f0x1/Kaenguru_requests
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases Wiki Activity

second loop

Browse source
This commit is contained in:
f0x1 2022-01-14 19:41:02 +01:00
parent 4f89c7b7ea
commit 6a36518bbc
1 changed files with 9 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
ZeitOnlineRequests.py
View file

@ -1,8 +1,6 @@
# -*- coding: utf-8 -*-
import os, requests, shutil
import requests
from bs4 import BeautifulSoup
from time import time
from multiprocessing.pool import ThreadPool
base_url = 'https://www.zeit.de/serie/die-kaenguru-comics?p='
@ -14,5 +12,11 @@ for page in range(1, 15):
soup = BeautifulSoup(r.text, 'html.parser')
articles = soup.find_all('article')
for article in articles:
comic_title = article.a.contents
print(comic_title)
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)