# -*- coding:utf-8 -*-
# pip install beautifulsoup4 安装
from bs4 import BeautifulSoup
import re
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')
#soup = BeautifulSoup(html_doc,'xml')
# 打印 title标签和标签内的内容
print(soup.title)
# 打印title标签名
print(soup.title.name)
# 打印title标签里面的内容
print(soup.title.string)
# 打印title父标签的标签名
print(soup.title.parent.name)
# 打印p标签名和标签内容
print(soup.p)
# 打印第一个p标签的class属性值
print(soup.p['class'])
# 打印a标签和标签内容
print(soup.a)
# 打印查询到的所有p标签和标签内容
print(soup.find_all('p'))
# 打印 id属性是link3的标签和内容
print(soup.find(id='link3'))
for link in soup.find_all('a'):
# 打印 a标签 href 属性值 http://example.com/...
print(link.get('href'))
print('-'*50)
# 打印文档除了标签之外的所有内容
print(soup.get_text())
print('-'*50)
# 打印文档除了标签之外的所有内容
print(soup.text)
print('*'*50)
# 正则匹配查找含有b的标签
# body
# b
for tag in soup.find_all(re.compile('b')):
print(tag.name)
print('*'*50)
# 查找所有a标签和b标签
print(soup.find_all(['a','b']))
print('*'*50)
# 查找a标签 并且class属性为 sister
print(soup.find_all("a", attrs={"class": "sister"}))
# 查找a标签并且 值为Elsize
print(soup.find_all("a", text="Elsie"))
BeautifulSoup
最新推荐文章于 2023-05-12 22:32:44 发布