BeautifulSoup
BeautifulSoup是一个模块，该模块用于接收一个HTML或XML字符串，然后将其进行格式化，之后遍可以使用他提供的方法进行快速查找指定元素，从而使得在HTML或XML中查找指定元素变得简单
1、安装：
pip3 install beautifulsoup4 pip install lxml # python2.x
2、简单使用：
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse‘s story</title></head>
<body>
asdf
<div class="title">
<b>The Dormouse‘s story总共</b>
<h1>f</h1>
</div>
<div class="story">Once upon a time there were three little sisters; and their names were
<a class="sister0" id="link1">Els<span>f</span>ie</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.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
# soup = BeautifulSoup(html_doc, features="lxml")
soup = BeautifulSoup(html_doc, features="html.parser") # 等同于上面
# 找到第一个a标签
tag1 = soup.find(name=‘a‘)
# 找到所有的a标签
tag2 = soup.find_all(name=‘a‘)
# 找到id＝link2的标签
tag3 = soup.select(‘#link2‘)
print(tag1)
print(tag2)
print(tag3)
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
# [<a class="sister0" id="link1">Els<span>f</span>ie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
3、标签方法：
① name标签名称
# name tag = soup.find(‘a‘) # <a class="sister0" id="link1">Els<span>f</span>ie</a> name = tag.name # 获取 print(name) # a tag.name = ‘span‘ # 设置 替换第一个a标签为span标签 print(soup)
② attrs标签属性
# attrs
tag = soup.find(‘a‘)
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
attrs = tag.attrs # 获取
print(attrs)
# {‘class‘: [‘sister0‘], ‘id‘: ‘link1‘}
tag.attrs = {‘ik‘:123} # 设置属性
tag.attrs[‘id‘] = ‘iiiii‘ # 更改id
print(soup)
③ children所有子标签
# 子标签，只是获取儿子
tag = soup.find(‘a‘)
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
v = tag.children
print(v)
# <list_iterator object at 0x02E71230>
for i in v:
print(i)
# Els
# <span>f</span>
# ie
④ descendants子子孙孙标签
# 获得子子孙孙
body = soup.find(‘body‘)
v = body.descendants
print(v)
for i in v:
print(i)
⑤ clear将标签的所有子标签全部清空（保留标签名）
# 清空表签内容 tag = soup.find(‘body‘) tag.clear() print(soup) # <html><head><title>The Dormouse‘s story</title></head> # <body></body> # </html>
⑥ decompose,递归的删除所有的标签
# 递归的删除所有的标签 body = soup.find(‘body‘) body.decompose() print(soup) # <html><head><title>The Dormouse‘s story</title></head> # # </html>
⑦ extract递归的删除所有的标签，并获取删除的标签
# 递归的删除所有的标签，并获取删除的标签 body = soup.find(‘body‘) v = body.extract() print(soup) # <html><head><title>The Dormouse‘s story</title></head> # # </html> print(v,type(v)) # <body> # asdf # <div class="title"> # <b>The Dormouse‘s story总共</b> # <h1>f</h1> # </div> # <div id="story">Once upon a time there were three little sisters; and their names were # <a class="sister0" id="link1">Els<span>f</span>ie</a>, # <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a> and # <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>; # and they lived at the bottom of a well.</div> # ad<br/>sf # <p class="story">...</p> # </body> <class ‘bs4.element.Tag‘>
时间： 2024-11-03 22:10:30