Comment srape tous les liens d'un site Web de Python
# importing the HTMLSession class
from requests_html import HTMLSession
# create the object of the session
session = HTMLSession()
# url of the page
web_page = 'https://www.trtworld.com/'
# making get request to the webpage
respone = session.get(web_page)
# getting the html of the page
page_html = respone.html
# finding all <a> tags
all_links= page_html.links
# extracting meta tags html
for tag in all_links:
print(tag)
# getting only absolute links
absolute_links = page_html.absolute_links
for abs_link in absolute_links:
print(abs_link)Copy Code
Pythonist