2023-02-28 21:42:21 +01:00
|
|
|
#!/usr/bin/python3
|
|
|
|
|
|
|
|
|
|
# Python 3
|
|
|
|
|
# Extraction des liens d'une page web
|
|
|
|
|
from bs4 import BeautifulSoup
|
2023-02-28 21:52:12 +01:00
|
|
|
import requests
|
2023-02-28 21:42:21 +01:00
|
|
|
|
2023-02-28 21:52:12 +01:00
|
|
|
page = requests.get("https://www.clarissariviere.com")
|
|
|
|
|
|
|
|
|
|
if page.status_code == 200:
|
|
|
|
|
soup = BeautifulSoup(page.text, 'html.parser')
|
2023-02-28 22:03:03 +01:00
|
|
|
ul = soup.find_all("ul", id="listsmooth")
|
|
|
|
|
for anchor in ul[0].find_all("a"):
|
|
|
|
|
href = anchor.get('href', '/')
|
|
|
|
|
if href != "#" and href != "http://www.clarissariviere.com/":
|
|
|
|
|
print(href)
|
