标签：htm imp string href head time ring from otto
from bs4 import BeautifulSoup
from bs4 import Comment
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">...<!-- aaaaa --></p></html>
"""
soup = BeautifulSoup(html_doc, "lxml")
print(soup.prettify())
print(‘*‘ * 100)
print(soup.title)
print(soup.title.string)
print(soup.title.text)
print(soup.title.parent.name)
print(‘*‘ * 100)
print(soup.a)
print(soup.a.attrs)
print(soup.a[‘href‘])
print(soup.a.attrs[‘href‘])
print(soup.find(‘p‘))
print(soup.find(id="link1"))
print(soup.find_all(‘a‘))
for link in soup.find_all(‘a‘):
print(link.get(‘href‘))
print(soup.select(‘.sister‘))
print(‘*‘ * 100)
print(soup.get_text())
print(‘*‘ * 100)
comments = soup.findAll(text=lambda text: isinstance(text, Comment))
print(comments)
标签：htm imp string href head time ring from otto
原文地址：https://www.cnblogs.com/xgege/p/13280510.html
