parser with default arguments
+            parser = parser(
+                target=self, strip_cdata=False, recover=True, encoding=encoding
+            )
+        return parser
+
+    def __init__(self, parser=None, empty_element_tags=None, **kwargs):
+        # TODO: Issue a warning if parser is present but not a
+        # callable, since that means there's no way to create new
+        # parsers for different encodings.
+        self._default_parser = parser
+        if empty_element_tags is not None:
+            self.empty_element_tags = set(empty_element_tags)
+        self.soup = None
+        self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
+        super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
+        
+    def _getNsTag(self, tag):
+        # Split the namespace URL out of a fully-qualified lxml tag
+        # name. Copied from lxml's src/lxml/sax.py.
+        if tag[0] == '{':
+            return tuple(tag[1:].split('}', 1))
+        else:
+            return (None, tag)
+
+    def prepare_markup(self, markup, user_specified_encoding=None,
+                       exclude_encodings=None,
+                       document_declared_encoding=None):
+        """Run any preliminary steps necessary to make incoming markup
+        acceptable to the parser.
+
+        lxml really wants to get a bytestring and convert it to
+        Unicode itself. So instead of using UnicodeDammit to convert
+        the bytestring to Unicode using different encodings, this
+        implementation uses EncodingDetector to iterate over the
+        encodings, and tell lxml to try to parse the document as each
+        one in turn.
+
+        :param markup: Some markup -- hopefully a bytestring.
+        :param user_specified_encoding: The user asked to try this encoding.
+        :param document_declared_encoding: The markup itself claims to be
+            in this encoding.
+        :param exclude_encodings: The user asked _not_ to try any of
+            these encodings.
+
+        :yield: A series of 4-tuples:
+         (markup, encoding, declared encoding,
+          has undergone character replacement)
+
+         Each 4-tuple represents a strategy for converting the
+         document to Unicode and parsing it. Each strategy will be tried 
+         in turn.
+        """
+        is_html = not self.is_xml
+        if is_html:
+            self.processing_instruction_class = ProcessingInstruction
+        else:
+            self.processing_instruction_class = XMLProcessingInstruction
+
+        if isinstance(markup, str):
+            # We were given Unicode. Maybe lxml can parse Unicode on
+            # this system?
+            yield markup, None, document_declared_encoding, False
+
+        if isinstance(markup, str):
+            # No, apparently not. Convert the Unicode to UTF-8 and
+            # tell lxml to parse it as UTF-8.
+            yield (markup.encode("utf8"), "utf8",
+                   document_declared_encoding, False)
+
+        # This was provided by the end-user; treat it as a known
+        # definite encoding per the algorithm laid out in the HTML5
+        # spec.  (See the EncodingDetector class for details.)
+        known_definite_encodings = [user_specified_encoding]
+
+        # This was found in the document; treat it as a slightly lower-priority
+        # user encoding.
+        user_encodings = [document_declared_encoding]
+        detector = EncodingDetector(
+            markup, known_definite_encodings=known_definite_encodings,
+            user_encodings=user_encodings, is_html=is_html,
+            exclude_encodings=exclude_encodings
+        )
+        for encoding in detector.encodings:
+            yield (detector.markup, encoding, document_declared_encoding, False)
+
+    def feed(self, markup):
+        if isinstance(markup, bytes):
+            markup = BytesIO(markup)
+        elif isinstance(markup, str):
+            markup = StringIO(markup)
+
+        # Call feed() at least once, even if the markup is empty,
+        # or the parser won't be initialized.
+        data = markup.read(self.CHUNK_SIZE)
+        try:
+            self.parser = self.parser_for(self.soup.original_encoding)
+            self.parser.feed(data)
+            while len(data) != 0:
+                # Now call feed() on the rest of the data, chunk by chunk.
+                data = markup.read(self.CHUNK_SIZE)
+                if len(data) != 0:
+                    self.parser.feed(data)
+            self.parser.close()
+        except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
+            raise ParserRejectedMarkup(e)
+
+    def close(self):
+        self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
+
+    def start(self, name, attrs, nsmap={}):
+        # Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
+        attrs = dict(attrs)
+        nsprefix = None
+        # Invert each namespace map as it comes in.
+        if len(nsmap) == 0 and len(self.nsmaps) > 1:
+                # There are no new namespaces for this tag, but
+                # non-default namespaces are in play, so we need a
+                # separate tag stack to know when they end.
+                self.nsmaps.append(None)
+        elif len(nsmap) > 0:
+            # A new namespace mapping has come into play.
+
+            # First, Let the BeautifulSoup object know about it.
+            self._register_namespaces(nsmap)
+
+            # Then, add it to our running list of inverted namespace
+            # mappings.
+            self.nsmaps.append(_invert(nsmap))
+
+            # Also treat the namespace mapping as a set of attributes on the
+            # tag, so we can recreate it later.
+            attrs = attrs.copy()
+            for prefix, namespace in list(nsmap.items()):
+                attribute = NamespacedAttribute(
+                    "xmlns", prefix, "http://www.w3.org/2000/xmlns/")
+                attrs[attribute] = namespace
+
+        # Namespaces are in play. Find any attributes that came in
+        # from lxml with namespaces attached to their names, and
+        # turn then into NamespacedAttribute objects.
+        new_attrs = {}
+        for attr, value in list(attrs.items()):
+            namespace, attr = self._getNsTag(attr)
+            if namespace is None:
+                new_attrs[attr] = value
+            else:
+                nsprefix = self._prefix_for_namespace(namespace)
+                attr = NamespacedAttribute(nsprefix, attr, namespace)
+                new_attrs[attr] = value
+        attrs = new_attrs
+
+        namespace, name = self._getNsTag(name)
+        nsprefix = self._prefix_for_namespace(namespace)
+        self.soup.handle_starttag(name, namespace, nsprefix, attrs)
+
+    def _prefix_for_namespace(self, namespace):
+        """Find the currently active prefix for the given namespace."""
+        if namespace is None:
+            return None
+        for inverted_nsmap in reversed(self.nsmaps):
+            if inverted_nsmap is not None and namespace in inverted_nsmap:
+                return inverted_nsmap[namespace]
+        return None
+
+    def end(self, name):
+        self.soup.endData()
+        completed_tag = self.soup.tagStack[-1]
+        namespace, name = self._getNsTag(name)
+        nsprefix = None
+        if namespace is not None:
+            for inverted_nsmap in reversed(self.nsmaps):
+                if inverted_nsmap is not None and namespace in inverted_nsmap:
+                    nsprefix = inverted_nsmap[namespace]
+                    break
+        self.soup.handle_endtag(name, nsprefix)
+        if len(self.nsmaps) > 1:
+            # This tag, or one of its parents, introduced a namespace
+            # mapping, so pop it off the stack.
+            self.nsmaps.pop()
+
+    def pi(self, target, data):
+        self.soup.endData()
+        self.soup.handle_data(target + ' ' + data)
+        self.soup.endData(self.processing_instruction_class)
+
+    def data(self, content):
+        self.soup.handle_data(content)
+
+    def doctype(self, name, pubid, system):
+        self.soup.endData()
+        doctype = Doctype.for_name_and_ids(name, pubid, system)
+        self.soup.object_was_parsed(doctype)
+
+    def comment(self, content):
+        "Handle comments as Comment objects."
+        self.soup.endData()
+        self.soup.handle_data(content)
+        self.soup.endData(Comment)
+
+    def test_fragment_to_document(self, fragment):
+        """See `TreeBuilder`."""
+        return '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
+
+
+class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
+
+    NAME = LXML
+    ALTERNATE_NAMES = ["lxml-html"]
+
+    features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
+    is_xml = False
+    processing_instruction_class = ProcessingInstruction
+
+    def default_parser(self, encoding):
+        return etree.HTMLParser
+
+    def feed(self, markup):
+        encoding = self.soup.original_encoding
+        try:
+            self.parser = self.parser_for(encoding)
+            self.parser.feed(markup)
+            self.parser.close()
+        except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
+            raise ParserRejectedMarkup(e)
+
+
+    def test_fragment_to_document(self, fragment):
+        """See `TreeBuilder`."""
+        return '<html><body>%s</body></html>' % fragment

IKEA_scrapper/.venv/Lib/site-packages/bs4/diagnose.py

@@ -0,0 +1,242 @@
+"""Diagnostic functions, mainly for use when doing tech support."""
+
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+import cProfile
+from io import StringIO
+from html.parser import HTMLParser
+import bs4
+from bs4 import BeautifulSoup, __version__
+from bs4.builder import builder_registry
+
+import os
+import pstats
+import random
+import tempfile
+import time
+import traceback
+import sys
+import cProfile
+
+def diagnose(data):
+    """Diagnostic suite for isolating common problems.
+
+    :param data: A string containing markup that needs to be explained.
+    :return: None; diagnostics are printed to standard output.
+    """
+    print(("Diagnostic running on Beautiful Soup %s" % __version__))
+    print(("Python version %s" % sys.version))
+
+    basic_parsers = ["html.parser", "html5lib", "lxml"]
+    for name in basic_parsers:
+        for builder in builder_registry.builders:
+            if name in builder.features:
+                break
+        else:
+            basic_parsers.remove(name)
+            print((
+                "I noticed that %s is not installed. Installing it may help." %
+                name))
+
+    if 'lxml' in basic_parsers:
+        basic_parsers.append("lxml-xml")
+        try:
+            from lxml import etree
+            print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
+        except ImportError as e:
+            print(
+                "lxml is not installed or couldn't be imported.")
+
+
+    if 'html5lib' in basic_parsers:
+        try:
+            import html5lib
+            print(("Found html5lib version %s" % html5lib.__version__))
+        except ImportError as e:
+            print(
+                "html5lib is not installed or couldn't be imported.")
+
+    if hasattr(data, 'read'):
+        data = data.read()
+    elif data.startswith("http:") or data.startswith("https:"):
+        print(('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data))
+        print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
+        return
+    else:
+        try:
+            if os.path.exists(data):
+                print(('"%s" looks like a filename. Reading data from the file.' % data))
+                with open(data) as fp:
+                    data = fp.read()
+        except ValueError:
+            # This can happen on some platforms when the 'filename' is
+            # too long. Assume it's data and not a filename.
+            pass
+        print("")
+
+    for parser in basic_parsers:
+        print(("Trying to parse your markup with %s" % parser))
+        success = False
+        try:
+            soup = BeautifulSoup(data, features=parser)
+            success = True
+        except Exception as e:
+            print(("%s could not parse the markup." % parser))
+            traceback.print_exc()
+        if success:
+            print(("Here's what %s did with the markup:" % parser))
+            print((soup.prettify()))
+
+        print(("-" * 80))
+
+def lxml_trace(data, html=True, **kwargs):
+    """Print out the lxml events that occur during parsing.
+
+    This lets you see how lxml parses a document when no Beautiful
+    Soup code is running. You can use this to determine whether
+    an lxml-specific problem is in Beautiful Soup's lxml tree builders
+    or in lxml itself.
+
+    :param data: Some markup.
+    :param html: If True, markup will be parsed with lxml's HTML parser.
+       if False, lxml's XML parser will be used.
+    """
+    from lxml import etree
+    for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
+        print(("%s, %4s, %s" % (event, element.tag, element.text)))
+
+class AnnouncingParser(HTMLParser):
+    """Subclass of HTMLParser that announces parse events, without doing
+    anything else.
+
+    You can use this to get a picture of how html.parser sees a given
+    document. The easiest way to do this is to call `htmlparser_trace`.
+    """
+
+    def _p(self, s):
+        print(s)
+
+    def handle_starttag(self, name, attrs):
+        self._p("%s START" % name)
+
+    def handle_endtag(self, name):
+        self._p("%s END" % name)
+
+    def handle_data(self, data):
+        self._p("%s DATA" % data)
+
+    def handle_charref(self, name):
+        self._p("%s CHARREF" % name)
+
+    def handle_entityref(self, name):
+        self._p("%s ENTITYREF" % name)
+
+    def handle_comment(self, data):
+        self._p("%s COMMENT" % data)
+
+    def handle_decl(self, data):
+        self._p("%s DECL" % data)
+
+    def unknown_decl(self, data):
+        self._p("%s UNKNOWN-DECL" % data)
+
+    def handle_pi(self, data):
+        self._p("%s PI" % data)
+
+def htmlparser_trace(data):
+    """Print out the HTMLParser events that occur during parsing.
+
+    This lets you see how HTMLParser parses a document when no
+    Beautiful Soup code is running.
+
+    :param data: Some markup.
+    """
+    parser = AnnouncingParser()
+    parser.feed(data)
+
+_vowels = "aeiou"
+_consonants = "bcdfghjklmnpqrstvwxyz"
+
+def rword(length=5):
+    "Generate a random word-like string."
+    s = ''
+    for i in range(length):
+        if i % 2 == 0:
+            t = _consonants
+        else:
+            t = _vowels
+        s += random.choice(t)
+    return s
+
+def rsentence(length=4):
+    "Generate a random sentence-like string."
+    return " ".join(rword(random.randint(4,9)) for i in range(length))
+        
+def rdoc(num_elements=1000):
+    """Randomly generate an invalid HTML document."""
+    tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
+    elements = []
+    for i in range(num_elements):
+        choice = random.randint(0,3)
+        if choice == 0:
+            # New tag.
+            tag_name = random.choice(tag_names)
+            elements.append("<%s>" % tag_name)
+        elif choice == 1:
+            elements.append(rsentence(random.randint(1,4)))
+        elif choice == 2:
+            # Close a tag.
+            tag_name = random.choice(tag_names)
+            elements.append("</%s>" % tag_name)
+    return "<html>" + "\n".join(elements) + "</html>"
+
+def benchmark_parsers(num_elements=100000):
+    """Very basic head-to-head performance benchmark."""
+    print(("Comparative parser benchmark on Beautiful Soup %s" % __version__))
+    data = rdoc(num_elements)
+    print(("Generated a large invalid HTML document (%d bytes)." % len(data)))
+    
+    for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
+        success = False
+        try:
+            a = time.time()
+            soup = BeautifulSoup(data, parser)
+            b = time.time()
+            success = True
+        except Exception as e:
+            print(("%s could not parse the markup." % parser))
+            traceback.print_exc()
+        if success:
+            print(("BS4+%s parsed the markup in %.2fs." % (parser, b-a)))
+
+    from lxml import etree
+    a = time.time()
+    etree.HTML(data)
+    b = time.time()
+    print(("Raw lxml parsed the markup in %.2fs." % (b-a)))
+
+    import html5lib
+    parser = html5lib.HTMLParser()
+    a = time.time()
+    parser.parse(data)
+    b = time.time()
+    print(("Raw html5lib parsed the markup in %.2fs." % (b-a)))
+
+def profile(num_elements=100000, parser="lxml"):
+    """Use Python's profiler on a randomly generated document."""
+    filehandle = tempfile.NamedTemporaryFile()
+    filename = filehandle.name
+
+    data = rdoc(num_elements)
+    vars = dict(bs4=bs4, data=data, parser=parser)
+    cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
+
+    stats = pstats.Stats(filename)
+    # stats.strip_dirs()
+    stats.sort_stats("cumulative")
+    stats.print_stats('_html5lib|bs4', 50)
+
+# If this file is run as a script, standard input is diagnosed.
+if __name__ == '__main__':
+    diagnose(sys.stdin.read())

