Selenium scraper - done

.gitignore

@@ -1,4 +1,6 @@
 .vscode/
 **/__pycache__/
 **/.venv/
-**.log
+**.log
+/december/task_081221/files
+/december/task_081221/*.log

december/task_011221/task_011221_ss_scraper.py

@@ -10,7 +10,7 @@ from io import BytesIO
 from openpyxl.styles import Font, Alignment
 import openpyxl
 
-HEADERS = {"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36 Vivaldi/4.1.2369.21'}
+HEADERS = {"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.97 Safari/537.36 Vivaldi/4.1.2369.21'}
 
 
 class SS:

december/task_081221/task_081221_homework.py

@@ -1,67 +1,118 @@
-# Date - 11.12.2021
+# Date - 14.12.2021
 # Author - Kristiāns Francis Cagulis
 # Title - Homework Selenium
 
-import time
-
+import os
+from os.path import exists
+import requests
+from bs4 import BeautifulSoup
 from selenium import webdriver
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.common.by import By
 
+debug = False
+
 chromium = ["1", "chromium", "chrome"]
 firefox = ["2", "firefox"]
 
 
+def get_data():
+	user_browser, user_pages, search_word = get_user_input()
+
+	for page in user_pages:
+		if user_browser in chromium:
+			if os.name in ('nt', 'dos'):
+				browser = webdriver.Chrome("chromedriver.exe")  # windows
+			else:
+				browser = webdriver.Chrome("chromedriver")  # gnu/linux
+		elif user_browser in firefox:
+			browser = webdriver.Firefox()
+
+		url = f"https://www.riga.lv/lv/search?q={search_word}&types=file&page={page - 1}"
+		browser.get(url)
+		browser.find_element(By.CLASS_NAME, 'cookie-accept-all').click()
+
+		files = browser.find_elements(By.CLASS_NAME, 'file')
+		for file in files:
+			file_name = file.text
+			file_url = file.get_attribute('href')
+			file_download(file_name, file_url)
+		browser.quit()
+
+
 def get_user_input():
-	print("Choose which browser to use:")
+	if debug == True:
+		search_word = "dokum"
+	else:
+		search_word = input("Choose keyword to search: ")
+
+	last_page = get_max_page_amount(search_word)
+	print("\nChoose which browser to use:")
 	print("1 - chromium (chrome)")
 	print("2 - firefox")
-	browser = input("").lower()
 
-	print("Choose from which pages you want to download files (1 4 7; 2-5; all)")
-	pages = input("").lower()
-	return browser, pages
+	if debug == True:
+		browser = "firefox"
+	else:
+		browser = input("").lower()
+
+	print(f"\nChoose from which pages you want to download files (1 4 7; 2-5; all). Maximum is {last_page} pages.")
+	try:
+		if debug == True:
+			user_input = "1"
+		else:
+			user_input = input("").lower()
+
+		if user_input == "all":
+			pages = list(map(int, range(1, last_page + 1)))  # creates list with all pages
+		else:
+			user_page_list = user_input.split(" ")
+			for page_range in user_page_list:
+				if "-" in page_range:
+
+					first_num = int(page_range[:page_range.find("-")])  # gets first number
+					second_num = int(page_range[page_range.find("-") + 1:]) + 1  # gets second number
+
+					if second_num > last_page:  # reduces user input to max page amount
+						second_num = last_page
+
+					user_page_list = user_page_list + list(map(str, range(first_num, second_num)))  # creates list with str range
+			pages = [elem for elem in user_page_list if not "-" in elem]  # removes all elements containing "-"
+			pages = list(map(int, pages))  # convers str to int
+			pages.sort()  # sorts list
+			pages = list(set(pages))  # removes duplicates from list
+	except:
+		print("Enered incorrect number/s. Try again.")
+	return browser, pages, search_word
 
 
-def get_data():
-	user_browser, user_pages = get_user_input()
-	if user_browser in chromium:
+def get_max_page_amount(keyword: str):
+	url = f"https://www.riga.lv/lv/search?q={keyword}&types=file"
+	page = requests.get(url)
+	soup = BeautifulSoup(page.content, 'html.parser')
+	try:
+		last_page = soup.find(class_='pager__item--last').get_text().strip()
+	except:
 		try:
-			browser = webdriver.Chrome("chromedriver.exe")  # windows
+			last_page = soup.find_all(class_='pager__item page-item')
+			last_page = last_page[-1].get_text().strip()[-1]  # gets last number from navigation bar
 		except:
-			browser = webdriver.Chrome("chromedriver")  # gnu/linux
-	elif user_browser in firefox:
-		profile = webdriver.FirefoxProfile()
-		profile.set_preference('browser.download.folderList', 2)  # custom location
-		profile.set_preference('browser.download.manager.showWhenStarting', False)
-		profile.set_preference('browser.download.dir', '/files')
-		profile.set_preference('browser.helpApps.neverAsk.saveToDisk', 'text/csv')
-		browser = webdriver.Firefox(profile)
+			print("Something went wrong. Please try again or try another keyword.")
+	return int(last_page)
 
