PYTHON 爬虫笔记五:BeautifulSoup库基础用法

知识点一：BeautifulSoup库详解及其基本使用方法

  • 什么是BeautifulSoup

灵活又方便的网页解析库，处理高效，支持多种解析器。利用它不用编写正则表达式即可方便实现网页信息的提取库。

  • BeautifulSoup中常见的解析库

　　　　　　　　

  • 基本用法：

    html = '''
<html><head><title>The Domouse'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 little sisters;and their names were
<a href="http://example.com/elsie"class="sister"id="link1"><!--Elsie--></a>
<a hred="http://example.com/lacle"class="sister"id="link2">Lacle</a>and
<a hred="http://example.com/tilie"class="sister"id="link3">Tillie</a>
and they lived at bottom of a well.</p>
<p class="story">...</p>
'''
 
from bs4 import BeautifulSoup
soup= BeautifulSoup(html,'lxml')
 
print(soup.prettify())#格式化代码，打印结果自动补全缺失的代码
print(soup.title.string)#文章标题
    <html>
 <head>
  <title>
   The Domouse'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 little sisters;and their names were
   <a class="sister" href="http://example.com/elsie" id="link1">
    <!--Elsie-->
   </a>
   <a class="sister" hred="http://example.com/lacle" id="link2">
    Lacle
   </a>
   and
   <a class="sister" hred="http://example.com/tilie" id="link3">
    Tillie
   </a>
   and they lived at bottom of a well.
  </p>
  <p class="story">
   ...
  </p>
 </body>
</html>
The Domouse's story
    获得的结果

  1. 标签选择器

    1. 选择元素

      html = '''
<html><head><title>The Domouse'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 little sisters;and their names were
<a href="http://example.com/elsie"class="sister"id="link1"><!--Elsie--></a>
<a hred="http://example.com/lacle"class="sister"id="link2">Lacle</a>and
<a hred="http://example.com/tilie"class="sister"id="link3">Tillie</a>
and they lived at bottom of a well.</p>
<p class="story">...</p>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
      
      print(soup.title)
        #<title>The Domouse's story</title>
print(type(soup.title))
        #<class 'bs4.element.Tag'>
print(soup.head)
        #<head><title>The Domouse's story</title></head>
print(soup.p)#当出现多个时，只返回第一个
        #<p class="title" name="dromouse"><b>The Dormouse's story</b></p>

    2. 获取标签名称

      html = '''
<html><head><title>The Domouse'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 little sisters;and their names were
<a href="http://example.com/elsie"class="sister"id="link1"><!--Elsie--></a>
<a hred="http://example.com/lacle"class="sister"id="link2">Lacle</a>and
<a hred="http://example.com/tilie"class="sister"id="link3">Tillie</a>
and they lived at bottom of a well.</p>
<p class="story">...</p>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
      
      print(soup.title.name)
        #title

    3. 获取属性

      html = '''
<html><head><title>The Domouse'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 little sisters;and their names were
<a href="http://example.com/elsie"class="sister"id="link1"><!--Elsie--></a>
<a hred="http://example.com/lacle"class="sister"id="link2">Lacle</a>and
<a hred="http://example.com/tilie"class="sister"id="link3">Tillie</a>
and they lived at bottom of a well.</p>
<p class="story">...</p>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

print(soup.p.attrs['name'])
        #dromouse
print(soup.p['name'])
        #dromouse

    4. 获取标签内容

      html = '''
<html><head><title>The Domouse'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 little sisters;and their names were
<a href="http://example.com/elsie"class="sister"id="link1"><!--Elsie--></a>
<a hred="http://example.com/lacle"class="sister"id="link2">Lacle</a>and
<a hred="http://example.com/tilie"class="sister"id="link3">Tillie</a>
and they lived at bottom of a well.</p>
<p class="story">...</p>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

print(soup.p.string)
        #The Dormouse's story

    5. 嵌套选择

      html = '''
<html><head><title>The Domouse'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 little sisters;and their names were
<a href="http://example.com/elsie"class="sister"id="link1"><!--Elsie--></a>
<a hred="http://example.com/lacle"class="sister"id="link2">Lacle</a>and
<a hred="http://example.com/tilie"class="sister"id="link3">Tillie</a>
and they lived at bottom of a well.</p>
<p class="story">...</p>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

print(type(soup.title))
        #<class 'bs4.element.Tag'>
print(soup.head.title.string)#观察html的代码，其中有一层包含的关系：head（title），那我们就可以用嵌套的形式将其内容打印出来；body（p或是a）
        #The Domouse's story