IKEA_scrapper/.venv/Lib/site-packages/bs4/formatter.py

@@ -0,0 +1,165 @@
+from bs4.dammit import EntitySubstitution
+
+class Formatter(EntitySubstitution):
+    """Describes a strategy to use when outputting a parse tree to a string.
+
+    Some parts of this strategy come from the distinction between
+    HTML4, HTML5, and XML. Others are configurable by the user.
+
+    Formatters are passed in as the `formatter` argument to methods
+    like `PageElement.encode`. Most people won't need to think about
+    formatters, and most people who need to think about them can pass
+    in one of these predefined strings as `formatter` rather than
+    making a new Formatter object:
+
+    For HTML documents:
+     * 'html' - HTML entity substitution for generic HTML documents. (default)
+     * 'html5' - HTML entity substitution for HTML5 documents, as
+                 well as some optimizations in the way tags are rendered.
+     * 'minimal' - Only make the substitutions necessary to guarantee
+                   valid HTML.
+     * None - Do not perform any substitution. This will be faster
+              but may result in invalid markup.
+
+    For XML documents:
+     * 'html' - Entity substitution for XHTML documents.
+     * 'minimal' - Only make the substitutions necessary to guarantee
+                   valid XML. (default)
+     * None - Do not perform any substitution. This will be faster
+              but may result in invalid markup.
+    """
+    # Registries of XML and HTML formatters.
+    XML_FORMATTERS = {}
+    HTML_FORMATTERS = {}
+
+    HTML = 'html'
+    XML = 'xml'
+
+    HTML_DEFAULTS = dict(
+        cdata_containing_tags=set(["script", "style"]),
+    )
+
+    def _default(self, language, value, kwarg):
+        if value is not None:
+            return value
+        if language == self.XML:
+            return set()
+        return self.HTML_DEFAULTS[kwarg]
+
+    def __init__(
+            self, language=None, entity_substitution=None,
+            void_element_close_prefix='/', cdata_containing_tags=None,
+            empty_attributes_are_booleans=False,
+    ):
+        """Constructor.
+
+        :param language: This should be Formatter.XML if you are formatting
+           XML markup and Formatter.HTML if you are formatting HTML markup.
+
+        :param entity_substitution: A function to call to replace special
+           characters with XML/HTML entities. For examples, see 
+           bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
+        :param void_element_close_prefix: By default, void elements
+           are represented as <tag/> (XML rules) rather than <tag>
+           (HTML rules). To get <tag>, pass in the empty string.
+        :param cdata_containing_tags: The list of tags that are defined
+           as containing CDATA in this dialect. For example, in HTML,
+           <script> and <style> tags are defined as containing CDATA,
+           and their contents should not be formatted.
+        :param blank_attributes_are_booleans: Render attributes whose value
+            is the empty string as HTML-style boolean attributes.
+            (Attributes whose value is None are always rendered this way.)
+        """
+        self.language = language
+        self.entity_substitution = entity_substitution
+        self.void_element_close_prefix = void_element_close_prefix
+        self.cdata_containing_tags = self._default(
+            language, cdata_containing_tags, 'cdata_containing_tags'
+        )
+        self.empty_attributes_are_booleans=empty_attributes_are_booleans
+        
+    def substitute(self, ns):
+        """Process a string that needs to undergo entity substitution.
+        This may be a string encountered in an attribute value or as
+        text.
+
+        :param ns: A string.
+        :return: A string with certain characters replaced by named
+           or numeric entities.
+        """
+        if not self.entity_substitution:
+            return ns
+        from .element import NavigableString
+        if (isinstance(ns, NavigableString)
+            and ns.parent is not None
+            and ns.parent.name in self.cdata_containing_tags):
+            # Do nothing.
+            return ns
+        # Substitute.
+        return self.entity_substitution(ns)
+
+    def attribute_value(self, value):
+        """Process the value of an attribute.
+
+        :param ns: A string.
+        :return: A string with certain characters replaced by named
+           or numeric entities.
+        """
+        return self.substitute(value)
+    
+    def attributes(self, tag):
+        """Reorder a tag's attributes however you want.
+        
+        By default, attributes are sorted alphabetically. This makes
+        behavior consistent between Python 2 and Python 3, and preserves
+        backwards compatibility with older versions of Beautiful Soup.
+
+        If `empty_boolean_attributes` is True, then attributes whose
+        values are set to the empty string will be treated as boolean
+        attributes.
+        """
+        if tag.attrs is None:
+            return []
+        return sorted(
+            (k, (None if self.empty_attributes_are_booleans and v == '' else v))
+            for k, v in list(tag.attrs.items())
+        )
+   
+class HTMLFormatter(Formatter):
+    """A generic Formatter for HTML."""
+    REGISTRY = {}
+    def __init__(self, *args, **kwargs):
+        return super(HTMLFormatter, self).__init__(self.HTML, *args, **kwargs)
+
+    
+class XMLFormatter(Formatter):
+    """A generic Formatter for XML."""
+    REGISTRY = {}
+    def __init__(self, *args, **kwargs):
+        return super(XMLFormatter, self).__init__(self.XML, *args, **kwargs)
+
+
+# Set up aliases for the default formatters.
+HTMLFormatter.REGISTRY['html'] = HTMLFormatter(
+    entity_substitution=EntitySubstitution.substitute_html
+)
+HTMLFormatter.REGISTRY["html5"] = HTMLFormatter(
+    entity_substitution=EntitySubstitution.substitute_html,
+    void_element_close_prefix=None,
+    empty_attributes_are_booleans=True,
+)
+HTMLFormatter.REGISTRY["minimal"] = HTMLFormatter(
+    entity_substitution=EntitySubstitution.substitute_xml
+)
+HTMLFormatter.REGISTRY[None] = HTMLFormatter(
+    entity_substitution=None
+)
+XMLFormatter.REGISTRY["html"] =  XMLFormatter(
+    entity_substitution=EntitySubstitution.substitute_html
+)
+XMLFormatter.REGISTRY["minimal"] = XMLFormatter(
+    entity_substitution=EntitySubstitution.substitute_xml
+)
+XMLFormatter.REGISTRY[None] = Formatter(
+    Formatter(Formatter.XML, entity_substitution=None)
+)

IKEA_scrapper/.venv/Lib/site-packages/certifi-2021.5.30.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

IKEA_scrapper/.venv/Lib/site-packages/certifi-2021.5.30.dist-info/LICENSE

@@ -0,0 +1,21 @@
+This package contains a modified version of ca-bundle.crt:
+
+ca-bundle.crt -- Bundle of CA Root Certificates
+
+Certificate data from Mozilla as of: Thu Nov  3 19:04:19 2011#
+This is a bundle of X.509 certificates of public Certificate Authorities
+(CA). These were automatically extracted from Mozilla's root certificates
+file (certdata.txt).  This file can be found in the mozilla source tree:
+http://mxr.mozilla.org/mozilla/source/security/nss/lib/ckfw/builtins/certdata.txt?raw=1#
+It contains the certificates in PEM format and therefore
+can be directly used with curl / libcurl / php_curl, or with
+an Apache+mod_ssl webserver for SSL client authentication.
+Just configure this file as the SSLCACertificateFile.#
+
+***** BEGIN LICENSE BLOCK *****
+This Source Code Form is subject to the terms of the Mozilla Public License,
+v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
+one at http://mozilla.org/MPL/2.0/.
+
+***** END LICENSE BLOCK *****
+@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

IKEA_scrapper/.venv/Lib/site-packages/certifi-2021.5.30.dist-info/METADATA

@@ -0,0 +1,83 @@
+Metadata-Version: 2.1
+Name: certifi
+Version: 2021.5.30
+Summary: Python package for providing Mozilla's CA Bundle.
+Home-page: https://certifiio.readthedocs.io/en/latest/
+Author: Kenneth Reitz
+Author-email: me@kennethreitz.com
+License: MPL-2.0
+Project-URL: Documentation, https://certifiio.readthedocs.io/en/latest/
+Project-URL: Source, https://github.com/certifi/python-certifi
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+
+Certifi: Python SSL Certificates
+================================
+
+`Certifi`_ provides Mozilla's carefully curated collection of Root Certificates for
+validating the trustworthiness of SSL certificates while verifying the identity
+of TLS hosts. It has been extracted from the `Requests`_ project.
+
+Installation
+------------
+
+``certifi`` is available on PyPI. Simply install it with ``pip``::
+
+    $ pip install certifi
+
+Usage
+-----
+
+To reference the installed certificate authority (CA) bundle, you can use the
+built-in function::
+
+    >>> import certifi
+
+    >>> certifi.where()
+    '/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
+
+Or from the command line::
+
+    $ python -m certifi
+    /usr/local/lib/python3.7/site-packages/certifi/cacert.pem
+
+Enjoy!
+
+1024-bit Root Certificates
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Browsers and certificate authorities have concluded that 1024-bit keys are
+unacceptably weak for certificates, particularly root certificates. For this
+reason, Mozilla has removed any weak (i.e. 1024-bit key) certificate from its
+bundle, replacing it with an equivalent strong (i.e. 2048-bit or greater key)
+certificate from the same CA. Because Mozilla removed these certificates from
+its bundle, ``certifi`` removed them as well.
+
+In previous versions, ``certifi`` provided the ``certifi.old_where()`` function
+to intentionally re-add the 1024-bit roots back into your bundle. This was not
+recommended in production and therefore was removed at the end of 2018.
+
+.. _`Certifi`: https://certifiio.readthedocs.io/en/latest/
+.. _`Requests`: https://requests.readthedocs.io/en/master/
+
+Addition/Removal of Certificates
+--------------------------------
+
+Certifi does not support any addition/removal or other modification of the
+CA trust store content. This project is intended to provide a reliable and
+highly portable root of trust to python deployments. Look to upstream projects
+for methods to use alternate trust.
+
+

IKEA_scrapper/.venv/Lib/site-packages/certifi-2021.5.30.dist-info/RECORD

@@ -0,0 +1,13 @@
+certifi-2021.5.30.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+certifi-2021.5.30.dist-info/LICENSE,sha256=vp2C82ES-Hp_HXTs1Ih-FGe7roh4qEAEoAEXseR1o-I,1049
+certifi-2021.5.30.dist-info/METADATA,sha256=RDzuah_IZxjVhKootR1Ha1BrDovPSA-xF-rcaD90PTo,2994
+certifi-2021.5.30.dist-info/RECORD,,
+certifi-2021.5.30.dist-info/WHEEL,sha256=ADKeyaGyKF5DwBNE0sRE5pvW-bSkFMJfBuhzZ3rceP4,110
+certifi-2021.5.30.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
+certifi/__init__.py,sha256=-b78tXibbl0qtgCzv9tc9v6ozwcNX915lT9Tf4a9lds,62
+certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
+certifi/__pycache__/__init__.cpython-39.pyc,,
+certifi/__pycache__/__main__.cpython-39.pyc,,
+certifi/__pycache__/core.cpython-39.pyc,,
+certifi/cacert.pem,sha256=3i-hfE2K5o3CBKG2tYt6ehJWk2fP64o6Th83fHPoPp4,259465
+certifi/core.py,sha256=V0uyxKOYdz6ulDSusclrLmjbPgOXsD0BnEf0SQ7OnoE,2303

IKEA_scrapper/.venv/Lib/site-packages/certifi-2021.5.30.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.35.1)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+

IKEA_scrapper/.venv/Lib/site-packages/certifi-2021.5.30.dist-info/top_level.txt

@@ -0,0 +1 @@
+certifi

IKEA_scrapper/.venv/Lib/site-packages/certifi/__init__.py

@@ -0,0 +1,3 @@
+from .core import contents, where
+
+__version__ = "2021.05.30"

IKEA_scrapper/.venv/Lib/site-packages/certifi/__main__.py

@@ -0,0 +1,12 @@
+import argparse
+
+from certifi import contents, where
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-c", "--contents", action="store_true")
+args = parser.parse_args()
+
+if args.contents:
+    print(contents())
+else:
+    print(where())

IKEA_scrapper/.venv/Lib/site-packages/certifi/core.py

@@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+
+"""
+certifi.py
+~~~~~~~~~~
+
+This module returns the installation location of cacert.pem or its contents.
+"""
+import os
+
+try:
+    from importlib.resources import path as get_path, read_text
+
+    _CACERT_CTX = None
+    _CACERT_PATH = None
+
+    def where():
+        # This is slightly terrible, but we want to delay extracting the file
+        # in cases where we're inside of a zipimport situation until someone
+        # actually calls where(), but we don't want to re-extract the file
+        # on every call of where(), so we'll do it once then store it in a
+        # global variable.
+        global _CACERT_CTX
+        global _CACERT_PATH
+        if _CACERT_PATH is None:
+            # This is slightly janky, the importlib.resources API wants you to
+            # manage the cleanup of this file, so it doesn't actually return a
+            # path, it returns a context manager that will give you the path
+            # when you enter it and will do any cleanup when you leave it. In
+            # the common case of not needing a temporary file, it will just
+            # return the file system location and the __exit__() is a no-op.
+            #
+            # We also have to hold onto the actual context manager, because
+            # it will do the cleanup whenever it gets garbage collected, so
+            # we will also store that at the global level as well.
+            _CACERT_CTX = get_path("certifi", "cacert.pem")
+            _CACERT_PATH = str(_CACERT_CTX.__enter__())
+
+        return _CACERT_PATH
+
+
+except ImportError:
+    # This fallback will work for Python versions prior to 3.7 that lack the
+    # importlib.resources module but relies on the existing `where` function
+    # so won't address issues with environments like PyOxidizer that don't set
+    # __file__ on modules.
+    def read_text(_module, _path, encoding="ascii"):
+        with open(where(), "r", encoding=encoding) as data:
+            return data.read()
+
+    # If we don't have importlib.resources, then we will just do the old logic
+    # of assuming we're on the filesystem and munge the path directly.
+    def where():
+        f = os.path.dirname(__file__)
+
+        return os.path.join(f, "cacert.pem")
+
+
+def contents():
+    return read_text("certifi", "cacert.pem", encoding="ascii")

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 TAHRI Ahmed R.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/METADATA

