spiegel_online_bestseller.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-


import requests
from lxml import html


def load_doc():
    doc= requests.get('http://www.spiegel.de/kultur/literatur/spiegel-bestseller-taschenbuecher-a-1025518.html')
    
    if doc.status_code == 200:
        return doc.content


def extract_dom(doc):
    dom = html.fromstring(doc)
    blocks = dom.xpath('//div[@class="content clearfix"]')

    for block in blocks:
        img = block.xpath('./div/div/a/img/@src')
        title = block.xpath('./div/a/span[@class="title bestseller-popup-link"]/text()')
        div = block.xpath('./div[@class="bestseller-popup-content clearfix"]/div[@class="bestseller-popup-klappentext"]/text()')
        print('<div class="row mb-50"><div class="col-xs-12 col-sm-3">')
        print('<img src="http://www.spiegel.de{}" width="200px" height="auto">'.format(img[0]))
        print('</div><div class="col-xs-12 col-sm-9"><h2>{}</h2>'.format(title[0]))
        try:
            print('<p>{}</p>'.format(div[0]))
        except:
            pass
        print('</div></div>')
        


def main():
    doc = load_doc()
    extract_dom(doc)


if __name__ == '__main__':
    main()