    6. 子节点和子孙节点

      #获取标签的子节点
html2 = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup
soup2 = BeautifulSoup(html2,'lxml')
print(soup2.p.contents)
      ['\n        Once upon a time there were little sisters;and their names were\n        ', <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>, '\n', <a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>, '\n        and\n        ', <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>, '\n        and they lived at bottom of a well.\n        ']
      获得的内容

      另一中方法：

      #获取标签的子节点
html2 = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup

soup = BeautifulSoup(html2,'lxml')
 
print(soup.children)#不同之处：children实际上是一个迭代器，需要用循环的方式才能将内容取出
 
for i,child in enumerate(soup.p.children):
    print(i,child)
      <list_iterator object at 0x00000208F026B400>
0 
        Once upon a time there were little sisters;and their names were
        
1 <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
2 

3 <a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
4 
        and
        
5 <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
6 
        and they lived at bottom of a well.
      获得的结果

      不同之处：children实际上是一个迭代器，需要用循环的方式才能将内容取出，而子节点只是一个列表

      #获取标签的子孙节点
html2 = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup

soup = BeautifulSoup(html2,'lxml')
    
print(soup2.p.descendants)#获取所有的子孙节点，也是一个迭代器
 
for i,child in enumerate(soup2.p.descendants):
    print(i,child)
      子孙节点
      <generator object descendants at 0x00000208F0240AF0>
0 
        Once upon a time there were little sisters;and their names were
        
1 <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
2 

3 <span>Elsle</span>
4 Elsle
5 

6 

7 <a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
8 Lacle
9 
        and
        
10 <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
11 Tillie
12 
        and they lived at bottom of a well.
      --->获得的结果

    7. 父节点和祖先节点

      #父节点
html = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup

soup = BeautifulSoup(html,'lxml')

print(soup.a.parent)
      父节点
      <p class="story">
        Once upon a time there were little sisters;and their names were
        <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
<a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
        and
        <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
      --->获得的结果
      #获取祖先节点
html = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup

soup = BeautifulSoup(html,'lxml')
print(list(enumerate(soup.a.parents)))#所有祖先节点（爸爸也算）
      祖先节点
      [(0, <p class="story">
        Once upon a time there were little sisters;and their names were
        <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
<a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
        and
        <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>), (1, <body>
<p class="story">
        Once upon a time there were little sisters;and their names were
        <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
<a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
        and
        <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
<p class="story">...</p>
</body>), (2, <html>
<head>
<title>The Domouse's story</title>
</head>
<body>
<p class="story">
        Once upon a time there were little sisters;and their names were
        <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
<a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
        and
        <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
<p class="story">...</p>
</body></html>), (3, <html>
<head>
<title>The Domouse's story</title>
</head>
<body>
<p class="story">
        Once upon a time there were little sisters;and their names were
        <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsle</span>
</a>
<a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>
        and
        <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
<p class="story">...</p>
</body></html>)]
      --->获得的内容

    8. 兄弟节点

      #获取前兄弟节点
html = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup

soup = BeautifulSoup(html,'lxml')
 
#兄弟节点（与之并列的节点）
print(list(enumerate(soup.a.previous_siblings)))#前面的兄弟节点
      前兄弟节点
      [(0, '\n        Once upon a time there were little sisters;and their names were\n        ')]
      --->获得的内容
      html = '''
<html>
    <head>
        <title>The Domouse's story</title>
    </head>
    <body>
    <p class="story">
        Once upon a time there were little sisters;and their names were
        <a href="http://example.com/elsie" class="sister"id="link1">
        <span>Elsle</span>
        </a>
        <a hred="http://example.com/lacle"class="sister" id="link2">Lacle</a>
        and
        <a hred="http://example.com/tilie"class="sister" id="link3">Tillie</a>
        and they lived at bottom of a well.
        </p>
        <p class="story">...</p>
'''
from bs4 import BeautifulSoup

soup = BeautifulSoup(html,'lxml')
 