@@ -0,0 +1,275 @@
+Metadata-Version: 2.1
+Name: charset-normalizer
+Version: 2.0.4
+Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
+Home-page: https://github.com/ousret/charset_normalizer
+Author: Ahmed TAHRI @Ousret
+Author-email: ahmed.tahri@cloudnursery.dev
+License: MIT
+Keywords: encoding,i18n,txt,text,charset,charset-detector,normalization,unicode,chardet
+Platform: UNKNOWN
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Utilities
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.5.0
+Description-Content-Type: text/markdown
+Provides-Extra: unicode_backport
+Requires-Dist: unicodedata2 ; extra == 'unicode_backport'
+
+
+<h1 align="center">Charset Detection, for Everyone 👋 <a href="https://twitter.com/intent/tweet?text=The%20Real%20First%20Universal%20Charset%20%26%20Language%20Detector&url=https://www.github.com/Ousret/charset_normalizer&hashtags=python,encoding,chardet,developers"><img src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"/></a></h1>
+
+<p align="center">
+  <sup>The Real First Universal Charset Detector</sup><br>
+  <a href="https://travis-ci.org/Ousret/charset_normalizer">
+    <img src="https://travis-ci.org/Ousret/charset_normalizer.svg?branch=master"/>
+  </a>
+  <a href="https://pypi.org/project/charset-normalizer">
+    <img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
+  </a>
+  <a href="https://app.codacy.com/project/Ousret/charset_normalizer/dashboard">
+    <img alt="Code Quality Badge" src="https://api.codacy.com/project/badge/Grade/a0c85b7f56dd4f628dc022763f82762c"/>
+  </a>
+  <a href="https://codecov.io/gh/Ousret/charset_normalizer">
+      <img src="https://codecov.io/gh/Ousret/charset_normalizer/branch/master/graph/badge.svg" />
+  </a>
+  <a href='https://charset-normalizer.readthedocs.io/en/latest/?badge=latest'>
+    <img src='https://readthedocs.org/projects/charset-normalizer/badge/?version=latest' alt='Documentation Status' />
+  </a>
+  <a href="https://pepy.tech/project/charset-normalizer/">
+    <img alt="Download Count Total" src="https://pepy.tech/badge/charset-normalizer" />
+  </a>
+</p>
+
+> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
+> I'm trying to resolve the issue by taking a new approach.
+> All IANA character set names for which the Python core library provides codecs are supported.
+
+<p align="center">
+  >>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
+</p>
+
+This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
+
+| Feature       | [Chardet](https://github.com/chardet/chardet)       | Charset Normalizer | [cChardet](https://github.com/PyYoshi/cChardet) |
+| ------------- | :-------------: | :------------------: | :------------------: |
+| `Fast`         | ❌<br>          | ✅<br>             | ✅ <br> |
+| `Universal**`     | ❌            | ✅                 | ❌ |
+| `Reliable` **without** distinguishable standards | ❌ | ✅ | ✅ |
+| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
+| `Free & Open`  | ✅             | ✅                | ✅ |
+| `License` | LGPL-2.1 | MIT | MPL-1.1
+| `Native Python` | ✅ | ✅ | ❌ |
+| `Detect spoken language` | ❌ | ✅ | N/A |
+| `Supported Encoding` | 30 | :tada: [93](https://charset-normalizer.readthedocs.io/en/latest/support.html)  | 40
+
+<p align="center">
+<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
+
+*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br> 
+
+## ⚡ Performance
+
+This package offer better performance than its counterpart Chardet. Here are some numbers.
+
+| Package       | Accuracy       | Mean per file (ns) | File per sec (est) |
+| ------------- | :-------------: | :------------------: | :------------------: |
+|      [chardet](https://github.com/chardet/chardet)        |     93.0 %     |     150 ms      |       7 file/sec        |
+| charset-normalizer |    **95.0 %**     |     **36 ms**      |       28 file/sec    |
+
+| Package       | 99th percentile       | 95th percentile | 50th percentile |
+| ------------- | :-------------: | :------------------: | :------------------: |
+|      [chardet](https://github.com/chardet/chardet)        |     647 ms     |     250 ms      |       24 ms        |
+| charset-normalizer |    354 ms     |     202 ms      |       16 ms    |
+
+Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
+
+> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
+> And yes, these results might change at any time. The dataset can be updated to include more files.
+
+[cchardet](https://github.com/PyYoshi/cChardet) is a non-native (cpp binding) faster alternative. If speed is the most important factor,
+you should try it.
+
+## Your support
+
+Please ⭐ this repository if this project helped you!
+
+## ✨ Installation
+
+Using PyPi for latest stable
+```sh
+pip install charset-normalizer
+```
+Or directly from dev-master for latest preview
+```sh
+pip install git+https://github.com/Ousret/charset_normalizer.git
+```
+
+If you want a more up-to-date `unicodedata` than the one available in your Python setup.
+```sh
+pip install charset-normalizer[unicode_backport]
+```
+
+## 🚀 Basic Usage
+
+### CLI
+This package comes with a CLI.
+
+```
+usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
+                  file [file ...]
+
+The Real First Universal Charset Detector. Discover originating encoding used
+on text file. Normalize text to unicode.
+
+positional arguments:
+  files                 File(s) to be analysed
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -v, --verbose         Display complementary information about file if any.
+                        Stdout will contain logs about the detection process.
+  -a, --with-alternative
+                        Output complementary possibilities if any. Top-level
+                        JSON WILL be a list.
+  -n, --normalize       Permit to normalize input file. If not set, program
+                        does not write anything.
+  -m, --minimal         Only output the charset detected to STDOUT. Disabling
+                        JSON output.
+  -r, --replace         Replace file when trying to normalize it instead of
+                        creating a new one.
+  -f, --force           Replace file without asking if you are sure, use this
+                        flag with caution.
+  -t THRESHOLD, --threshold THRESHOLD
+                        Define a custom maximum amount of chaos allowed in
+                        decoded content. 0. <= chaos <= 1.
+  --version             Show version information and exit.
+```
+
+```bash
+normalizer ./data/sample.1.fr.srt
+```
+
+:tada: Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
+
+```json
+{
+    "path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
+    "encoding": "cp1252",
+    "encoding_aliases": [
+        "1252",
+        "windows_1252"
+    ],
+    "alternative_encodings": [
+        "cp1254",
+        "cp1256",
+        "cp1258",
+        "iso8859_14",
+        "iso8859_15",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_9",
+        "latin_1",
+        "mbcs"
+    ],
+    "language": "French",
+    "alphabets": [
+        "Basic Latin",
+        "Latin-1 Supplement"
+    ],
+    "has_sig_or_bom": false,
+    "chaos": 0.149,
+    "coherence": 97.152,
+    "unicode_path": null,
+    "is_preferred": true
+}
+```
+
+### Python
+*Just print out normalized text*
+```python
+from charset_normalizer import from_path
+
+results = from_path('./my_subtitle.srt')
+
+print(str(results.best()))
+```
+
+*Normalize any text file*
+```python
+from charset_normalizer import normalize
+try:
+    normalize('./my_subtitle.srt') # should write to disk my_subtitle-***.srt
+except IOError as e:
+    print('Sadly, we are unable to perform charset normalization.', str(e))
+```
+
+*Upgrade your code without effort*
+```python
+from charset_normalizer import detect
+```
+
+The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
+
+See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
+
+## 😇 Why
+
+When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
+reliable alternative using a completely different method. Also! I never back down on a good challenge !
+
+I **don't care** about the **originating charset** encoding, because **two different tables** can
+produce **two identical files.**
+What I want is to get readable text, the best I can. 
+
+In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
+
+Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
+
+## 🍰 How
+
+  - Discard all charset encoding table that could not fit the binary content.
+  - Measure chaos, or the mess once opened (by chunks) with a corresponding charset encoding.
+  - Extract matches with the lowest mess detected.
+  - Finally, if there is too much match left, we measure coherence.
+
+**Wait a minute**, what is chaos/mess and coherence according to **YOU ?**
+
+*Chaos :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
+**I established** some ground rules about **what is obvious** when **it seems like** a mess.
+ I know that my interpretation of what is chaotic is very subjective, feel free to contribute in order to
+ improve or rewrite it.
+
+*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
+that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
+
+## ⚡ Known limitations
+
+  - Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
+  - Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
+
+## 👤 Contributing
+
+Contributions, issues and feature requests are very much welcome.<br />
+Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
+
+## 📝 License
+
+Copyright © 2019 [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
+This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
+
+Characters frequencies used in this project © 2012 [Denny Vrandečić](http://denny.vrandecic.de)
+
+

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/RECORD

@@ -0,0 +1,33 @@
+../../Scripts/normalizer.exe,sha256=iFgihohsb1sL3yDVC9JJjy5BWPNahDIoahd71p-gOgE,106392
+charset_normalizer-2.0.4.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+charset_normalizer-2.0.4.dist-info/LICENSE,sha256=6zGgxaT7Cbik4yBV0lweX5w1iidS_vPNcgIT0cz-4kE,1070
+charset_normalizer-2.0.4.dist-info/METADATA,sha256=iGaSYKAbW7dltLfO_sIm347XsC5kqKiFrvR3IHolDio,11710
+charset_normalizer-2.0.4.dist-info/RECORD,,
+charset_normalizer-2.0.4.dist-info/WHEEL,sha256=OqRkF0eY5GHssMorFjlbTIq072vpHpF60fIQA6lS9xA,92
+charset_normalizer-2.0.4.dist-info/entry_points.txt,sha256=5AJq_EPtGGUwJPgQLnBZfbVr-FYCIwT0xP7dIEZO3NI,77
+charset_normalizer-2.0.4.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
+charset_normalizer/__init__.py,sha256=i8FSr9cSFIrh16O8h7com8LKtd9nsLY8wiEhSpk1_aY,1673
+charset_normalizer/__pycache__/__init__.cpython-39.pyc,,
+charset_normalizer/__pycache__/api.cpython-39.pyc,,
+charset_normalizer/__pycache__/cd.cpython-39.pyc,,
+charset_normalizer/__pycache__/constant.cpython-39.pyc,,
+charset_normalizer/__pycache__/legacy.cpython-39.pyc,,
+charset_normalizer/__pycache__/md.cpython-39.pyc,,
+charset_normalizer/__pycache__/models.cpython-39.pyc,,
+charset_normalizer/__pycache__/utils.cpython-39.pyc,,
+charset_normalizer/__pycache__/version.cpython-39.pyc,,
+charset_normalizer/api.py,sha256=xf9L11VEFJGNcGFSS0uJxZwfdPYy87ya97AiVhNr-MI,15685
+charset_normalizer/assets/__init__.py,sha256=JTs2XX9qbYSBhS4EEI93IqEOnzzrHhVmX1gp2vKjZdE,6938
+charset_normalizer/assets/__pycache__/__init__.cpython-39.pyc,,
+charset_normalizer/cd.py,sha256=_HLe1wgJAifJPl4dlBctjK5yIvH0ja67jePw36OrrhI,9223
+charset_normalizer/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+charset_normalizer/cli/__pycache__/__init__.cpython-39.pyc,,
+charset_normalizer/cli/__pycache__/normalizer.cpython-39.pyc,,
+charset_normalizer/cli/normalizer.py,sha256=HWLuXnvQa12U2zjv6rXtashpNnxgxN3lZtVCnqHjIFQ,8334
+charset_normalizer/constant.py,sha256=YA8r7rNGeuLlnqWLs2MISs1mFLmaralG99HNevHuUuo,18390
+charset_normalizer/legacy.py,sha256=L3Qn-DSLjRQoYPtDIzkXcqO0mnFIjOl0p6-gAzYUY54,1640
+charset_normalizer/md.py,sha256=m3XxcK9UhsSCFK7-vrOU6ztn-eaeXKLuS8dP88QY6zw,16263
+charset_normalizer/models.py,sha256=A7vIN3PCJuM1KMDBs60Gb_WF1lHJsrkrllc5_RMV-nE,12541
+charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+charset_normalizer/utils.py,sha256=0HasZ3NtRNiw-HbmgnfhSDySJfSa4pO4azPTn6vOrP0,8594
+charset_normalizer/version.py,sha256=Ou-PvSj5-2Ci5Y_bH8OSoXrbbTt8sxO5pJRagAzlYUc,79

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.36.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+normalizer = charset_normalizer.cli.normalizer:cli_detect
+

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer-2.0.4.dist-info/top_level.txt

@@ -0,0 +1 @@
+charset_normalizer

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/__init__.py

@@ -0,0 +1,31 @@
+"""
+Charset-Normalizer
+~~~~~~~~~~~~~~
+The Real First Universal Charset Detector.
+A library that helps you read text from an unknown charset encoding.
+Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
+All IANA character set names for which the Python core library provides codecs are supported.
+
+Basic usage:
+   >>> from charset_normalizer import from_bytes
+   >>> results = from_bytes('Bсеки човек има право на образование. Oбразованието трябва да бъде безплатно, поне що се отнася до началното и основното образование.'.encode('utf_8'))
+   >>> "utf_8" in results
+   True
+   >>> best_result = results.best()
+   >>> str(best_result)
+   'Bсеки човек има право на образование. Oбразованието трябва да бъде безплатно, поне що се отнася до началното и основното образование.'
+
+Others methods and usages are available - see the full documentation
+at <https://github.com/Ousret/charset_normalizer>.
+:copyright: (c) 2021 by Ahmed TAHRI
+:license: MIT, see LICENSE for more details.
+"""
+from charset_normalizer.api import from_fp, from_path, from_bytes, normalize
+from charset_normalizer.legacy import detect
+from charset_normalizer.version import __version__, VERSION
+from charset_normalizer.models import CharsetMatch, CharsetMatches
+
+# Backward-compatible v1 imports
+from charset_normalizer.models import CharsetNormalizerMatch
+import charset_normalizer.api as CharsetDetector
+CharsetNormalizerMatches = CharsetDetector

