You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

22 lines
891 B
Python

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
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 = dict()
target_page = requests.get(article.a.get('href'))
target_soup = BeautifulSoup(target_page.text, 'html.parser')
comic['title'] = target_soup.find('span', class_="article-heading__title")
comic['time'] = target_soup.find('time', class_="metadata__date").get('datetime')
comic['number'] = target_soup.find('span', class_="article-heading__kicker")
comic['image_url'] = target_soup.find(class_="scrollable-media-container").img.get('src')
print(comic)