22 lines
562 B
Python
22 lines
562 B
Python
|
import requests
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
import json
|
||
|
|
|
||
|
|
# URL de la page
|
||
|
|
url = "https://partipirate.org/programTags"
|
||
|
|
|
||
|
|
# Récupérer le contenu HTML de la page
|
||
|
|
response = requests.get(url)
|
||
|
|
soup = BeautifulSoup(response.content, "html.parser")
|
||
|
|
|
||
|
|
# Extraire les ancres "#main figcaption a" et leurs attributs "href"
|
||
|
|
links = []
|
||
|
|
for a in soup.select("#main figcaption a"):
|
||
|
|
href = a.get("href")
|
||
|
|
if href:
|
||
|
|
links.append(href)
|
||
|
|
|
||
|
|
# Enregistrer les liens dans un fichier JSON
|
||
|
|
with open("partipirate_links.json", "w") as f:
|
||
|
|
json.dump(links, f, indent=4)
|