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/api.py

@@ -0,0 +1,427 @@
+from os.path import splitext, basename
+from typing import List, BinaryIO, Optional, Set, Union
+
+try:
+    from os import PathLike
+except ImportError:
+    PathLike = Union[str, 'os.PathLike[str]']  # type: ignore
+
+from charset_normalizer.constant import TOO_SMALL_SEQUENCE, TOO_BIG_SEQUENCE, IANA_SUPPORTED
+from charset_normalizer.md import mess_ratio
+from charset_normalizer.models import CharsetMatches, CharsetMatch
+from warnings import warn
+import logging
+
+from charset_normalizer.utils import any_specified_encoding, is_multi_byte_encoding, identify_sig_or_bom, \
+    should_strip_sig_or_bom, is_cp_similar, iana_name
+from charset_normalizer.cd import coherence_ratio, encoding_languages, mb_encoding_languages, merge_coherence_ratios
+
+logger = logging.getLogger("charset_normalizer")
+logger.setLevel(logging.DEBUG)
+
+handler = logging.StreamHandler()
+handler.setFormatter(logging.Formatter('%(asctime)s | %(levelname)s | %(message)s'))
+logger.addHandler(handler)
+
+
+def from_bytes(
+        sequences: bytes,
+        steps: int = 5,
+        chunk_size: int = 512,
+        threshold: float = 0.2,
+        cp_isolation: List[str] = None,
+        cp_exclusion: List[str] = None,
+        preemptive_behaviour: bool = True,
+        explain: bool = False
+) -> CharsetMatches:
+    """
+    Given a raw bytes sequence, return the best possibles charset usable to render str objects.
+    If there is no results, it is a strong indicator that the source is binary/not text.
+    By default, the process will extract 5 blocs of 512o each to assess the mess and coherence of a given sequence.
+    And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
+
+    The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
+    but never take it for granted. Can improve the performance.
+
+    You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
+    purpose.
+
+    This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
+    """
+
+    if not explain:
+        logger.setLevel(logging.CRITICAL)
+    else:
+        logger.setLevel(logging.INFO)
+
+    length = len(sequences)  # type: int
+
+    if length == 0:
+        logger.warning("Given content is empty, stopping the process very early, returning empty utf_8 str match")
+        return CharsetMatches(
+            [
+                CharsetMatch(
+                    sequences,
+                    "utf_8",
+                    0.,
+                    False,
+                    [],
+                    ""
+                )
+            ]
+        )
+
+    if cp_isolation is not None:
+        logger.warning('cp_isolation is set. use this flag for debugging purpose. '
+                       'limited list of encoding allowed : %s.',
+                       ', '.join(cp_isolation))
+        cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
+    else:
+        cp_isolation = []
+
+    if cp_exclusion is not None:
+        logger.warning(
+            'cp_exclusion is set. use this flag for debugging purpose. '
+            'limited list of encoding excluded : %s.',
+            ', '.join(cp_exclusion))
+        cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
+    else:
+        cp_exclusion = []
+
+    if length <= (chunk_size * steps):
+        logger.warning(
+            'override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.',
+            steps, chunk_size, length)
+        steps = 1
+        chunk_size = length
+
+    if steps > 1 and length / steps < chunk_size:
+        chunk_size = int(length / steps)
+
+    is_too_small_sequence = len(sequences) < TOO_SMALL_SEQUENCE  # type: bool
+    is_too_large_sequence = len(sequences) >= TOO_BIG_SEQUENCE  # type: bool
+
+    if is_too_small_sequence:
+        warn('Trying to detect encoding from a tiny portion of ({}) byte(s).'.format(length))
+
+    prioritized_encodings = []  # type: List[str]
+
+    specified_encoding = any_specified_encoding(sequences) if preemptive_behaviour is True else None  # type: Optional[str]
+
+    if specified_encoding is not None:
+        prioritized_encodings.append(specified_encoding)
+        logger.info('Detected declarative mark in sequence. Priority +1 given for %s.', specified_encoding)
+
+    tested = set()  # type: Set[str]
+    tested_but_hard_failure = []  # type: List[str]
+    tested_but_soft_failure = []  # type: List[str]
+
+    fallback_ascii = None  # type: Optional[CharsetMatch]
+    fallback_u8 = None  # type: Optional[CharsetMatch]
+    fallback_specified = None  # type: Optional[CharsetMatch]
+
+    single_byte_hard_failure_count = 0  # type: int
+    single_byte_soft_failure_count = 0  # type: int
+
+    results = CharsetMatches()  # type: CharsetMatches
+
+    sig_encoding, sig_payload = identify_sig_or_bom(sequences)
+
+    if sig_encoding is not None:
+        prioritized_encodings.append(sig_encoding)
+        logger.info('Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.', len(sig_payload), sig_encoding)
+
+    prioritized_encodings.append("ascii")
+
+    if "utf_8" not in prioritized_encodings:
+        prioritized_encodings.append("utf_8")
+
+    for encoding_iana in prioritized_encodings+IANA_SUPPORTED:
+
+        if cp_isolation and encoding_iana not in cp_isolation:
+            continue
+
+        if cp_exclusion and encoding_iana in cp_exclusion:
+            continue
+
+        if encoding_iana in tested:
+            continue
+
+        tested.add(encoding_iana)
+
+        decoded_payload = None  # type: Optional[str]
+        bom_or_sig_available = sig_encoding == encoding_iana  # type: bool
+        strip_sig_or_bom = bom_or_sig_available and should_strip_sig_or_bom(encoding_iana)  # type: bool
+
+        if encoding_iana in {"utf_16", "utf_32"} and bom_or_sig_available is False:
+            logger.info("Encoding %s wont be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.", encoding_iana)
+            continue
+
+        try:
+            is_multi_byte_decoder = is_multi_byte_encoding(encoding_iana)  # type: bool
+        except (ModuleNotFoundError, ImportError):
+            logger.debug("Encoding %s does not provide an IncrementalDecoder", encoding_iana)
+            continue
+
+        try:
+            if is_too_large_sequence and is_multi_byte_decoder is False:
+                str(
+                    sequences[:int(50e4)] if strip_sig_or_bom is False else sequences[len(sig_payload):int(50e4)],
+                    encoding=encoding_iana
+                )
+            else:
+                decoded_payload = str(
+                    sequences if strip_sig_or_bom is False else sequences[len(sig_payload):],
+                    encoding=encoding_iana
+                )
+        except UnicodeDecodeError as e:
+            logger.warning('Code page %s does not fit given bytes sequence at ALL. %s', encoding_iana, str(e))
+            tested_but_hard_failure.append(encoding_iana)
+            if not is_multi_byte_decoder:
+                single_byte_hard_failure_count += 1
+            continue
+        except LookupError:
+            tested_but_hard_failure.append(encoding_iana)
+            if not is_multi_byte_decoder:
+                single_byte_hard_failure_count += 1
+            continue
+
+        similar_soft_failure_test = False  # type: bool
+
+        for encoding_soft_failed in tested_but_soft_failure:
+            if is_cp_similar(encoding_iana, encoding_soft_failed):
+                similar_soft_failure_test = True
+                break
+
+        if similar_soft_failure_test:
+            logger.warning("%s is deemed too similar to code page %s and was consider unsuited already. Continuing!", encoding_iana, encoding_soft_failed)
+            continue
+
+        r_ = range(
+            0 if bom_or_sig_available is False else len(sig_payload),
+            length,
+            int(length / steps)
+        )
+
+        multi_byte_bonus = is_multi_byte_decoder and decoded_payload is not None and len(decoded_payload) < length  # type: bool
+
+        if multi_byte_bonus:
+            logger.info('Code page %s is a multi byte encoding table and it appear that at least one character was encoded using n-bytes.', encoding_iana)
+
+        max_chunk_gave_up = int(len(r_) / 4)  # type: int
+
+        if max_chunk_gave_up < 2:
+            max_chunk_gave_up = 2
+
+        early_stop_count = 0  # type: int
+
+        md_chunks = []  # type: List[str]
+        md_ratios = []
+
+        for i in r_:
+            cut_sequence = sequences[i:i + chunk_size]
+
+            if bom_or_sig_available and strip_sig_or_bom is False:
+                cut_sequence = sig_payload+cut_sequence
+
+            chunk = cut_sequence.decode(encoding_iana, errors="ignore")  # type: str
+
+            md_chunks.append(chunk)
+
+            md_ratios.append(
+                mess_ratio(
+                    chunk,
+                    threshold
+                )
+            )
+
+            if md_ratios[-1] >= threshold:
+                early_stop_count += 1
+
+            if (early_stop_count >= max_chunk_gave_up) or (bom_or_sig_available and strip_sig_or_bom is False):
+                break
+
+        if md_ratios:
+            mean_mess_ratio = sum(md_ratios) / len(md_ratios)  # type: float
+        else:
+            mean_mess_ratio = 0.
+
+        if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
+            tested_but_soft_failure.append(encoding_iana)
+            if not is_multi_byte_decoder:
+                single_byte_soft_failure_count += 1
+            logger.warning('%s was excluded because of initial chaos probing. Gave up %i time(s). '
+                           'Computed mean chaos is %f %%.',
+                           encoding_iana,
+                           early_stop_count,
+                           round(mean_mess_ratio * 100, ndigits=3))
+            # Preparing those fallbacks in case we got nothing.
+            if encoding_iana in ["ascii", "utf_8", specified_encoding]:
+                fallback_entry = CharsetMatch(
+                    sequences,
+                    encoding_iana,
+                    threshold,
+                    False,
+                    [],
+                    decoded_payload
+                )
+                if encoding_iana == specified_encoding:
+                    fallback_specified = fallback_entry
+                elif encoding_iana == "ascii":
+                    fallback_ascii = fallback_entry
+                else:
+                    fallback_u8 = fallback_entry
+            continue
+
+        logger.info(
+            '%s passed initial chaos probing. Mean measured chaos is %f %%',
+            encoding_iana,
+            round(mean_mess_ratio * 100, ndigits=3)
+        )
+
+        if not is_multi_byte_decoder:
+            target_languages = encoding_languages(encoding_iana)  # type: List[str]
+        else:
+            target_languages = mb_encoding_languages(encoding_iana)
+
+        if target_languages:
+            logger.info("{} should target any language(s) of {}".format(encoding_iana, str(target_languages)))
+
+        cd_ratios = []
+
+        for chunk in md_chunks:
+            chunk_languages = coherence_ratio(chunk, 0.1, ",".join(target_languages) if target_languages else None)
+
+            cd_ratios.append(
+                chunk_languages
+            )
+
+        cd_ratios_merged = merge_coherence_ratios(cd_ratios)
+
+        if cd_ratios_merged:
+            logger.info("We detected language {} using {}".format(cd_ratios_merged, encoding_iana))
+
+        results.append(
+            CharsetMatch(
+                sequences,
+                encoding_iana,
+                mean_mess_ratio,
+                bom_or_sig_available,
+                cd_ratios_merged,
+                decoded_payload
+            )
+        )
+
+        if encoding_iana in [specified_encoding, "ascii", "utf_8"] and mean_mess_ratio < 0.1:
+            logger.info("%s is most likely the one. Stopping the process.", encoding_iana)
+            return CharsetMatches(
+                [results[encoding_iana]]
+            )
+
+        if encoding_iana == sig_encoding:
+            logger.info(
+                "%s is most likely the one as we detected a BOM or SIG within the beginning of the sequence.",
+                encoding_iana
+            )
+            return CharsetMatches(
+                [results[encoding_iana]]
+            )
+
+        if results[-1].languages:
+            logger.info(
+                "Using %s code page we detected the following languages: %s",
+                encoding_iana,
+                results[encoding_iana]._languages
+            )
+
+    if len(results) == 0:
+        if fallback_u8 or fallback_ascii or fallback_specified:
+            logger.warning("Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.")
+
+        if fallback_specified:
+            logger.warning("%s will be used as a fallback match", fallback_specified.encoding)
+            results.append(fallback_specified)
+        elif (fallback_u8 and fallback_ascii is None) or (fallback_u8 and fallback_u8.fingerprint != fallback_ascii.fingerprint):
+            logger.warning("utf_8 will be used as a fallback match")
+            results.append(fallback_u8)
+        elif fallback_ascii:
+            logger.warning("ascii will be used as a fallback match")
+            results.append(fallback_ascii)
+
+    return results
+
+
+def from_fp(
+        fp: BinaryIO,
+        steps: int = 5,
+        chunk_size: int = 512,
+        threshold: float = 0.20,
+        cp_isolation: List[str] = None,
+        cp_exclusion: List[str] = None,
+        preemptive_behaviour: bool = True,
+        explain: bool = False
+) -> CharsetMatches:
+    """
+    Same thing than the function from_bytes but using a file pointer that is already ready.
+    Will not close the file pointer.
+    """
+    return from_bytes(
+        fp.read(),
+        steps,
+        chunk_size,
+        threshold,
+        cp_isolation,
+        cp_exclusion,
+        preemptive_behaviour,
+        explain
+    )
+
+
+def from_path(
+        path: PathLike,
+        steps: int = 5,
+        chunk_size: int = 512,
+        threshold: float = 0.20,
+        cp_isolation: List[str] = None,
+        cp_exclusion: List[str] = None,
+        preemptive_behaviour: bool = True,
+        explain: bool = False
+) -> CharsetMatches:
+    """
+    Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
+    Can raise IOError.
+    """
+    with open(path, 'rb') as fp:
+        return from_fp(fp, steps, chunk_size, threshold, cp_isolation, cp_exclusion, preemptive_behaviour, explain)
+
+
+def normalize(path: PathLike, steps: int = 5, chunk_size: int = 512, threshold: float = 0.20, cp_isolation: List[str] = None, cp_exclusion: List[str] = None, preemptive_behaviour: bool = True) -> CharsetMatch:
+    """
+    Take a (text-based) file path and try to create another file next to it, this time using UTF-8.
+    """
+    results = from_path(
+        path,
+        steps,
+        chunk_size,
+        threshold,
+        cp_isolation,
+        cp_exclusion,
+        preemptive_behaviour
+    )
+
+    filename = basename(path)
+    target_extensions = list(splitext(filename))
+
+    if len(results) == 0:
+        raise IOError('Unable to normalize "{}", no encoding charset seems to fit.'.format(filename))
+
+    result = results.best()
+
+    target_extensions[0] += '-' + result.encoding  # type: ignore
+
+    with open('{}'.format(path.replace(filename, ''.join(target_extensions))), 'wb') as fp:
+        fp.write(
+            result.output()  # type: ignore
+        )
+
+    return result  # type: ignore

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/assets/__init__.py

@@ -0,0 +1,52 @@
+"""
+This submodule purpose is to load attached JSON asset.
+Will be loaded once per package import / python init.
+
+The file 'frequencies.json' is mandatory for language/coherence detection. Not having it will weaker considerably
+the core detection.
+"""
+from collections import OrderedDict
+
+
+FREQUENCIES = OrderedDict(
+    [
+        ('English', ['e', 'a', 't', 'i', 'o', 'n', 's', 'r', 'h', 'l', 'd', 'c', 'u', 'm', 'f', 'p', 'g', 'w', 'y', 'b', 'v', 'k', 'x', 'j', 'z', 'q']),
+        ('German', ['e', 'n', 'i', 'r', 's', 't', 'a', 'd', 'h', 'u', 'l', 'g', 'o', 'c', 'm', 'b', 'f', 'k', 'w', 'z', 'p', 'v', 'ü', 'ä', 'ö', 'j']),
+        ('French', ['e', 'a', 's', 'n', 'i', 't', 'r', 'l', 'u', 'o', 'd', 'c', 'p', 'm', 'é', 'v', 'g', 'f', 'b', 'h', 'q', 'à', 'x', 'è', 'y', 'j']),
+        ('Dutch', ['e', 'n', 'a', 'i', 'r', 't', 'o', 'd', 's', 'l', 'g', 'h', 'v', 'm', 'u', 'k', 'c', 'p', 'b', 'w', 'j', 'z', 'f', 'y', 'x', 'ë']),
+        ('Italian', ['e', 'i', 'a', 'o', 'n', 'l', 't', 'r', 's', 'c', 'd', 'u', 'p', 'm', 'g', 'v', 'f', 'b', 'z', 'h', 'q', 'è', 'à', 'k', 'y', 'ò']),
+        ('Polish', ['a', 'i', 'o', 'e', 'n', 'r', 'z', 'w', 's', 'c', 't', 'k', 'y', 'd', 'p', 'm', 'u', 'l', 'j', 'ł', 'g', 'b', 'h', 'ą', 'ę', 'ó']),
+        ('Spanish', ['e', 'a', 'o', 'n', 's', 'r', 'i', 'l', 'd', 't', 'c', 'u', 'm', 'p', 'b', 'g', 'v', 'f', 'y', 'ó', 'h', 'q', 'í', 'j', 'z', 'á']),
+        ('Russian', ['о', 'а', 'е', 'и', 'н', 'с', 'т', 'р', 'в', 'л', 'к', 'м', 'д', 'п', 'у', 'г', 'я', 'ы', 'з', 'б', 'й', 'ь', 'ч', 'х', 'ж', 'ц']),
+        ('Japanese', ['の', 'に', 'る', 'た', 'は', 'ー', 'と', 'し', 'を', 'で', 'て', 'が', 'い', 'ン', 'れ', 'な', '年', 'ス', 'っ', 'ル', 'か', 'ら', 'あ', 'さ', 'も', 'り']),
+        ('Portuguese', ['a', 'e', 'o', 's', 'i', 'r', 'd', 'n', 't', 'm', 'u', 'c', 'l', 'p', 'g', 'v', 'b', 'f', 'h', 'ã', 'q', 'é', 'ç', 'á', 'z', 'í']),
+        ('Swedish', ['e', 'a', 'n', 'r', 't', 's', 'i', 'l', 'd', 'o', 'm', 'k', 'g', 'v', 'h', 'f', 'u', 'p', 'ä', 'c', 'b', 'ö', 'å', 'y', 'j', 'x']),
+        ('Chinese', ['的', '一', '是', '不', '了', '在', '人', '有', '我', '他', '这', '个', '们', '中', '来', '上', '大', '为', '和', '国', '地', '到', '以', '说', '时', '要', '就', '出', '会']),
+        ('Ukrainian', ['о', 'а', 'н', 'і', 'и', 'р', 'в', 'т', 'е', 'с', 'к', 'л', 'у', 'д', 'м', 'п', 'з', 'я', 'ь', 'б', 'г', 'й', 'ч', 'х', 'ц', 'ї']),
+        ('Norwegian', ['e', 'r', 'n', 't', 'a', 's', 'i', 'o', 'l', 'd', 'g', 'k', 'm', 'v', 'f', 'p', 'u', 'b', 'h', 'å', 'y', 'j', 'ø', 'c', 'æ', 'w']),
+        ('Finnish', ['a', 'i', 'n', 't', 'e', 's', 'l', 'o', 'u', 'k', 'ä', 'm', 'r', 'v', 'j', 'h', 'p', 'y', 'd', 'ö', 'g', 'c', 'b', 'f', 'w', 'z']),
+        ('Vietnamese', ['n', 'h', 't', 'i', 'c', 'g', 'a', 'o', 'u', 'm', 'l', 'r', 'à', 'đ', 's', 'e', 'v', 'p', 'b', 'y', 'ư', 'd', 'á', 'k', 'ộ', 'ế']),
+        ('Czech', ['o', 'e', 'a', 'n', 't', 's', 'i', 'l', 'v', 'r', 'k', 'd', 'u', 'm', 'p', 'í', 'c', 'h', 'z', 'á', 'y', 'j', 'b', 'ě', 'é', 'ř']),
+        ('Hungarian', ['e', 'a', 't', 'l', 's', 'n', 'k', 'r', 'i', 'o', 'z', 'á', 'é', 'g', 'm', 'b', 'y', 'v', 'd', 'h', 'u', 'p', 'j', 'ö', 'f', 'c']),
+        ('Korean', ['이', '다', '에', '의', '는', '로', '하', '을', '가', '고', '지', '서', '한', '은', '기', '으', '년', '대', '사', '시', '를', '리', '도', '인', '스', '일']),
+        ('Indonesian', ['a', 'n', 'e', 'i', 'r', 't', 'u', 's', 'd', 'k', 'm', 'l', 'g', 'p', 'b', 'o', 'h', 'y', 'j', 'c', 'w', 'f', 'v', 'z', 'x', 'q']),
+        ('Turkish', ['a', 'e', 'i', 'n', 'r', 'l', 'ı', 'k', 'd', 't', 's', 'm', 'y', 'u', 'o', 'b', 'ü', 'ş', 'v', 'g', 'z', 'h', 'c', 'p', 'ç', 'ğ']),
+        ('Romanian', ['e', 'i', 'a', 'r', 'n', 't', 'u', 'l', 'o', 'c', 's', 'd', 'p', 'm', 'ă', 'f', 'v', 'î', 'g', 'b', 'ș', 'ț', 'z', 'h', 'â', 'j']),
+        ('Farsi', ['ا', 'ی', 'ر', 'د', 'ن', 'ه', 'و', 'م', 'ت', 'ب', 'س', 'ل', 'ک', 'ش', 'ز', 'ف', 'گ', 'ع', 'خ', 'ق', 'ج', 'آ', 'پ', 'ح', 'ط', 'ص']),
+        ('Arabic', ['ا', 'ل', 'ي', 'م', 'و', 'ن', 'ر', 'ت', 'ب', 'ة', 'ع', 'د', 'س', 'ف', 'ه', 'ك', 'ق', 'أ', 'ح', 'ج', 'ش', 'ط', 'ص', 'ى', 'خ', 'إ']),
+        ('Danish', ['e', 'r', 'n', 't', 'a', 'i', 's', 'd', 'l', 'o', 'g', 'm', 'k', 'f', 'v', 'u', 'b', 'h', 'p', 'å', 'y', 'ø', 'æ', 'c', 'j', 'w']),
+        ('Serbian', ['а', 'и', 'о', 'е', 'н', 'р', 'с', 'у', 'т', 'к', 'ј', 'в', 'д', 'м', 'п', 'л', 'г', 'з', 'б', 'a', 'i', 'e', 'o', 'n', 'ц', 'ш']),
+        ('Lithuanian', ['i', 'a', 's', 'o', 'r', 'e', 't', 'n', 'u', 'k', 'm', 'l', 'p', 'v', 'd', 'j', 'g', 'ė', 'b', 'y', 'ų', 'š', 'ž', 'c', 'ą', 'į']),
+        ('Slovene', ['e', 'a', 'i', 'o', 'n', 'r', 's', 'l', 't', 'j', 'v', 'k', 'd', 'p', 'm', 'u', 'z', 'b', 'g', 'h', 'č', 'c', 'š', 'ž', 'f', 'y']),
+        ('Slovak', ['o', 'a', 'e', 'n', 'i', 'r', 'v', 't', 's', 'l', 'k', 'd', 'm', 'p', 'u', 'c', 'h', 'j', 'b', 'z', 'á', 'y', 'ý', 'í', 'č', 'é']),
+        ('Hebrew', ['י', 'ו', 'ה', 'ל', 'ר', 'ב', 'ת', 'מ', 'א', 'ש', 'נ', 'ע', 'ם', 'ד', 'ק', 'ח', 'פ', 'ס', 'כ', 'ג', 'ט', 'צ', 'ן', 'ז', 'ך']),
+        ('Bulgarian', ['а', 'и', 'о', 'е', 'н', 'т', 'р', 'с', 'в', 'л', 'к', 'д', 'п', 'м', 'з', 'г', 'я', 'ъ', 'у', 'б', 'ч', 'ц', 'й', 'ж', 'щ', 'х']),
+        ('Croatian', ['a', 'i', 'o', 'e', 'n', 'r', 'j', 's', 't', 'u', 'k', 'l', 'v', 'd', 'm', 'p', 'g', 'z', 'b', 'c', 'č', 'h', 'š', 'ž', 'ć', 'f']),
+        ('Hindi', ['क', 'र', 'स', 'न', 'त', 'म', 'ह', 'प', 'य', 'ल', 'व', 'ज', 'द', 'ग', 'ब', 'श', 'ट', 'अ', 'ए', 'थ', 'भ', 'ड', 'च', 'ध', 'ष', 'इ']),
+        ('Estonian', ['a', 'i', 'e', 's', 't', 'l', 'u', 'n', 'o', 'k', 'r', 'd', 'm', 'v', 'g', 'p', 'j', 'h', 'ä', 'b', 'õ', 'ü', 'f', 'c', 'ö', 'y']),
+        ('Simple English', ['e', 'a', 't', 'i', 'o', 'n', 's', 'r', 'h', 'l', 'd', 'c', 'm', 'u', 'f', 'p', 'g', 'w', 'b', 'y', 'v', 'k', 'j', 'x', 'z', 'q']),
+        ('Thai', ['า', 'น', 'ร', 'อ', 'ก', 'เ', 'ง', 'ม', 'ย', 'ล', 'ว', 'ด', 'ท', 'ส', 'ต', 'ะ', 'ป', 'บ', 'ค', 'ห', 'แ', 'จ', 'พ', 'ช', 'ข', 'ใ']),
+        ('Greek', ['α', 'τ', 'ο', 'ι', 'ε', 'ν', 'ρ', 'σ', 'κ', 'η', 'π', 'ς', 'υ', 'μ', 'λ', 'ί', 'ό', 'ά', 'γ', 'έ', 'δ', 'ή', 'ω', 'χ', 'θ', 'ύ']),
+        ('Tamil', ['க', 'த', 'ப', 'ட', 'ர', 'ம', 'ல', 'ன', 'வ', 'ற', 'ய', 'ள', 'ச', 'ந', 'இ', 'ண', 'அ', 'ஆ', 'ழ', 'ங', 'எ', 'உ', 'ஒ', 'ஸ']),
+        ('Classical Chinese', ['之', '年', '為', '也', '以', '一', '人', '其', '者', '國', '有', '二', '十', '於', '曰', '三', '不', '大', '而', '子', '中', '五', '四'])]
+)

