Files
cours/referencement/search.py
2024-11-23 13:38:17 +01:00

14 lines
327 B
Python

import requests
from bs4 import BeautifulSoup
def search(url):
r = requests.get(url)
return r.text
def search_urls_in_text(content):
soup = BeautifulSoup(content, 'html5lib')
hrefs = [a['href'] for a in soup.find_all('a', href=True)]
return hrefs
print(search_urls_in_text(search("https://google.com")))