beautifulsoup测试

时间:2021-04-30 22:09:40
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" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">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