first commit

master
f0x1 3 years ago
commit 4f89c7b7ea

@ -0,0 +1,18 @@
# -*- coding: utf-8 -*-
import os, requests, shutil
from bs4 import BeautifulSoup
from time import time
from multiprocessing.pool import ThreadPool
base_url = 'https://www.zeit.de/serie/die-kaenguru-comics?p='
for page in range(1, 15):
page_url = base_url + str(page)
print(page_url)
r = requests.get(page_url)
soup = BeautifulSoup(r.text, 'html.parser')
articles = soup.find_all('article')
for article in articles:
comic_title = article.a.contents
print(comic_title)
Loading…
Cancel
Save