# -*- coding: utf-8 -*-
import requests
import csv
import os
from bs4 import BeautifulSoup

base_url = 'https://www.zeit.de/serie/die-kaenguru-comics?p='
csv_file = open('output.csv', 'w', newline='')
csv_file_writer = csv.writer(csv_file, dialect='excel')

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").string
        comic['time'] = target_soup.find('time', class_="metadata__date").get('datetime')
        comic['number'] = target_soup.find('span', class_="article-heading__kicker").string.replace("Folge ", '')
        media_container = target_soup.find(class_="scrollable-media-container")
        if media_container: 
            comic['image_url'] = media_container.img.get('src')
        else: 
            media_container = target_soup.find(class_="collapsible-image__figure")
            if media_container:
                comic['image_url'] = media_container.img.get('src')
            else: 
                print('media_container not found')
        
        csv_file_writer.writerow(comic)
        
        image_download = requests.get(comic['image_url'])
        if os.path.exists(comic['number']+'.webp'):
            comic['number'] += '_'
        file = open(comic['number']+'.webp', 'xb')
        file.write(image_download.content)
        file.close()
        print(comic)
csv_file.close()