<ul class="list-group">
  <li class="list-group-item"><a href="">Element 1</a></li>
  <li class="list-group-item"><a href="">Element 2</a></li>
  <li class="list-group-item"><a href="">Element 3</a></li>
</ul>

import requests
from bs4 import BeautifulSoup


url =URL, um HTML zu erhalten
response = requests.get(url)
response.encoding = response.apparent_encoding

bs = BeautifulSoup(response.text, 'html.parser')

ul = bs.select('ul.list-group')

for li in ul[0].select('li.list-group-item'):
    a_tags = li.select('a')
    a_tag = a_tags[0]
    item_name = a_tag.text.strip()

<ul class="list-group">
  <li class="list-group-item"><a href="">Element 1</a></li>
  <li class="list-group-item"><a href="">Element 2</a></li>
  <li class="list-group-item"><a href="">Element 3</a></li>
</ul>

import scrapy


class SampleSpider(scrapy.Spider):
    name = 'sample'
    allowd_domains = [Domain]
    start_urls = [
Ziel-URL
    ]

    def parse_list(self, response):
        ul = response.css('ul.list-group')[0]
        for li in ul.css('li.list-group-item'):
            item_url = li.css('a::attr(href)').extract_first()

            yield scrapy.Request(item_url, callback=parse_detail)

    def parse_detail(self, response):
        item_name = response.css('h1.item-name::text').extract_first()
        return item_name

Recommended Posts