问用BS4抓取网站

EN

import requests
from bs4 import BeautifulSoup


result = requests.get("http://www.cvbankas.lt/")
src = result.content
soup = BeautifulSoup(src, 'lxml')

urls = []
for article_tag in soup.find_all("article"):
        a_tag = article_tag.find('a')
        urls.append(a_tag.attrs['href'])
        div_tag = article_tag.find('span')
        urls.append(div_tag.attrs['class'])

print(urls)