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/cd.py

@@ -0,0 +1,261 @@
+from codecs import IncrementalDecoder
+from functools import lru_cache
+from typing import List, Set, Optional, Tuple, Dict
+import importlib
+
+from charset_normalizer.models import CoherenceMatches
+from charset_normalizer.utils import unicode_range, is_unicode_range_secondary, is_multi_byte_encoding
+from charset_normalizer.md import is_suspiciously_successive_range
+from charset_normalizer.assets import FREQUENCIES
+from collections import Counter
+
+
+def encoding_unicode_range(iana_name: str) -> List[str]:
+    """
+    Return associated unicode ranges in a single byte code page.
+    """
+    if is_multi_byte_encoding(iana_name):
+        raise IOError("Function not supported on multi-byte code page")
+
+    decoder = importlib.import_module('encodings.{}'.format(iana_name)).IncrementalDecoder  # type: ignore
+
+    p = decoder(errors="ignore")  # type: IncrementalDecoder
+    seen_ranges = set()  # type: Set[str]
+
+    for i in range(48, 255):
+        chunk = p.decode(
+            bytes([i])
+        )  # type: str
+
+        if chunk:
+            character_range = unicode_range(chunk)  # type: Optional[str]
+
+            if character_range is None:
+                continue
+
+            if is_unicode_range_secondary(character_range) is False:
+                seen_ranges.add(character_range)
+
+    return sorted(list(seen_ranges))
+
+
+def unicode_range_languages(primary_range: str) -> List[str]:
+    """
+    Return inferred languages used with a unicode range.
+    """
+    languages = []  # type: List[str]
+
+    for language, characters in FREQUENCIES.items():
+        for character in characters:
+            if unicode_range(character) == primary_range:
+                languages.append(language)
+                break
+
+    return languages
+
+
+@lru_cache()
+def encoding_languages(iana_name: str) -> List[str]:
+    """
+    Single-byte encoding language association. Some code page are heavily linked to particular language(s).
+    This function does the correspondence.
+    """
+    unicode_ranges = encoding_unicode_range(iana_name)  # type: List[str]
+    primary_range = None  # type: Optional[str]
+
+    for specified_range in unicode_ranges:
+        if "Latin" not in specified_range:
+            primary_range = specified_range
+            break
+
+    if primary_range is None:
+        return ["Latin Based"]
+
+    return unicode_range_languages(primary_range)
+
+
+def mb_encoding_languages(iana_name: str) -> List[str]:
+    """
+    Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
+    This function does the correspondence.
+    """
+    if iana_name.startswith("shift_") or iana_name.startswith("iso2022_jp") or iana_name.startswith("euc_j") or iana_name in {"cp932"}:
+        return ["Japanese"]
+    if iana_name.startswith("gb") or iana_name in {"big5", "cp950", "big5hkscs"}:
+        return ["Chinese", "Classical Chinese"]
+    if iana_name.startswith("iso2022_kr") or iana_name in {"johab", "cp949", "euc_kr"}:
+        return ["Korean"]
+
+    return []
+
+
+def alphabet_languages(characters: List[str]) -> List[str]:
+    """
+    Return associated languages associated to given characters.
+    """
+    languages = []  # type: List[str]
+
+    for language, language_characters in FREQUENCIES.items():
+        character_match_count = 0  # type: int
+        character_count = len(language_characters)  # type: int
+
+        for character in language_characters:
+            if character in characters:
+                character_match_count += 1
+
+        if character_match_count / character_count >= 0.2:
+            languages.append(language)
+
+    return languages
+
+
+def characters_popularity_compare(language: str, ordered_characters: List[str]) -> float:
+    """
+    Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
+    The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
+    Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
+    """
+    if language not in FREQUENCIES:
+        raise ValueError("{} not available".format(language))
+
+    character_approved_count = 0  # type: int
+
+    for character in ordered_characters:
+        if character not in FREQUENCIES[language]:
+            continue
+
+        characters_before_source = FREQUENCIES[language][0:FREQUENCIES[language].index(character)]  # type: List[str]
+        characters_after_source = FREQUENCIES[language][FREQUENCIES[language].index(character):]  # type: List[str]
+
+        characters_before = ordered_characters[0:ordered_characters.index(character)]  # type: List[str]
+        characters_after = ordered_characters[ordered_characters.index(character):]  # type: List[str]
+
+        before_match_count = [e in characters_before for e in characters_before_source].count(True)  # type: int
+        after_match_count = [e in characters_after for e in characters_after_source].count(True)  # type: int
+
+        if len(characters_before_source) == 0 and before_match_count <= 4:
+            character_approved_count += 1
+            continue
+
+        if len(characters_after_source) == 0 and after_match_count <= 4:
+            character_approved_count += 1
+            continue
+
+        if before_match_count / len(characters_before_source) >= 0.4 or after_match_count / len(characters_after_source) >= 0.4:
+            character_approved_count += 1
+            continue
+
+    return character_approved_count / len(ordered_characters)
+
+
+def alpha_unicode_split(decoded_sequence: str) -> List[str]:
+    """
+    Given a decoded text sequence, return a list of str. Unicode range / alphabet separation.
+    Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list;
+    One containing the latin letters and the other hebrew.
+    """
+    layers = {}  # type: Dict[str, str]
+
+    for character in decoded_sequence:
+        if character.isalpha() is False:
+            continue
+
+        character_range = unicode_range(character)  # type: str
+
+        layer_target_range = None  # type: Optional[str]
+
+        for discovered_range in layers:
+            if is_suspiciously_successive_range(discovered_range, character_range) is False:
+                layer_target_range = discovered_range
+                break
+
+        if layer_target_range is None:
+            layer_target_range = character_range
+
+        if layer_target_range not in layers:
+            layers[layer_target_range] = character.lower()
+            continue
+
+        layers[layer_target_range] += character.lower()
+
+    return list(layers.values())
+
+
+def merge_coherence_ratios(results: List[CoherenceMatches]) -> CoherenceMatches:
+    """
+    This function merge results previously given by the function coherence_ratio.
+    The return type is the same as coherence_ratio.
+    """
+    per_language_ratios = {}  # type: Dict[str, List[float]]
+    merge = []  # type: CoherenceMatches
+
+    for result in results:
+        for sub_result in result:
+            language, ratio = sub_result
+            if language not in per_language_ratios:
+                per_language_ratios[language] = [ratio]
+                continue
+            per_language_ratios[language].append(
+                ratio
+            )
+
+    for language in per_language_ratios:
+        merge.append(
+            (
+                language,
+                round(
+                    sum(
+                        per_language_ratios[language]
+                    ) / len(per_language_ratios[language]),
+                    4
+                )
+            )
+        )
+
+    return sorted(merge, key=lambda x: x[1], reverse=True)
+
+
+@lru_cache(maxsize=2048)
+def coherence_ratio(decoded_sequence: str, threshold: float = 0.1, lg_inclusion: Optional[str] = None) -> CoherenceMatches:
+    """
+    Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
+    A layer = Character extraction by alphabets/ranges.
+    """
+
+    results = []  # type: List[Tuple[str, float]]
+
+    sufficient_match_count = 0  # type: int
+
+    if lg_inclusion is not None:
+        lg_inclusion = lg_inclusion.split(",")
+
+    if lg_inclusion is not None and "Latin Based" in lg_inclusion:
+        lg_inclusion.remove("Latin Based")
+
+    for layer in alpha_unicode_split(decoded_sequence):
+        sequence_frequencies = Counter(layer)  # type: Counter
+        most_common = sequence_frequencies.most_common()
+
+        character_count = sum([o for c, o in most_common])  # type: int
+
+        if character_count <= 32:
+            continue
+
+        popular_character_ordered = [c for c, o in most_common]  # type: List[str]
+
+        for language in lg_inclusion or alphabet_languages(popular_character_ordered):
+            ratio = characters_popularity_compare(language, popular_character_ordered)  # type: float
+
+            if ratio < threshold:
+                continue
+            elif ratio >= 0.8:
+                sufficient_match_count += 1
+
+            results.append(
+                (language, round(ratio, 4))
+            )
+
+            if sufficient_match_count >= 3:
+                break
+
+    return sorted(results, key=lambda x: x[1], reverse=True)

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/cli/normalizer.py

@@ -0,0 +1,223 @@
+import argparse
+import sys
+from os.path import abspath
+from json import dumps
+
+from charset_normalizer import from_fp
+from charset_normalizer.models import CliDetectionResult
+from charset_normalizer.version import __version__
+
+from platform import python_version
+
+
+def query_yes_no(question, default="yes"):
+    """Ask a yes/no question via input() and return their answer.
+
+    "question" is a string that is presented to the user.
+    "default" is the presumed answer if the user just hits <Enter>.
+        It must be "yes" (the default), "no" or None (meaning
+        an answer is required of the user).
+
+    The "answer" return value is True for "yes" or False for "no".
+
+    Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input
+    """
+    valid = {"yes": True, "y": True, "ye": True,
+             "no": False, "n": False}
+    if default is None:
+        prompt = " [y/n] "
+    elif default == "yes":
+        prompt = " [Y/n] "
+    elif default == "no":
+        prompt = " [y/N] "
+    else:
+        raise ValueError("invalid default answer: '%s'" % default)
+
+    while True:
+        sys.stdout.write(question + prompt)
+        choice = input().lower()
+        if default is not None and choice == '':
+            return valid[default]
+        elif choice in valid:
+            return valid[choice]
+        else:
+            sys.stdout.write("Please respond with 'yes' or 'no' "
+                             "(or 'y' or 'n').\n")
+
+
+def cli_detect(argv=None):
+    """
+    CLI assistant using ARGV and ArgumentParser
+    :param argv:
+    :return: 0 if everything is fine, anything else equal trouble
+    """
+    parser = argparse.ArgumentParser(
+        description="The Real First Universal Charset Detector. "
+                    "Discover originating encoding used on text file. "
+                    "Normalize text to unicode."
+    )
+
+    parser.add_argument('files', type=argparse.FileType('rb'), nargs='+', help='File(s) to be analysed')
+    parser.add_argument('-v', '--verbose', action="store_true", default=False, dest='verbose',
+                        help='Display complementary information about file if any. Stdout will contain logs about the detection process.')
+    parser.add_argument('-a', '--with-alternative', action="store_true", default=False, dest='alternatives',
+                        help='Output complementary possibilities if any. Top-level JSON WILL be a list.')
+    parser.add_argument('-n', '--normalize', action="store_true", default=False, dest='normalize',
+                        help='Permit to normalize input file. If not set, program does not write anything.')
+    parser.add_argument('-m', '--minimal', action="store_true", default=False, dest='minimal',
+                        help='Only output the charset detected to STDOUT. Disabling JSON output.')
+    parser.add_argument('-r', '--replace', action="store_true", default=False, dest='replace',
+                        help='Replace file when trying to normalize it instead of creating a new one.')
+    parser.add_argument('-f', '--force', action="store_true", default=False, dest='force',
+                        help='Replace file without asking if you are sure, use this flag with caution.')
+    parser.add_argument('-t', '--threshold', action="store", default=0.1, type=float, dest='threshold',
+                        help="Define a custom maximum amount of chaos allowed in decoded content. 0. <= chaos <= 1.")
+    parser.add_argument(
+        "--version",
+        action="version",
+        version="Charset-Normalizer {} - Python {}".format(__version__, python_version()),
+        help="Show version information and exit."
+    )
+
+    args = parser.parse_args(argv)
+
+    if args.replace is True and args.normalize is False:
+        print('Use --replace in addition of --normalize only.', file=sys.stderr)
+        return 1
+
+    if args.force is True and args.replace is False:
+        print('Use --force in addition of --replace only.', file=sys.stderr)
+        return 1
+
+    if args.threshold < 0. or args.threshold > 1.:
+        print('--threshold VALUE should be between 0. AND 1.', file=sys.stderr)
+        return 1
+
+    x_ = []
+
+    for my_file in args.files:
+
+        matches = from_fp(
+            my_file,
+            threshold=args.threshold,
+            explain=args.verbose
+        )
+
+        if len(matches) == 0:
+            print('Unable to identify originating encoding for "{}". {}'.format(my_file.name, 'Maybe try increasing maximum amount of chaos.' if args.threshold < 1. else ''), file=sys.stderr)
+            x_.append(
+                CliDetectionResult(
+                    abspath(my_file.name),
+                    None,
+                    [],
+                    [],
+                    "Unknown",
+                    [],
+                    False,
+                    1.,
+                    0.,
+                    None,
+                    True
+                )
+            )
+        else:
+
+            r_ = matches.best()
+            p_ = r_.first()
+
+            x_.append(
+                CliDetectionResult(
+                    abspath(my_file.name),
+                    p_.encoding,
+                    p_.encoding_aliases,
+                    [cp for cp in p_.could_be_from_charset if cp != p_.encoding],
+                    p_.language,
+                    p_.alphabets,
+                    p_.bom,
+                    p_.percent_chaos,
+                    p_.percent_coherence,
+                    None,
+                    True
+                )
+            )
+
+            if len(matches) > 1 and args.alternatives:
+                for el in matches:
+                    if el != p_:
+                        x_.append(
+                            CliDetectionResult(
+                                abspath(my_file.name),
+                                el.encoding,
+                                el.encoding_aliases,
+                                [cp for cp in el.could_be_from_charset if cp != el.encoding],
+                                el.language,
+                                el.alphabets,
+                                el.bom,
+                                el.percent_chaos,
+                                el.percent_coherence,
+                                None,
+                                False
+                            )
+                        )
+
+            if args.normalize is True:
+
+                if p_.encoding.startswith('utf') is True:
+                    print('"{}" file does not need to be normalized, as it already came from unicode.'.format(my_file.name), file=sys.stderr)
+                    if my_file.closed is False:
+                        my_file.close()
+                    continue
+
+                o_ = my_file.name.split('.')  # type: list[str]
+
+                if args.replace is False:
+                    o_.insert(-1, p_.encoding)
+                    if my_file.closed is False:
+                        my_file.close()
+                else:
+                    if args.force is False and query_yes_no(
+                            'Are you sure to normalize "{}" by replacing it ?'.format(my_file.name), 'no') is False:
+                        if my_file.closed is False:
+                            my_file.close()
+                        continue
+
+                try:
+                    x_[0].unicode_path = abspath('./{}'.format('.'.join(o_)))
+
+                    with open(x_[0].unicode_path, 'w', encoding='utf-8') as fp:
+                        fp.write(
+                            str(p_)
+                        )
+                except IOError as e:
+                    print(str(e), file=sys.stderr)
+                    if my_file.closed is False:
+                        my_file.close()
+                    return 2
+
+        if my_file.closed is False:
+            my_file.close()
+
+    if args.minimal is False:
+        print(
+            dumps(
+                [
+                    el.__dict__ for el in x_
+                ] if len(x_) > 1 else x_[0].__dict__,
+                ensure_ascii=True,
+                indent=4
+            )
+        )
+    else:
+        print(
+            ', '.join(
+                [
+                    el.encoding for el in x_
+                ]
+            )
+        )
+
+    return 0
+
+
+if __name__ == '__main__':
+    cli_detect()