-	address = "https://www.riga.lv/lv"
-	browser.get(address)
-	# time.sleep(3)
-	browser.find_element_by_class_name('cookie-accept-all').click()
 
-	browser.find_element_by_class_name('search-link').click()
+def file_download(file_name, file_url):
+	print(f"\nNAME: {file_name}")
+	print(f"URL: {file_url}")
 
-	delay = 0
-	WebDriverWait(browser, delay).until(EC.presence_of_all_elements_located((By.ID, 'edit-search')))
-	browser.find_element_by_id('edit-search').send_keys("dokum")  # writes in search line
+	path = "files"
+	if not exists(path):
+		os.mkdir(path)
 
-	browser.find_element_by_id('search-header-button').click()
-
-	browser.maximize_window()
-	WebDriverWait(browser, delay).until(EC.presence_of_all_elements_located((By.CLASS_NAME, 'filter-content')))
-	# delay = 3
-	WebDriverWait(browser, delay).until(EC.presence_of_all_elements_located((By.ID, 'filter_type_file')))
-
-	browser.find_element_by_css_selector('label[for="filter_type_file"]').click()
-
-	browser.find_element_by_id('search-view-button').click()
-
-	file = browser.find_element_by_class_name('file')
+	response = requests.get(file_url)
+	if ".pdf" in file_name:
+		open(f"{path}/{file_name}", "wb").write(response.content)
+	else:
+		open(f"{path}/{file_name}.pdf", "wb").write(response.content)
 
 
 def main():

december/task_081221/test.py

@@ -1,21 +0,0 @@
-from selenium import webdriver
-from selenium.webdriver import ActionChains
-from selenium.webdriver.common.keys import Keys
-#browser exposes an executable file
-#Through Selenium test we will invoke the executable file which will then
-#invoke actual browser
-driver = webdriver.Chrome(executable_path="chromedriver")
-# to maximize the browser window
-driver.maximize_window()
-#get method to launch the URL
-driver.get("https://www.tutorialspoint.com/about/about_careers.htm")
-#to refresh the browser
-driver.refresh()
-# identifying the source element
-source = driver.find_element_by_xpath("//*[text()='Company']")
-# action chain object creation
-action = ActionChains(driver)
-# right click operation and then perform
-action.context_click(source).perform()
-#to close the browser
-# driver.close()

december/task_081221/user_input.py

@@ -0,0 +1,26 @@
+def main():
+	try:
+		user_input = input("Input: ")
+		user_input_array = user_input.split(" ")
+		if user_input == "all":
+			pages = list(map(int, range(1, 17 + 1)))
+		else:
+			for page_range in user_input_array:
+				if "-" in page_range:
+					first_num = int(page_range[:page_range.find("-")])  # gets first number
+					second_num = int(page_range[page_range.find("-") + 1:]) + 1  # gets second number
+					user_input_array = user_input_array + list(map(str, range(first_num, second_num)))  # creates list with str range
+			pages = [elem for elem in user_input_array if not "-" in elem]  # removes all elements containing "-"
+			pages = list(map(int, pages))  # convers str to int
+			pages.sort()  # sorts list
+			pages = list(set(pages))  # removes duplicates from list
+		print(pages)
+
+	except:
+		print("Something went wrong. Try again.")
+
+
+if __name__ == '__main__':
+	main()
+
+# 3 1 5 2 7-11 3-30

requirements.txt

@@ -39,3 +39,57 @@ wsproto==1.0.0
 xlrd==2.0.1
 xlwt==1.3.0
 yapf==0.31.0
+async-generator==1.10
+attrs==21.2.0
+beautifulsoup4==4.10.0
+bs4==0.0.1
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.8
+cryptography==36.0.0
+cycler==0.11.0
+et-xmlfile==1.1.0
+filelock==3.4.0
+fonttools==4.28.2
+geckodriver-autoinstaller==0.1.0
+h11==0.12.0
+idna==3.3
+jsoncodable==0.1.7
+jsonpickle==2.0.0
+k-selenium-cookies==0.0.4
+kiwisolver==1.3.2
+kproxy==0.0.1
+matplotlib==3.5.0
+noraise==0.0.16
+numpy==1.21.4
+openpyxl==3.0.9
+outcome==1.1.0
+packaging==21.3
+pandas==1.3.4
+Pillow==8.4.0
+pycparser==2.21
+pyOpenSSL==21.0.0
+pyparsing==3.0.6
+python-dateutil==2.8.2
+pytz==2021.3
+requests==2.26.0
+requests-file==1.5.1
+selenium==4.1.0
+selenium-browser==0.0.15
+setuptools-scm==6.3.2
+six==1.16.0
+sniffio==1.2.0
+sortedcontainers==2.4.0
+soupsieve==2.3.1
+tldextract==3.1.2
+tomli==1.2.2
+trio==0.19.0
+trio-websocket==0.9.2
+urllib3==1.26.7
+wget==3.2
+wsproto==1.0.0
+xlrd==2.0.1
+XlsxWriter==3.0.2
+xlwt==1.3.0
+xpath-utils==0.0.3
+yapf==0.31.0