#兄弟节点（与之并列的节点）
print(list(enumerate(soup.a.next_siblings)))#后面的兄弟节点
      后面兄弟节点
      [(0, '\n'), (1, <a class="sister" hred="http://example.com/lacle" id="link2">Lacle</a>), (2, '\n        and\n        '), (3, <a class="sister" hred="http://example.com/tilie" id="link3">Tillie</a>), (4, '\n        and they lived at bottom of a well.\n        ')]
      --->获得的结果

  2.  标准选择器

    find_all(name,attrs,recursive,text,**kwargs)

    　　可以根据标签名，属性，内容查找文档

    1. 根据name查找

      html = '''
<div class="panel">
    <div class="panel-heading"name="elements">
        <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>
'''
from bs4 import BeautifulSoup 
soup = BeautifulSoup(html,'lxml')
 
print(soup.find_all('ul'))#列表类型
print(type(soup.find_all('ul')[0]))
      [<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>]
<class 'bs4.element.Tag'>
      获得的结果
      html = '''
<div class="panel">
    <div class="panel-heading"name="elements">
        <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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
 
for ul in soup.find_all('ul'):
    print(ul.find_all('li'))#层层嵌套的查找
      [<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>]
[<li class="element">Foo</li>, <li class="element">Bar</li>]
      获得的结果

    2. 根据attrs查找

      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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

print(soup.find_all(attrs={'id':'list-1'}))
print(soup.find_all(attrs={'name':'elements'}))
      [<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" id="list-1" name="elements">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>]
      获得的结果

      另一种方式

      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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
 
print(soup.find_all(id='list-1'))
print(soup.find_all(class_='element'))
      另一种方式
      [<ul class="list" id="list-1">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>]
[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>, <li class="element">Foo</li>, <li class="element">Bar</li>]
      --->获得的结果

    3. 根据text查找

      #text
html = '''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body"name="elelments">
        <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>
''' 
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
 
print(soup.find_all(text='Foo'))
        #['Foo', 'Foo']
      find（name，attrs，recursive，text，**kwargs）返回单个元素，find_all返回所有元素
      html = '''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body"name="elelments">
        <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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
      
print(soup.find('ul'))
print(type(soup.find('ul')))
print(soup.find('page'))
      <ul class="list" id="list-1">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>
<class 'bs4.element.Tag'>
None
      获得的结果

    4. 其他方法

      如果使用find方法，返回单个元素 

find_parents()返回所有祖先节点 
find_parent()返回直接父节点 
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()返回前面所有的兄弟节点 
find_previous_sibling()返回前面第一个的兄弟节点 
find_all_next()返回节点后所有符合条件的节点 
find_next()返回节点后第一个符合条件的节点 
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

  3. CSS选择器（通过select()直接传入CSS选择器即可完成选择）

    1. html = '''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body"name="elelments">
        <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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

print(soup.select('.panel .panel-heading')) #class就需要加一个“.”
print(soup.select('ul li')) #选择标签
print(soup.select('#list-2 .element'))
print(type(soup.select('ul')[0]))  
      [<div class="panel-heading">
<h4>Hello</h4>
</div>]
[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>, <li class="element">Foo</li>, <li class="element">Bar</li>]
[<li class="element">Foo</li>, <li class="element">Bar</li>]
<class 'bs4.element.Tag'>
      获得的结果

      另一种方法:

      html = '''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body"name="elelments">
        <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>
'''
 
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
 
for ul in soup.select('ul'):#直接print(soup.select('ul li'))
    print(ul.select('li'))
      另一种方法
      [<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>]
[<li class="element">Foo</li>, <li class="element">Bar</li>]
      --->获得的结果

    2. 获取属性

      html = '''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body"name="elelments">
        <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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

for ul in soup.select('ul'):
    print(ul['id'])#直接用[]
    print(ul.attrs['id'])#或是attrs+[]
      list-1
list-1
list-2
list-2
      获得的结果

    3. 获取内容

      html = '''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body"name="elelments">
        <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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')

for li in soup.select('li'):
    print(li['class'], li.get_text())
      ['element'] Foo
['element'] Bar
['element'] Jay
['element'] Foo
['element'] Bar
      获得的结果

  • 总结

推荐使用'lxml'解析库，必要时使用html.parser

标签选择器筛选功能但速度快

建议使用find（），find_all（）查询匹配单个结果或者多个结果

如果对CSS选择器熟悉建议选用select（）

记住常用的获取属性和文本值得方法

 

 

posted @ 2018-08-08 19:58  达尔文在思考  阅读(306)  评论(0)  编辑  收藏  举报