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/legacy.py

@@ -0,0 +1,38 @@
+from charset_normalizer.api import from_bytes
+from charset_normalizer.constant import CHARDET_CORRESPONDENCE
+from typing import Dict, Optional, Union
+
+
+def detect(byte_str: bytes) -> Dict[str, Optional[Union[str, float]]]:
+    """
+    chardet legacy method
+    Detect the encoding of the given byte string. It should be mostly backward-compatible.
+    Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
+    This function is deprecated and should be used to migrate your project easily, consult the documentation for
+    further information. Not planned for removal.
+
+    :param byte_str:     The byte sequence to examine.
+    """
+    if not isinstance(byte_str, (bytearray, bytes)):
+        raise TypeError('Expected object of type bytes or bytearray, got: '
+                        '{0}'.format(type(byte_str)))
+
+    if isinstance(byte_str, bytearray):
+        byte_str = bytes(byte_str)
+
+    r = from_bytes(byte_str).best()
+
+    encoding = r.encoding if r is not None else None
+    language = r.language if r is not None and r.language != 'Unknown' else ''
+    confidence = 1. - r.chaos if r is not None else None
+
+    # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
+    # but chardet does return 'utf-8-sig' and it is a valid codec name.
+    if r is not None and encoding == 'utf_8' and r.bom:
+        encoding += '_sig'
+
+    return {
+        'encoding': encoding if encoding not in CHARDET_CORRESPONDENCE else CHARDET_CORRESPONDENCE[encoding],
+        'language': language,
+        'confidence': confidence
+    }

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/md.py

@@ -0,0 +1,480 @@
+from functools import lru_cache
+from typing import Optional, List
+
+from charset_normalizer.constant import UNICODE_SECONDARY_RANGE_KEYWORD
+from charset_normalizer.utils import is_punctuation, is_symbol, unicode_range, is_accentuated, is_latin, \
+    remove_accent, is_separator, is_cjk, is_case_variable, is_hangul, is_katakana, is_hiragana, is_ascii, is_thai
+
+
+class MessDetectorPlugin:
+    """
+    Base abstract class used for mess detection plugins.
+    All detectors MUST extend and implement given methods.
+    """
+
+    def eligible(self, character: str) -> bool:
+        """
+        Determine if given character should be fed in.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    def feed(self, character: str) -> None:
+        """
+        The main routine to be executed upon character.
+        Insert the logic in witch the text would be considered chaotic.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    def reset(self) -> None:
+        """
+        Permit to reset the plugin to the initial state.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    @property
+    def ratio(self) -> float:
+        """
+        Compute the chaos ratio based on what your feed() has seen.
+        Must NOT be lower than 0.; No restriction gt 0.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+
+class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
+
+    def __init__(self):
+        self._punctuation_count = 0  # type: int
+        self._symbol_count = 0  # type: int
+        self._character_count = 0  # type: int
+
+        self._last_printable_char = None  # type: Optional[str]
+        self._frenzy_symbol_in_word = False  # type: bool
+
+    def eligible(self, character: str) -> bool:
+        return character.isprintable()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if character != self._last_printable_char and character not in ["<", ">", "=", ":", "/", "&", ";", "{", "}", "[", "]", ",", "|", '"']:
+            if is_punctuation(character):
+                self._punctuation_count += 1
+            elif character.isdigit() is False and is_symbol(character):
+                self._symbol_count += 2
+
+        self._last_printable_char = character
+
+    def reset(self) -> None:
+        self._punctuation_count = 0
+        self._character_count = 0
+        self._symbol_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.
+
+        ratio_of_punctuation = (self._punctuation_count + self._symbol_count) / self._character_count  # type: float
+
+        return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.
+
+
+class TooManyAccentuatedPlugin(MessDetectorPlugin):
+
+    def __init__(self):
+        self._character_count = 0  # type: int
+        self._accentuated_count = 0  # type: int
+
+    def eligible(self, character: str) -> bool:
+        return character.isalpha()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if is_accentuated(character):
+            self._accentuated_count += 1
+
+    def reset(self) -> None:
+        self._character_count = 0
+        self._accentuated_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.
+        ratio_of_accentuation = self._accentuated_count / self._character_count  # type: float
+        return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.
+
+
+class UnprintablePlugin(MessDetectorPlugin):
+
+    def __init__(self):
+        self._unprintable_count = 0  # type: int
+        self._character_count = 0  # type: int
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character not in {'\n', '\t', '\r', '\v'} and character.isprintable() is False:
+            self._unprintable_count += 1
+        self._character_count += 1
+
+    def reset(self) -> None:
+        self._unprintable_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.
+
+        return (self._unprintable_count * 8) / self._character_count
+
+
+class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
+
+    def __init__(self):
+        self._successive_count = 0  # type: int
+        self._character_count = 0  # type: int
+
+        self._last_latin_character = None  # type: Optional[str]
+
+    def eligible(self, character: str) -> bool:
+        return character.isalpha() and is_latin(character)
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+        if self._last_latin_character is not None:
+            if is_accentuated(character) and is_accentuated(self._last_latin_character):
+                if character.isupper() and self._last_latin_character.isupper():
+                    self._successive_count += 1
+                # Worse if its the same char duplicated with different accent.
+                if remove_accent(character) == remove_accent(self._last_latin_character):
+                    self._successive_count += 1
+        self._last_latin_character = character
+
+    def reset(self) -> None:
+        self._successive_count = 0
+        self._character_count = 0
+        self._last_latin_character = None
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.
+
+        return (self._successive_count * 2) / self._character_count
+
+
+class SuspiciousRange(MessDetectorPlugin):
+
+    def __init__(self):
+        self._suspicious_successive_range_count = 0  # type: int
+        self._character_count = 0  # type: int
+        self._last_printable_seen = None  # type: Optional[str]
+
+    def eligible(self, character: str) -> bool:
+        return character.isprintable()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if character.isspace() or is_punctuation(character):
+            self._last_printable_seen = None
+            return
+
+        if self._last_printable_seen is None:
+            self._last_printable_seen = character
+            return
+
+        unicode_range_a = unicode_range(self._last_printable_seen)  # type: Optional[str]
+        unicode_range_b = unicode_range(character)  # type: Optional[str]
+
+        if is_suspiciously_successive_range(unicode_range_a, unicode_range_b):
+            self._suspicious_successive_range_count += 1
+
+        self._last_printable_seen = character
+
+    def reset(self) -> None:
+        self._character_count = 0
+        self._suspicious_successive_range_count = 0
+        self._last_printable_seen = None
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.
+
+        ratio_of_suspicious_range_usage = (self._suspicious_successive_range_count * 2) / self._character_count  # type: float
+
+        if ratio_of_suspicious_range_usage < 0.1:
+            return 0.
+
+        return ratio_of_suspicious_range_usage
+
+
+class SuperWeirdWordPlugin(MessDetectorPlugin):
+
+    def __init__(self):
+        self._word_count = 0  # type: int
+        self._bad_word_count = 0  # type: int
+        self._is_current_word_bad = False  # type: bool
+        self._foreign_long_watch = False  # type: bool
+
+        self._character_count = 0  # type: int
+        self._bad_character_count = 0  # type: int
+
+        self._buffer = ""  # type: str
+        self._buffer_accent_count = 0  # type: int
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character.isalpha():
+            self._buffer = "".join([self._buffer, character])
+            if is_accentuated(character):
+                self._buffer_accent_count += 1
+            if self._foreign_long_watch is False and is_latin(character) is False and is_cjk(character) is False and is_hangul(character) is False and is_katakana(character) is False and is_hiragana(character) is False and is_thai(character) is False:
+                self._foreign_long_watch = True
+            return
+        if not self._buffer:
+            return
+        if (character.isspace() or is_punctuation(character) or is_separator(character)) and self._buffer:
+            self._word_count += 1
+            buffer_length = len(self._buffer)  # type: int
+
+            self._character_count += buffer_length
+
+            if buffer_length >= 4 and self._buffer_accent_count / buffer_length >= 0.3:
+                self._is_current_word_bad = True
+            if buffer_length >= 24 and self._foreign_long_watch:
+                self._is_current_word_bad = True
+
+            if self._is_current_word_bad:
+                self._bad_word_count += 1
+                self._bad_character_count += len(self._buffer)
+                self._is_current_word_bad = False
+
+            self._foreign_long_watch = False
+            self._buffer = ""
+            self._buffer_accent_count = 0
+        elif character not in {"<", ">", "-", "="} and character.isdigit() is False and is_symbol(character):
+            self._is_current_word_bad = True
+            self._buffer += character
+
+    def reset(self) -> None:
+        self._buffer = ""
+        self._is_current_word_bad = False
+        self._foreign_long_watch = False
+        self._bad_word_count = 0
+        self._word_count = 0
+        self._character_count = 0
+        self._bad_character_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._word_count <= 10:
+            return 0.
+
+        return self._bad_character_count / self._character_count
+
+
+class CjkInvalidStopPlugin(MessDetectorPlugin):
+    """
+    GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and can be easily detected.
+    Searching for the overuse of '丅' and '丄'.
+    """
+
+    def __init__(self):
+        self._wrong_stop_count = 0  # type: int
+        self._cjk_character_count = 0  # type: int
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character in ["丅", "丄"]:
+            self._wrong_stop_count += 1
+            return
+        if is_cjk(character):
+            self._cjk_character_count += 1
+
+    def reset(self) -> None:
+        self._wrong_stop_count = 0
+        self._cjk_character_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._cjk_character_count < 16:
+            return 0.
+        return self._wrong_stop_count / self._cjk_character_count
+
+
+class ArchaicUpperLowerPlugin(MessDetectorPlugin):
+
+    def __init__(self):
+        self._buf = False  # type: bool
+
+        self._character_count_since_last_sep = 0  # type: int
+
+        self._successive_upper_lower_count = 0  # type: int
+        self._successive_upper_lower_count_final = 0  # type: int
+
+        self._character_count = 0  # type: int
+
+        self._last_alpha_seen = None  # type: Optional[str]
+        self._current_ascii_only = True  # type: bool
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        is_concerned = character.isalpha() and is_case_variable(character)
+        chunk_sep = is_concerned is False
+
+        if chunk_sep and self._character_count_since_last_sep > 0:
+            if self._character_count_since_last_sep <= 64 and character.isdigit() is False and self._current_ascii_only is False:
+                self._successive_upper_lower_count_final += self._successive_upper_lower_count
+
+            self._successive_upper_lower_count = 0
+            self._character_count_since_last_sep = 0
+            self._last_alpha_seen = None
+            self._buf = False
+            self._character_count += 1
+            self._current_ascii_only = True
+
+            return
+
+        if self._current_ascii_only is True and is_ascii(character) is False:
+            self._current_ascii_only = False
+
+        if self._last_alpha_seen is not None:
+            if (character.isupper() and self._last_alpha_seen.islower()) or (character.islower() and self._last_alpha_seen.isupper()):
+                if self._buf is True:
+                    self._successive_upper_lower_count += 2
+                    self._buf = False
+                else:
+                    self._buf = True
+            else:
+                self._buf = False
+
+        self._character_count += 1
+        self._character_count_since_last_sep += 1
+        self._last_alpha_seen = character
+
+    def reset(self) -> None:
+        self._character_count = 0
+        self._character_count_since_last_sep = 0
+        self._successive_upper_lower_count = 0
+        self._successive_upper_lower_count_final = 0
+        self._last_alpha_seen = None
+        self._buf = False
+        self._current_ascii_only = True
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.
+
+        return self._successive_upper_lower_count_final / self._character_count
+
+
+def is_suspiciously_successive_range(unicode_range_a: Optional[str], unicode_range_b: Optional[str]) -> bool:
+    """
+    Determine if two Unicode range seen next to each other can be considered as suspicious.
+    """
+    if unicode_range_a is None or unicode_range_b is None:
+        return True
+
+    if unicode_range_a == unicode_range_b:
+        return False
+
+    if "Latin" in unicode_range_a and "Latin" in unicode_range_b:
+        return False
+
+    if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b:
+        return False
+
+    keywords_range_a, keywords_range_b = unicode_range_a.split(" "), unicode_range_b.split(" ")
+
+    for el in keywords_range_a:
+        if el in UNICODE_SECONDARY_RANGE_KEYWORD:
+            continue
+        if el in keywords_range_b:
+            return False
+
+    # Japanese Exception
+    if unicode_range_a in ['Katakana', 'Hiragana'] and unicode_range_b in ['Katakana', 'Hiragana']:
+        return False
+
+    if unicode_range_a in ['Katakana', 'Hiragana'] or unicode_range_b in ['Katakana', 'Hiragana']:
+        if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
+            return False
+
+    if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b:
+        if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
+            return False
+        if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
+            return False
+
+    # Chinese/Japanese use dedicated range for punctuation and/or separators.
+    if ('CJK' in unicode_range_a or 'CJK' in unicode_range_b) or (unicode_range_a in ['Katakana', 'Hiragana'] and unicode_range_b in ['Katakana', 'Hiragana']):
+        if 'Punctuation' in unicode_range_a or 'Punctuation' in unicode_range_b:
+            return False
+        if 'Forms' in unicode_range_a or 'Forms' in unicode_range_b:
+            return False
+
+    return True
+
+
+@lru_cache(maxsize=2048)
+def mess_ratio(decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False) -> float:
+    """
+    Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier.
+    """
+    detectors = []  # type: List[MessDetectorPlugin]
+
+    for md_class in MessDetectorPlugin.__subclasses__():
+        detectors.append(
+            md_class()
+        )
+
+    length = len(decoded_sequence)  # type: int
+
+    mean_mess_ratio = 0.  # type: float
+
+    if length < 512:
+        intermediary_mean_mess_ratio_calc = 32  # type: int
+    elif length <= 1024:
+        intermediary_mean_mess_ratio_calc = 64
+    else:
+        intermediary_mean_mess_ratio_calc = 128
+
+    for character, index in zip(decoded_sequence, range(0, length)):
+        for detector in detectors:
+            if detector.eligible(character):
+                detector.feed(character)
+
+        if (index > 0 and index % intermediary_mean_mess_ratio_calc == 0) or index == length-1:
+            mean_mess_ratio = sum(
+                [
+                    dt.ratio for dt in detectors
+                ]
+            )
+
+            if mean_mess_ratio >= maximum_threshold:
+                break
+
+    if debug:
+        for dt in detectors:  # pragma: nocover
+            print(
+                dt.__class__,
+                dt.ratio
+            )
+
+    return round(
+        mean_mess_ratio,
+        3
+    )
+

