python bs4的使用

最新推荐文章于 2025-08-23 20:28:56 发布

weixin_30521649

最新推荐文章于 2025-08-23 20:28:56 发布

阅读量64

点赞数

CC 4.0 BY-SA版权

文章标签： python

原文链接：http://www.cnblogs.com/ceshixuexi/p/7764176.html

# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup as bs
import re

html_doc = """
<html><head><title>The Dormouse's story<a>试试</a></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=bs(html_doc,'html.parser')

# 获取网页内容
# print(soup.prettify())


# #获取网页的title
# print(soup.title)
#
# #H获取网页title的内容,获取id为link2的内容,若标签中还有标签，则返回值为None,这时就可以用.get_text()来获取结果
# print(soup.title.string)
# print(soup.title.get_text())

#获取第一个a标签
# print(soup.a)
#
#
# print(soup.find(id='link2').string)

#
# #获取所有的a标签，并返回列表
# print(soup.findAll('a'))
#
#
# #获取class为story的p标签，且不能像find(id='**')来获取，因为class为python的关键字
# print(soup.find('p',{'class':'story'}).get_text())

#
# for tag in soup.find_all(re.compile("^b")):
#     print(tag.name)






data=soup.findAll('a',href=re.compile(r'^http://example\.com'))

print(data)

转载于:https://www.cnblogs.com/ceshixuexi/p/7764176.html