import re
from bs4 import BeautifulSoup

html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>

<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" >Elsie</a>,
<a href="http://example.com/lacie" class="sister" >Lacie</a> and
<a href="http://example.com/tillie" class="sister" >Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc, 'html.parser')

links = soup.find('a',href=re.compile(r'ill'))
print links.get_text()
links = soup.find('p',class_="title")
print links.get_text(),links.name

相关文章:

猜你喜欢
  • 2022-01-11
  • 2021-05-22
  • 2021-08-17
  • 2021-05-30
  • 2021-06-12
  • 2021-12-22
相关资源
相似解决方案