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/models.py

@@ -0,0 +1,357 @@
+import warnings
+from encodings.aliases import aliases
+from hashlib import sha256
+from json import dumps
+from typing import Optional, List, Tuple, Set
+from collections import Counter
+from re import sub, compile as re_compile
+
+from charset_normalizer.constant import TOO_BIG_SEQUENCE
+from charset_normalizer.md import mess_ratio
+from charset_normalizer.utils import iana_name, is_multi_byte_encoding, unicode_range
+
+
+class CharsetMatch:
+    def __init__(
+            self,
+            payload: bytes,
+            guessed_encoding: str,
+            mean_mess_ratio: float,
+            has_sig_or_bom: bool,
+            languages: "CoherenceMatches",
+            decoded_payload: Optional[str] = None
+    ):
+        self._payload = payload  # type: bytes
+
+        self._encoding = guessed_encoding  # type: str
+        self._mean_mess_ratio = mean_mess_ratio  # type: float
+        self._languages = languages  # type: CoherenceMatches
+        self._has_sig_or_bom = has_sig_or_bom  # type: bool
+        self._unicode_ranges = None  # type: Optional[List[str]]
+
+        self._leaves = []  # type: List[CharsetMatch]
+        self._mean_coherence_ratio = 0.  # type: float
+
+        self._output_payload = None  # type: Optional[bytes]
+        self._output_encoding = None  # type: Optional[str]
+
+        self._string = decoded_payload  # type: Optional[str]
+
+    def __eq__(self, other) -> bool:
+        if not isinstance(other, CharsetMatch):
+            raise TypeError('__eq__ cannot be invoked on {} and {}.'.format(str(other.__class__), str(self.__class__)))
+        return self.encoding == other.encoding and self.fingerprint == other.fingerprint
+
+    def __lt__(self, other) -> bool:
+        """
+        Implemented to make sorted available upon CharsetMatches items.
+        """
+        if not isinstance(other, CharsetMatch):
+            raise ValueError
+
+        chaos_difference = abs(self.chaos - other.chaos)  # type: float
+
+        # Bellow 1% difference --> Use Coherence
+        if chaos_difference < 0.01:
+            return self.coherence > other.coherence
+
+        return self.chaos < other.chaos
+
+    @property
+    def chaos_secondary_pass(self) -> float:
+        """
+        Check once again chaos in decoded text, except this time, with full content.
+        Use with caution, this can be very slow.
+        Notice: Will be removed in 3.0
+        """
+        warnings.warn("chaos_secondary_pass is deprecated and will be removed in 3.0", DeprecationWarning)
+        return mess_ratio(
+            str(self),
+            1.
+        )
+
+    @property
+    def coherence_non_latin(self) -> float:
+        """
+        Coherence ratio on the first non-latin language detected if ANY.
+        Notice: Will be removed in 3.0
+        """
+        warnings.warn("coherence_non_latin is deprecated and will be removed in 3.0", DeprecationWarning)
+        return 0.
+
+    @property
+    def w_counter(self) -> Counter:
+        """
+        Word counter instance on decoded text.
+        Notice: Will be removed in 3.0
+        """
+        warnings.warn("w_counter is deprecated and will be removed in 3.0", DeprecationWarning)
+        not_printable_pattern = re_compile(r'[0-9\W\n\r\t]+')
+        string_printable_only = sub(not_printable_pattern, ' ', str(self).lower())
+
+        return Counter(string_printable_only.split())
+
+    def __str__(self) -> str:
+        # Lazy Str Loading
+        if self._string is None:
+            self._string = str(self._payload, self._encoding, "strict")
+        return self._string
+
+    def __repr__(self) -> str:
+        return "<CharsetMatch '{}' bytes({})>".format(self.encoding, self.fingerprint)
+
+    def add_submatch(self, other: "CharsetMatch") -> None:
+        if not isinstance(other, CharsetMatch) or other == self:
+            raise ValueError("Unable to add instance <{}> as a submatch of a CharsetMatch".format(other.__class__))
+
+        other._string = None  # Unload RAM usage; dirty trick.
+        self._leaves.append(other)
+
+    @property
+    def encoding(self) -> str:
+        return self._encoding
+
+    @property
+    def encoding_aliases(self) -> List[str]:
+        """
+        Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
+        """
+        also_known_as = []  # type: List[str]
+        for u, p in aliases.items():
+            if self.encoding == u:
+                also_known_as.append(p)
+            elif self.encoding == p:
+                also_known_as.append(u)
+        return also_known_as
+
+    @property
+    def bom(self) -> bool:
+        return self._has_sig_or_bom
+
+    @property
+    def byte_order_mark(self) -> bool:
+        return self._has_sig_or_bom
+
+    @property
+    def languages(self) -> List[str]:
+        """
+        Return the complete list of possible languages found in decoded sequence.
+        Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
+        """
+        return [e[0] for e in self._languages]
+
+    @property
+    def language(self) -> str:
+        """
+        Most probable language found in decoded sequence. If none were detected or inferred, the property will return
+        "Unknown".
+        """
+        if not self._languages:
+            # Trying to infer the language based on the given encoding
+            # Its either English or we should not pronounce ourselves in certain cases.
+            if "ascii" in self.could_be_from_charset:
+                return "English"
+
+            # doing it there to avoid circular import
+            from charset_normalizer.cd import mb_encoding_languages, encoding_languages
+
+            languages = mb_encoding_languages(self.encoding) if is_multi_byte_encoding(self.encoding) else encoding_languages(self.encoding)
+
+            if len(languages) == 0 or "Latin Based" in languages:
+                return "Unknown"
+
+            return languages[0]
+
+        return self._languages[0][0]
+
+    @property
+    def chaos(self) -> float:
+        return self._mean_mess_ratio
+
+    @property
+    def coherence(self) -> float:
+        if not self._languages:
+            return 0.
+        return self._languages[0][1]
+
+    @property
+    def percent_chaos(self) -> float:
+        return round(self.chaos * 100, ndigits=3)
+
+    @property
+    def percent_coherence(self) -> float:
+        return round(self.coherence * 100, ndigits=3)
+
+    @property
+    def raw(self) -> bytes:
+        """
+        Original untouched bytes.
+        """
+        return self._payload
+
+    @property
+    def submatch(self) -> List["CharsetMatch"]:
+        return self._leaves
+
+    @property
+    def has_submatch(self) -> bool:
+        return len(self._leaves) > 0
+
+    @property
+    def alphabets(self) -> List[str]:
+        if self._unicode_ranges is not None:
+            return self._unicode_ranges
+        detected_ranges = set()  # type: Set[str]
+        for character in str(self):
+            detected_range = unicode_range(character)  # type: Optional[str]
+            if detected_range:
+                detected_ranges.add(
+                    unicode_range(character)
+                )
+        self._unicode_ranges = sorted(list(detected_ranges))
+        return self._unicode_ranges
+
+    @property
+    def could_be_from_charset(self) -> List[str]:
+        """
+        The complete list of encoding that output the exact SAME str result and therefore could be the originating
+        encoding.
+        This list does include the encoding available in property 'encoding'.
+        """
+        return [self._encoding] + [m.encoding for m in self._leaves]
+
+    def first(self) -> "CharsetMatch":
+        """
+        Kept for BC reasons. Will be removed in 3.0.
+        """
+        return self
+
+    def best(self) -> "CharsetMatch":
+        """
+        Kept for BC reasons. Will be removed in 3.0.
+        """
+        return self
+
+    def output(self, encoding: str = "utf_8") -> bytes:
+        """
+        Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
+        Any errors will be simply ignored by the encoder NOT replaced.
+        """
+        if self._output_encoding is None or self._output_encoding != encoding:
+            self._output_encoding = encoding
+            self._output_payload = str(self).encode(encoding, "replace")
+
+        return self._output_payload  # type: ignore
+
+    @property
+    def fingerprint(self) -> str:
+        """
+        Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
+        """
+        return sha256(self.output()).hexdigest()
+
+
+class CharsetMatches:
+    """
+    Container with every CharsetMatch items ordered by default from most probable to the less one.
+    Act like a list(iterable) but does not implements all related methods.
+    """
+    def __init__(self, results: List[CharsetMatch] = None):
+        self._results = sorted(results) if results else []  # type: List[CharsetMatch]
+
+    def __iter__(self):
+        for result in self._results:
+            yield result
+
+    def __getitem__(self, item) -> CharsetMatch:
+        """
+        Retrieve a single item either by its position or encoding name (alias may be used here).
+        Raise KeyError upon invalid index or encoding not present in results.
+        """
+        if isinstance(item, int):
+            return self._results[item]
+        if isinstance(item, str):
+            item = iana_name(item, False)
+            for result in self._results:
+                if item in result.could_be_from_charset:
+                    return result
+        raise KeyError
+
+    def __len__(self) -> int:
+        return len(self._results)
+
+    def append(self, item: CharsetMatch) -> None:
+        """
+        Insert a single match. Will be inserted accordingly to preserve sort.
+        Can be inserted as a submatch.
+        """
+        if not isinstance(item, CharsetMatch):
+            raise ValueError("Cannot append instance '{}' to CharsetMatches".format(str(item.__class__)))
+        # We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
+        if len(item.raw) <= TOO_BIG_SEQUENCE:
+            for match in self._results:
+                if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
+                    match.add_submatch(item)
+                    return
+        self._results.append(item)
+        self._results = sorted(self._results)
+
+    def best(self) -> Optional["CharsetMatch"]:
+        """
+        Simply return the first match. Strict equivalent to matches[0].
+        """
+        if not self._results:
+            return None
+        return self._results[0]
+
+    def first(self) -> Optional["CharsetMatch"]:
+        """
+        Redundant method, call the method best(). Kept for BC reasons.
+        """
+        return self.best()
+
+
+CoherenceMatch = Tuple[str, float]
+CoherenceMatches = List[CoherenceMatch]
+
+
+class CliDetectionResult:
+
+    def __init__(self, path: str, encoding: str, encoding_aliases: List[str], alternative_encodings: List[str], language: str, alphabets: List[str], has_sig_or_bom: bool, chaos: float, coherence: float, unicode_path: Optional[str], is_preferred: bool):
+        self.path = path  # type: str
+        self.unicode_path = unicode_path  # type: Optional[str]
+        self.encoding = encoding  # type: str
+        self.encoding_aliases = encoding_aliases  # type: List[str]
+        self.alternative_encodings = alternative_encodings  # type: List[str]
+        self.language = language  # type: str
+        self.alphabets = alphabets  # type: List[str]
+        self.has_sig_or_bom = has_sig_or_bom  # type: bool
+        self.chaos = chaos  # type: float
+        self.coherence = coherence  # type: float
+        self.is_preferred = is_preferred  # type: bool
+
+    @property
+    def __dict__(self):
+        return {
+            'path': self.path,
+            'encoding': self.encoding,
+            'encoding_aliases': self.encoding_aliases,
+            'alternative_encodings': self.alternative_encodings,
+            'language': self.language,
+            'alphabets': self.alphabets,
+            'has_sig_or_bom': self.has_sig_or_bom,
+            'chaos': self.chaos,
+            'coherence': self.coherence,
+            'unicode_path': self.unicode_path,
+            'is_preferred': self.is_preferred
+        }
+
+    def to_json(self) -> str:
+        return dumps(
+            self.__dict__,
+            ensure_ascii=True,
+            indent=4
+        )
+
+
+CharsetNormalizerMatch = CharsetMatch

