web_scrap/web_scrap.py

#!/usr/bin/python3

# Python 3
# Extraction des liens d'une page web
from bs4 import BeautifulSoup
import requests

page = requests.get("https://www.clarissariviere.com")

if page.status_code == 200:
    soup = BeautifulSoup(page.text, 'html.parser')
    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)


for i in range(1,100):
    paging = i * 10
    page = requests.get("https://www.clarissariviere.com/archives/p{0}-10.html".format(i))
    soup = BeautifulSoup(page.text, 'html.parser')
    if page.status_code == 200:
        h2 = soup.find_all("h2")
        for title in h2:
            print(title.find_all("a")[0].get("href", "/"))