python之Beautiful Soup的基本用法

from bs4 import BeautifulSoup
soup = BeautifulSoup(‘
Hello‘, ‘lxml‘)
print(soup.p.string)

Hello

html = """

The Dormouse‘s story
Once upon a time there were three little sisters; and their names were
,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, ‘lxml‘)
#调用prettify()方法。这个方法可以把要解析的字符串以标准的缩进格式输出
print(soup.prettify())
print(soup.title.string)

 
class="title" name="dromouse">
   
    The Dormouse‘s story
   
  
  
class="story">
   Once upon a time there were three little sisters; and their names were
   class="sister" href="http://example.com/elsie" id="link1">
    
   
   ,
   class="sister" href="http://example.com/lacie" id="link2">
    Lacie
   
   and
   class="sister" href="http://example.com/tillie" id="link3">
    Tillie
   
   ;
and they lived at the bottom of a well.
  
  
class="story">
   ...
  
 

The Dormouse‘s story

html = """


The Dormouse‘s story

Once upon a time there were three little sisters; and their names were
,
Lacie and
Tillie;
and they lived at the bottom of a well.

...

"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, ‘lxml‘)
print(‘输出结果为title节点加里面的文字内容:\n‘,soup.title)
print(‘输出它的类型:\n‘,type(soup.title))
print(‘输出节点的文本内容:\n‘,soup.title.string)
print(‘结果是节点加其内部的所有内容:\n‘,soup.head)
print(‘结果是第一个p节点的内容:\n‘,soup.p)
print(‘利用name属性获取节点的名称:\n‘,soup.title.name)
#这里需要注意的是，有的返回结果是字符串，有的返回结果是字符串组成的列表。
# 比如，name属性的值是唯一的，返回的结果就是单个字符串。
# 而对于class，一个节点元素可能有多个class，所以返回的是列表。
print(‘每个节点可能有多个属性，比如id和class等:\n‘,soup.p.attrs)
print(‘选择这个节点元素后，可以调用attrs获取所有属性：\n‘,soup.p.attrs[‘name‘])
print(‘获取p标签的name属性值：\n‘,soup.p[‘name‘])
print(‘获取p标签的class属性值：\n‘,soup.p[‘class‘])
print(‘获取第一个p节点的文本:\n‘,soup.p.string)

输出结果为title节点加里面的文字内容:

html = """

"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, ‘lxml‘)
print(‘获取了head节点元素，继续调用head来选取其内部的head节点元素:\n‘,soup.head.title)
print(‘继续调用输出类型：\n‘,type(soup.head.title))
print(‘继续调用输出内容：\n‘,soup.head.title.string)

获取了head节点元素，继续调用head来选取其内部的head节点元素:
 继续调用输出类型：
 class ‘bs4.element.Tag‘>
继续调用输出内容：
 The Dormouse‘s story

html=‘‘‘

    

        
Hello
    
    

        

Foo
            
Bar
            
Jay
        

Foo
            
Bar
        


‘‘‘
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, ‘lxml‘)
print(‘查询所有ul节点，返回结果是列表类型，长度为2:\n‘,soup.find_all(name=‘ul‘))
print(‘每个元素依然都是bs4.element.Tag类型:\n‘,type(soup.find_all(name=‘ul‘)[0]))
#将以上步骤换一种方式，遍历出来
for ul in soup.find_all(name=‘ul‘):
    print(‘输出每个u1:‘,ul.find_all(name=‘li‘))
#遍历两层
for ul in soup.find_all(name=‘ul‘):
    print(‘输出每个u1:‘,ul.find_all(name=‘li‘))
    for li in ul.find_all(name=‘li‘):
        print(‘输出每个元素：‘,li.string)

查询所有ul节点，返回结果是列表类型，长度为2:
 [

class="list" id="list-1">
• class="element">Foo
• class="element">Bar
• class="element">Jay

class="list list-small" id="list-2">
• class="element">Foo
• class="element">Bar