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/utils.py

@@ -0,0 +1,301 @@
+try:
+    import unicodedata2 as unicodedata
+except ImportError:
+    import unicodedata
+
+from codecs import IncrementalDecoder
+from re import findall
+from typing import Optional, Tuple, Union, List, Set
+import importlib
+from _multibytecodec import MultibyteIncrementalDecoder  # type: ignore
+
+from encodings.aliases import aliases
+from functools import lru_cache
+
+from charset_normalizer.constant import UNICODE_RANGES_COMBINED, UNICODE_SECONDARY_RANGE_KEYWORD, \
+    RE_POSSIBLE_ENCODING_INDICATION, ENCODING_MARKS, UTF8_MAXIMAL_ALLOCATION, IANA_SUPPORTED_SIMILAR
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_accentuated(character: str) -> bool:
+    try:
+        description = unicodedata.name(character)  # type: str
+    except ValueError:
+        return False
+    return "WITH GRAVE" in description or "WITH ACUTE" in description or "WITH CEDILLA" in description or "WITH DIAERESIS" in description or "WITH CIRCUMFLEX" in description
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def remove_accent(character: str) -> str:
+    decomposed = unicodedata.decomposition(character)  # type: str
+    if not decomposed:
+        return character
+
+    codes = decomposed.split(" ")  # type: List[str]
+
+    return chr(
+        int(
+            codes[0],
+            16
+        )
+    )
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def unicode_range(character: str) -> Optional[str]:
+    """
+    Retrieve the Unicode range official name from a single character.
+    """
+    character_ord = ord(character)  # type: int
+
+    for range_name, ord_range in UNICODE_RANGES_COMBINED.items():
+        if character_ord in ord_range:
+            return range_name
+
+    return None
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_latin(character: str) -> bool:
+    try:
+        description = unicodedata.name(character)  # type: str
+    except ValueError:
+        return False
+    return "LATIN" in description
+
+
+def is_ascii(character: str) -> bool:
+    try:
+        character.encode("ascii")
+    except UnicodeEncodeError:
+        return False
+    return True
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_punctuation(character: str) -> bool:
+    character_category = unicodedata.category(character)  # type: str
+
+    if "P" in character_category:
+        return True
+
+    character_range = unicode_range(character)  # type: Optional[str]
+
+    if character_range is None:
+        return False
+
+    return "Punctuation" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_symbol(character: str) -> bool:
+    character_category = unicodedata.category(character)  # type: str
+
+    if "S" in character_category or "N" in character_category:
+        return True
+
+    character_range = unicode_range(character)  # type: Optional[str]
+
+    if character_range is None:
+        return False
+
+    return "Forms" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_separator(character: str) -> bool:
+    if character.isspace() or character in ["｜", "+", ",", ";", "<", ">"]:
+        return True
+
+    character_category = unicodedata.category(character)  # type: str
+
+    return "Z" in character_category
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_case_variable(character: str) -> bool:
+    return character.islower() != character.isupper()
+
+
+def is_private_use_only(character: str) -> bool:
+    character_category = unicodedata.category(character)  # type: str
+
+    return "Co" == character_category
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_cjk(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "CJK" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_hiragana(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "HIRAGANA" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_katakana(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "KATAKANA" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_hangul(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "HANGUL" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_thai(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "THAI" in character_name
+
+
+@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
+def is_unicode_range_secondary(range_name: str) -> bool:
+    for keyword in UNICODE_SECONDARY_RANGE_KEYWORD:
+        if keyword in range_name:
+            return True
+
+    return False
+
+
+def any_specified_encoding(sequence: bytes, search_zone: int = 4096) -> Optional[str]:
+    """
+    Extract using ASCII-only decoder any specified encoding in the first n-bytes.
+    """
+    if not isinstance(sequence, bytes):
+        raise TypeError
+
+    seq_len = len(sequence)  # type: int
+
+    results = findall(
+        RE_POSSIBLE_ENCODING_INDICATION,
+        sequence[:seq_len if seq_len <= search_zone else search_zone].decode('ascii', errors='ignore')
+    )  # type: List[str]
+
+    if len(results) == 0:
+        return None
+
+    for specified_encoding in results:
+        specified_encoding = specified_encoding.lower().replace('-', '_')
+
+        for encoding_alias, encoding_iana in aliases.items():
+            if encoding_alias == specified_encoding:
+                return encoding_iana
+            if encoding_iana == specified_encoding:
+                return encoding_iana
+
+    return None
+
+
+@lru_cache(maxsize=128)
+def is_multi_byte_encoding(name: str) -> bool:
+    """
+    Verify is a specific encoding is a multi byte one based on it IANA name
+    """
+    return name in {"utf_8", "utf_8_sig", "utf_16", "utf_16_be", "utf_16_le", "utf_32", "utf_32_le", "utf_32_be", "utf_7"} or issubclass(
+        importlib.import_module('encodings.{}'.format(name)).IncrementalDecoder,  # type: ignore
+        MultibyteIncrementalDecoder
+    )
+
+
+def identify_sig_or_bom(sequence: bytes) -> Tuple[Optional[str], bytes]:
+    """
+    Identify and extract SIG/BOM in given sequence.
+    """
+
+    for iana_encoding in ENCODING_MARKS:
+        marks = ENCODING_MARKS[iana_encoding]  # type: Union[bytes, List[bytes]]
+
+        if isinstance(marks, bytes):
+            marks = [marks]
+
+        for mark in marks:
+            if sequence.startswith(mark):
+                return iana_encoding, mark
+
+    return None, b""
+
+
+def should_strip_sig_or_bom(iana_encoding: str) -> bool:
+    return iana_encoding not in {"utf_16", "utf_32"}
+
+
+def iana_name(cp_name: str, strict: bool = True) -> str:
+    cp_name = cp_name.lower().replace('-', '_')
+
+    for encoding_alias, encoding_iana in aliases.items():
+        if cp_name == encoding_alias or cp_name == encoding_iana:
+            return encoding_iana
+
+    if strict:
+        raise ValueError("Unable to retrieve IANA for '{}'".format(cp_name))
+
+    return cp_name
+
+
+def range_scan(decoded_sequence: str) -> List[str]:
+    ranges = set()  # type: Set[str]
+
+    for character in decoded_sequence:
+        character_range = unicode_range(character)  # type: Optional[str]
+
+        if character_range is None:
+            continue
+
+        ranges.add(
+            character_range
+        )
+
+    return list(ranges)
+
+
+def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
+
+    if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
+        return 0.
+
+    decoder_a = importlib.import_module('encodings.{}'.format(iana_name_a)).IncrementalDecoder  # type: ignore
+    decoder_b = importlib.import_module('encodings.{}'.format(iana_name_b)).IncrementalDecoder  # type: ignore
+
+    id_a = decoder_a(errors="ignore")  # type: IncrementalDecoder
+    id_b = decoder_b(errors="ignore")  # type: IncrementalDecoder
+
+    character_match_count = 0  # type: int
+
+    for i in range(0, 255):
+        to_be_decoded = bytes([i])  # type: bytes
+        if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
+            character_match_count += 1
+
+    return character_match_count / 254
+
+
+def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
+    """
+    Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
+    the function cp_similarity.
+    """
+    return iana_name_a in IANA_SUPPORTED_SIMILAR and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]

IKEA_scrapper/.venv/Lib/site-packages/charset_normalizer/version.py

@@ -0,0 +1,6 @@
+"""
+Expose version
+"""
+
+__version__ = "2.0.4"
+VERSION = __version__.split('.')

IKEA_scrapper/.venv/Lib/site-packages/distutils-precedence.pth

@@ -0,0 +1 @@
+import os; var = 'SETUPTOOLS_USE_DISTUTILS'; enabled = os.environ.get(var, 'stdlib') == 'local'; enabled and __import__('_distutils_hack').add_shim(); 

IKEA_scrapper/.venv/Lib/site-packages/idna-3.2.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

IKEA_scrapper/.venv/Lib/site-packages/idna-3.2.dist-info/LICENSE.md

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2013-2021, Kim Davies
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

IKEA_scrapper/.venv/Lib/site-packages/idna-3.2.dist-info/METADATA

@@ -0,0 +1,225 @@
+Metadata-Version: 2.1
+Name: idna
+Version: 3.2
+Summary: Internationalized Domain Names in Applications (IDNA)
+Home-page: https://github.com/kjd/idna
+Author: Kim Davies
+Author-email: kim@cynosure.com.au
+License: BSD-3-Clause
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Internet :: Name Service (DNS)
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Utilities
+Requires-Python: >=3.5
+
+Internationalized Domain Names in Applications (IDNA)
+=====================================================
+
+Support for the Internationalised Domain Names in Applications
+(IDNA) protocol as specified in `RFC 5891 <https://tools.ietf.org/html/rfc5891>`_.
+This is the latest version of the protocol and is sometimes referred to as
+“IDNA 2008”.
+
+This library also provides support for Unicode Technical Standard 46,
+`Unicode IDNA Compatibility Processing <https://unicode.org/reports/tr46/>`_.
+
+This acts as a suitable replacement for the “encodings.idna” module that
+comes with the Python standard library, but which only supports the
+old, deprecated IDNA specification (`RFC 3490 <https://tools.ietf.org/html/rfc3490>`_).
+
+Basic functions are simply executed:
+
+.. code-block:: pycon
+
+    >>> import idna
+    >>> idna.encode('ドメイン.テスト')
+    b'xn--eckwd4c7c.xn--zckzah'
+    >>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
+    ドメイン.テスト
+
+Packages
+--------
+
+The latest tagged release version is published in the PyPI repository:
+
+.. image:: https://badge.fury.io/py/idna.svg
+   :target: https://badge.fury.io/py/idna
+
+
+Installation
+------------
+
+To install this library, you can use pip:
+
+.. code-block:: bash
+
+    $ pip install idna
+
+Alternatively, you can install the package using the bundled setup script:
+
+.. code-block:: bash
+
+    $ python setup.py install
+
+This library works with Python 3.4 or later. Earlier versions of this
+library support Python 2 - use "idna<3" in your requirements file if
+you need this library for a Python 2 application.
+
+
+Usage
+-----
+
+For typical usage, the ``encode`` and ``decode`` functions will take a domain
+name argument and perform a conversion to A-labels or U-labels respectively.
+
+.. code-block:: pycon
+
+    >>> import idna
+    >>> idna.encode('ドメイン.テスト')
+    b'xn--eckwd4c7c.xn--zckzah'
+    >>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
+    ドメイン.テスト
+
+You may use the codec encoding and decoding methods using the
+``idna.codec`` module:
+
+.. code-block:: pycon
+
+    >>> import idna.codec
+    >>> print('домена.испытание'.encode('idna'))
+    b'xn--80ahd1agd.xn--80akhbyknj4f'
+    >>> print(b'xn--80ahd1agd.xn--80akhbyknj4f'.decode('idna'))
+    домена.испытание
+
+Conversions can be applied at a per-label basis using the ``ulabel`` or ``alabel``
+functions if necessary:
+
+.. code-block:: pycon
+
+    >>> idna.alabel('测试')
+    b'xn--0zwm56d'
+
+Compatibility Mapping (UTS #46)
++++++++++++++++++++++++++++++++
+
+As described in `RFC 5895 <https://tools.ietf.org/html/rfc5895>`_, the IDNA
+specification does not normalize input from different potential ways a user
+may input a domain name. This functionality, known as a “mapping”, is 
+considered by the specification to be a local user-interface issue distinct
+from IDNA conversion functionality.
+
+This library provides one such mapping, that was developed by the Unicode
+Consortium. Known as `Unicode IDNA Compatibility Processing <https://unicode.org/reports/tr46/>`_,
+it provides for both a regular mapping for typical applications, as well as
+a transitional mapping to help migrate from older IDNA 2003 applications.
+
+For example, “Königsgäßchen” is not a permissible label as *LATIN CAPITAL
+LETTER K* is not allowed (nor are capital letters in general). UTS 46 will
+convert this into lower case prior to applying the IDNA conversion.
+
+.. code-block:: pycon
+
+    >>> import idna
+    >>> idna.encode('Königsgäßchen')
+    ...
+    idna.core.InvalidCodepoint: Codepoint U+004B at position 1 of 'Königsgäßchen' not allowed
+    >>> idna.encode('Königsgäßchen', uts46=True)
+    b'xn--knigsgchen-b4a3dun'
+    >>> print(idna.decode('xn--knigsgchen-b4a3dun'))
+    königsgäßchen
+
+Transitional processing provides conversions to help transition from the older
+2003 standard to the current standard. For example, in the original IDNA
+specification, the *LATIN SMALL LETTER SHARP S* (ß) was converted into two
+*LATIN SMALL LETTER S* (ss), whereas in the current IDNA specification this
+conversion is not performed.
+
+.. code-block:: pycon
+
+    >>> idna.encode('Königsgäßchen', uts46=True, transitional=True)
+    'xn--knigsgsschen-lcb0w'
+
+Implementors should use transitional processing with caution, only in rare
+cases where conversion from legacy labels to current labels must be performed
+(i.e. IDNA implementations that pre-date 2008). For typical applications
+that just need to convert labels, transitional processing is unlikely to be
+beneficial and could produce unexpected incompatible results.
+
+``encodings.idna`` Compatibility
+++++++++++++++++++++++++++++++++
+
+Function calls from the Python built-in ``encodings.idna`` module are
+mapped to their IDNA 2008 equivalents using the ``idna.compat`` module.
+Simply substitute the ``import`` clause in your code to refer to the
+new module name.
+
+Exceptions
+----------
+
+All errors raised during the conversion following the specification should
+raise an exception derived from the ``idna.IDNAError`` base class.
+
+More specific exceptions that may be generated as ``idna.IDNABidiError``
+when the error reflects an illegal combination of left-to-right and
+right-to-left characters in a label; ``idna.InvalidCodepoint`` when
+a specific codepoint is an illegal character in an IDN label (i.e.
+INVALID); and ``idna.InvalidCodepointContext`` when the codepoint is
+illegal based on its positional context (i.e. it is CONTEXTO or CONTEXTJ
+but the contextual requirements are not satisfied.)
+
+Building and Diagnostics
+------------------------
+
+The IDNA and UTS 46 functionality relies upon pre-calculated lookup
+tables for performance. These tables are derived from computing against
+eligibility criteria in the respective standards. These tables are
+computed using the command-line script ``tools/idna-data``.
+
+This tool will fetch relevant codepoint data from the Unicode repository 
+and perform the required calculations to identify eligibility. There are 
+three main modes:
+
+* ``idna-data make-libdata``. Generates ``idnadata.py`` and ``uts46data.py``,
+  the pre-calculated lookup tables using for IDNA and UTS 46 conversions. Implementors
+  who wish to track this library against a different Unicode version may use this tool
+  to manually generate a different version of the ``idnadata.py`` and ``uts46data.py``
+  files.
+
+* ``idna-data make-table``. Generate a table of the IDNA disposition
+  (e.g. PVALID, CONTEXTJ, CONTEXTO) in the format found in Appendix B.1 of RFC
+  5892 and the pre-computed tables published by `IANA <https://www.iana.org/>`_.
+
+* ``idna-data U+0061``. Prints debugging output on the various properties
+  associated with an individual Unicode codepoint (in this case, U+0061), that are
+  used to assess the IDNA and UTS 46 status of a codepoint. This is helpful in debugging
+  or analysis.
+
+The tool accepts a number of arguments, described using ``idna-data -h``. Most notably,
+the ``--version`` argument allows the specification of the version of Unicode to use
+in computing the table data. For example, ``idna-data --version 9.0.0 make-libdata``
+will generate library data against Unicode 9.0.0.
+
+
+Testing
+-------
+
+The library has a test suite based on each rule of the IDNA specification, as
+well as tests that are provided as part of the Unicode Technical Standard 46,
+`Unicode IDNA Compatibility Processing <https://unicode.org/reports/tr46/>`_.
+
+

IKEA_scrapper/.venv/Lib/site-packages/idna-3.2.dist-info/RECORD

@@ -0,0 +1,23 @@
+idna-3.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+idna-3.2.dist-info/LICENSE.md,sha256=otbk2UC9JNvnuWRc3hmpeSzFHbeuDVrNMBrIYMqj6DY,1523
+idna-3.2.dist-info/METADATA,sha256=L6eIrqdmpRK2oKwBFd8CcID4FQ8h2SYKf2fg7KEQLG0,8638
+idna-3.2.dist-info/RECORD,,
+idna-3.2.dist-info/WHEEL,sha256=OqRkF0eY5GHssMorFjlbTIq072vpHpF60fIQA6lS9xA,92
+idna-3.2.dist-info/top_level.txt,sha256=jSag9sEDqvSPftxOQy-ABfGV_RSy7oFh4zZJpODV8k0,5
+idna/__init__.py,sha256=KJQN1eQBr8iIK5SKrJ47lXvxG0BJ7Lm38W4zT0v_8lk,849
+idna/__pycache__/__init__.cpython-39.pyc,,
+idna/__pycache__/codec.cpython-39.pyc,,
+idna/__pycache__/compat.cpython-39.pyc,,
+idna/__pycache__/core.cpython-39.pyc,,
+idna/__pycache__/idnadata.cpython-39.pyc,,
+idna/__pycache__/intranges.cpython-39.pyc,,
+idna/__pycache__/package_data.cpython-39.pyc,,
+idna/__pycache__/uts46data.cpython-39.pyc,,
+idna/codec.py,sha256=QsPFD3Je8gN17rfs14e7zTGRWlnL7bNf2ZqcHTRVYHs,3453
+idna/compat.py,sha256=5A9xR04puRHCsyjBNewZlVSiarth7K1bZqyEOeob1fA,360
+idna/core.py,sha256=icq2P13S6JMjoXgKhhd6ihhby7QsnZlNfniH6fLyf6U,12826
+idna/idnadata.py,sha256=cl4x9RLdw1ZMtEEbvKwAsX-Id3AdIjO5U3HaoKM6VGs,42350
+idna/intranges.py,sha256=EqgXwyATAn-CTACInqH9tYsYAitGB2VcQ50RZt_Cpjs,1933
+idna/package_data.py,sha256=_028B4fvadRIaXMwMYjhuQPP3AxTIt1IRE7X6RDR4Mk,21
+idna/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+idna/uts46data.py,sha256=DGzwDQv8JijY17I_7ondo3stjFjNnjvVAbA-z0k1XOE,201849

IKEA_scrapper/.venv/Lib/site-packages/idna-3.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.36.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

IKEA_scrapper/.venv/Lib/site-packages/idna-3.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+idna

IKEA_scrapper/.venv/Lib/site-packages/idna/__init__.py

@@ -0,0 +1,44 @@
+from .package_data import __version__
+from .core import (
+    IDNABidiError,
+    IDNAError,
+    InvalidCodepoint,
+    InvalidCodepointContext,
+    alabel,
+    check_bidi,
+    check_hyphen_ok,
+    check_initial_combiner,
+    check_label,
+    check_nfc,
+    decode,
+    encode,
+    ulabel,
+    uts46_remap,
+    valid_contextj,
+    valid_contexto,
+    valid_label_length,
+    valid_string_length,
+)
+from .intranges import intranges_contain
+
+__all__ = [
+    "IDNABidiError",
+    "IDNAError",
+    "InvalidCodepoint",
+    "InvalidCodepointContext",
+    "alabel",
+    "check_bidi",
+    "check_hyphen_ok",
+    "check_initial_combiner",
+    "check_label",
+    "check_nfc",
+    "decode",
+    "encode",
+    "intranges_contain",
+    "ulabel",
+    "uts46_remap",
+    "valid_contextj",
+    "valid_contexto",
+    "valid_label_length",
+    "valid_string_length",
+]