BeautifulSoup是一个非常优秀的Python扩展库，可以用来从HTML或XML文件中提取我们感兴趣的数据，并且允许指定使用不同的解析器。由于beautifulsoup3已经不再继续维护，因此新的项目中应使用beautifulsoup4，目前最新版本是4.5.0，可以使用pip install beautifulsoup4直接进行安装，安装之后应使用from bs4 import BeautifulSoup导入并使用。下面我们就一起来简单看一下BeautifulSoup4的强大功能，更加详细完整的学习资料请参考https://www.crummy.com/software/BeautifulSoup/bs4/doc/。
>>> from bs4 import BeautifulSoup
>>> BeautifulSoup('hello world!', 'lxml') #自动添加和补全标签
<html><body><p>hello world!</p></body></html>
>>> 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') #也可以使用lxml或其他解析器
>>> print(soup.prettify()) #以优雅的方式显示出来
<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 class="sister" href="http://example.com/elsie" id="link1">
Elsie
</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.
</p>
<p class="story">
...
</p>
</body>
</html>
>>> soup.title #访问特定的标签
<title>The Dormouse's story</title>
>>> soup.title.name #标签名字
'title'
>>> soup.title.text #标签文本
"The Dormouse's story"
>>> soup.title.string
"The Dormouse's story"
>>> soup.title.parent #上一级标签
<head><title>The Dormouse's story</title></head>
>>> soup.head
<head><title>The Dormouse's story</title></head>
>>> soup.b
<b>The Dormouse's story</b>
>>> soup.body.b
<b>The Dormouse's story</b>
>>> soup.name #把整个BeautifulSoup对象看做标签对象
'[document]'
>>> soup.body
<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 class="sister" href="http://example.com/elsie" id="link1">Elsie</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.</p>
<p class="story">...</p>
</body>
>>> soup.p
<p class="title"><b>The Dormouse's story</b></p>
>>> soup.p['class'] #标签属性
['title']
>>> soup.p.get('class') #也可以这样查看标签属性
['title']
>>> soup.p.text
"The Dormouse's story"
>>> soup.p.contents
[<b>The Dormouse's story</b>]
>>> soup.a
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
>>> soup.a.attrs #查看标签所有属性
{'class': ['sister'], 'href': 'http://example.com/elsie', 'id': 'link1'}
>>> soup.find_all('a') #查找所有<a>标签
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</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>]
>>> soup.find_all(['a', 'b']) #同时查找<a>和<b>标签
[<b>The Dormouse's story</b>, <a class="sister" href="http://example.com/elsie" id="link1">Elsie</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>]
>>> import re
>>> soup.find_all(href=re.compile("elsie")) #查找href包含特定关键字的标签
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
>>> soup.find(id='link3')
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
>>> soup.find_all('a', id='link3')
[<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
>>> for link in soup.find_all('a'):
print(link.text,':',link.get('href'))
Elsie : http://example.com/elsie
Lacie : http://example.com/lacie
Tillie : http://example.com/tillie
>>> print(soup.get_text()) #返回所有文本
The Dormouse's story
The Dormouse's story
Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
>>> soup.a['id'] = 'test_link1' #修改标签属性的值
>>> soup.a
<a class="sister" href="http://example.com/elsie" id="test_link1">Elsie</a>
>>> soup.a.string.replace_with('test_Elsie') #修改标签文本
'Elsie'
>>> soup.a.string
'test_Elsie'
>>> print(soup.prettify())
<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 class="sister" href="http://example.com/elsie" id="test_link1">
test_Elsie
</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.
</p>
<p class="story">
...
</p>
</body>
</html>
>>> for child in soup.body.children: #遍历直接子标签
print(child)
<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 class="sister" href="http://example.com/elsie" id="test_link1">test_Elsie</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.</p>
<p class="story">...</p>
>>> for string in soup.strings: #遍历所有文本，结果略
print(string)
>>> test_doc = '<html><head></head><body><p></p><p></p></body></heml>'
>>> s = BeautifulSoup(test_doc, 'lxml')
>>> for child in s.html.children: #遍历直接子标签
print(child)
<head></head>
<body><p></p><p></p></body>
>>> for child in s.html.descendants: #遍历子孙标签
print(child)
<head></head>
<body><p></p><p></p></body>
<p></p>
<p></p>