BeautifulSoup 库学习笔记

浏览: 2644

1、常用解析库

Clipboard Image.png


2、BeautifulSoup的基本使用

from bs4 import BeautifulSoup

html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 美化后补全输出
print(bs4.prettify())
# 输出title标签中的内容
print(bs4.title.string)

3、BeautifulSoup标签选择器的用法

3.1、选择元素

from bs4 import BeautifulSoup

html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出title标签  <title>The Dormouse's story</title>
print(bs4.title)
# 输出获取到title标签的类型  <class 'bs4.element.Tag'>
print(type(bs4.title))
# 输出head标签
print(bs4.head)
# 输出获取到head标签的类型    <class 'bs4.element.Tag'>
print(type(bs4.head))
# 获取到head标签中的title标签
print(bs4.head.title)
# 输出p标签(只输出第一个)
print(bs4.p)

从上述的代码中可以看出,BeautifulSoup解析出的标签返回任然是一个BeautifulSoup的Tag类，可以再次进行筛选

3.2、获取名称

from bs4 import BeautifulSoup

html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 获取选择的标签的名称  title
print(bs4.title.name)

3.3、获取属性

from bs4 import BeautifulSoup

html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出p标签的name属性值
print(bs4.p['name'])
# 输出p标签的name属性值
print(bs4.p.attrs['name'])

3.4、获取内容

from bs4 import BeautifulSoup

html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出title标签中的内容
print(bs4.title.string)
# 输出a标签中的内容(去除html标签包括注释)
print(bs4.a.string)

3.5、嵌套选择

from bs4 import BeautifulSoup

html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出head标签中的title标签中的内容
print(bs4.head.title.string)

3.6、子节点和子孙节点

3.6.1、contents

html = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <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">
                <span>Elsie</span>
            </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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 将p标签的子节点以列表的方式输出
print(bs4.p.contents)

3.6.2、children

from bs4 import BeautifulSoup

html = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <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">
                <span>Elsie</span>
            </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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 获取p标签的所有子节点，返回一个 list 生成器对象
print(bs4.p.children)
# 对子节点进行遍历
for i, child in enumerate(bs4.p.children):
    print(i, child)

3.6.3、descendants

from bs4 import BeautifulSoup

html = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <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">
                <span>Elsie</span>
            </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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 获取p标签的所有子节点(包含子孙节点)，返回一个 list 生成器对象
print(bs4.p.descendants)
# 对子节点进行遍历
for i, child in enumerate(bs4.p.descendants):
    print(i, child)

3.7、父节点和祖先节点

3.7.1、parent

from bs4 import BeautifulSoup

html = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <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">
                <span>Elsie</span>
            </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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出第一个a标签的父节点
print(bs4.a.parent)

3.7.2、parents

from bs4 import BeautifulSoup

html = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <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">
                <span>Elsie</span>
            </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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出循环遍历出所有的祖先节点
for i, parent in enumerate(bs4.a.parents):
    print(i, parent)

3.8、兄弟节点

from bs4 import BeautifulSoup

html = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <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">
                <span>Elsie</span>
            </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>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出所有前兄弟节点
print(list(enumerate(bs4.a.next_siblings)))
# 输出所有后兄弟节点
print(list(enumerate(bs4.a.previous_siblings)))

4、标准选择器

4.1、find_all (返回所有元素)

可根据标签名、属性、内容查找文档

4.1.1、name根据标签名

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出所有的ul标签(列表)
print(bs4.find_all('ul'))
# 输出查找到元素的类型  <class 'bs4.element.Tag'>
print(type(bs4.find_all('ul')[0]))

for i in bs4.find_all('ul'):

    # 输出每个ul中的所有li

    print(i.find_all('li'))

4.1.2、attr根据属性

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出根据id属性查找到的tag元素
print(bs4.find_all(attrs={'id':'list-1'}))
# 上述的简写方式
print(bs4.find_all(id='list-1'))
# 输出根据name属性查找到的tag元素
print(bs4.find_all(attrs={'name':'elements'}))
# 根据class查找的话，因为class是python的关键字因此需要加上_
print(bs4.find_all(class_='list-small'))

4.1.3、text根据文本

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
# 通过 text 参数可以搜搜文档中的字符串内容.与 name 参数的可选值一样, text 参数接受 字符串 , 正则表达式 , 列表, True
print(bs4.find_all(text='Foo'))

4.2、find(查找单个)

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
# 输出第一个ul标签
print(bs4.find('ul'))
# <class 'bs4.element.Tag'>
print(type(bs4.find('ul')))
# 如果找不到则输出None
print(bs4.find('page'))

4.3、其他用法

find_parents() find_parent()

find_parents()返回所有祖先节点，find_parent()返回直接父节点。


find_next_siblings() find_next_sibling()

find_next_siblings()返回后面所有兄弟节点，find_next_sibling()返回后面第一个兄弟节点。


find_previous_siblings() find_previous_sibling()

find_previous_siblings()返回前面所有兄弟节点，find_previous_sibling()返回前面第一个兄弟节点。


find_all_next() find_next()

find_all_next()返回节点后所有符合条件的节点, find_next()返回第一个符合条件的节点


find_all_previous() 和 find_previous()

find_all_previous()返回节点后所有符合条件的节点, find_previous()返回第一个符合条件的节点

5、CSS选择器

通过select()直接传入CSS选择器即可完成选择

5.1、普通选择

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
print(bs4.select('.panel .panel-heading'))
print(bs4.select('ul li'))
print(bs4.select('#list-2 .element'))
# <class 'list'>  以列表方式输出
print(type(bs4.select('ul li')))
# <class 'bs4.element.Tag'>
print(type(bs4.select('ul')[0]))

5.2、获取属性

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
# 查找所有ul并遍历
for ul in bs4.select('ul'):
    # 获取ul的id属性
    print(ul['id'])
    # 获取ul的id属性
    print(ul.attrs['id'])

5.3、获取内容

from bs4 import BeautifulSoup

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""

bs4 = BeautifulSoup(html,'lxml')
# 查找所有li并遍历
for li in bs4.select('li'):
    # 输出li的文本内容
    print(li.get_text())
推荐 1
ID王大伟
本文由 蒋蜀黍 创作，采用 知识共享署名-相同方式共享 3.0 中国大陆许可协议 进行许可。
转载、引用前需联系作者，并署名作者且注明文章出处。
本站文章版权归原作者及原出处所有 。内容为作者个人观点， 并不代表本站赞同其观点和对其真实性负责。本站是一个个人学习交流的平台，并不用于任何商业目的，如果有任何问题，请及时联系我们，我们将根据著作权人的要求，立即更正或者删除有关内容。本站拥有对此声明的最终解释权。

0 个评论

要回复文章请先登录或注册