Python -- BeautifulSoup的学习使用

BeautifulSoup4.3 的使用

下载和安装

# 下载
http://www.crummy.com/software/BeautifulSoup/bs4/download/

# 解压后 使用root执行
# python setup.py install

# 最后 在python中测试是否成功
>>> import bs4

 

简单使用:

供练习的 Html Document

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>
"""
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup(html_doc)
# 知识点1: 打印漂亮的html  soup.prettify()
>>> print(soup.prettify())
<html>
 <head>
  <title>
   The Dormouse's story
  </title>

  </p>
 </body>
</html>

# 知识点2 解析获取html标签
>>> soup.title
<title>The Dormouse's story</title>
>>> soup.title.name
'title'
>>> soup.title.string
u"The Dormouse's story"
>>> soup.title.parent.name
'head'
>>> soup.p
<p class="title"><b>The Dormouse's story</b></p>
>>> soup.p['class']
['title']
>>> soup.a
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
>>> soup.find_all('a')
[<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(id='link3')
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>

总结:
>>> soup.title                    # 获取第一个title标签
>>> soup.title.name            # 获取标签名 --> title
>>> soup.title.string            # 获取标签内容
>>> soup.title.parent.name   # 获取title标签的父标签
>>> soup.p['class']             # 获取第一个p标签的class属性的值
>>> soup.find_all('a')          #获取所有a标签
>>> soup.find(id='link3')      #获取第一个id的值为link3的标签

# 知识点3  获取所有超链接
>>> for link in soup.find_all('a'):
...     print(link.get('href'))
... 
http://example.com/elsie
http://example.com/lacie
http://example.com/tillie

# 知识点4 获取所有文本
>>> print(soup.get_text())
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.

 

BeautifulSoup的四大对象  Tag, NavigableString, BeautifulSoup, and Comment.

Tag
>>> soup = BeautifulSoup('<b class="boldest">Extremely bold</b>')
>>> tag = soup.b
>>> type(tag)
<class 'bs4.element.Tag'>
>>> tag.name
'b'
>>> tag.name = 'blockquote'
>>> tag
<blockquote class="boldest">Extremely bold</blockquote>
>>> tag['class']
['boldest']
>>> tag.attrs
{'class': ['boldest']}
>>> tag['class'] = 'verybold'
>>> tag['id'] = 1
>>> tag
<blockquote class="verybold" id="1">Extremely bold</blockquote>
>>> del tag['class']
>>> del tag['id']
>>> tag
<blockquote>Extremely bold</blockquote>
>>> print(tag.get('class'))
None
>>> css_soup = BeautifulSoup('<p class="body strikeout"></p>')
>>> css_soup.p['class']
['body', 'strikeout']
>>> css_soup = BeautifulSoup('<p class="body"></p>')
>>> css_soup.p['class']
['body']
>>> id_soup = BeautifulSoup('<p id="my id"></p>')
>>> id_soup.p['id']
'my id'
>>> rel_soup = BeautifulSoup('<p>Back to the <a rel="index">homepage</a>') 
>>> rel_soup.a['rel']
['index']
>>> rel_soup.a['rel'] = ['index', 'contents']
>>> print(rel_soup.p)
<p>Back to the <a rel="index contents">homepage</a></p>

总结:
tag['class']          # 获取tag标签class属性的值
tag.attrs             # 获取tag标签所有属性
del tag['class']     # 删除tag标签的class属性

关于多值属性
>>> css_soup = BeautifulSoup('<p class="body strikeout"></p>')
>>> css_soup.p['class']
['body', 'strikeout']

>>> id_soup = BeautifulSoup('<p id="my id"></p>')
>>> id_soup.p['id']
'my id'
总结:
BeatifulSoup对于允许多值的属性 返回list, 对于不是多值的属性, 就只放回str

 

NavigableString -- 和String差不多
>>> tag.string
u'Extremely bold'
>>> type(tag.string)
<class 'bs4.element.NavigableString'>
>>> unicode_string = unicode(tag.string)
>>> unicode_string
u'Extremely bold'
>>> type(unicode_string)
<type 'unicode'>
>>> tag.string.replace_with('No loger bold')
u'Extremely bold'
>>> tag
<blockquote>No loger bold</blockquote>

总结:
1. NavigableString可以转换为unicode
2. 如果想替换NavigableString的值, 使用 replace_with()方法

 

BeautifulSoup对象  -- 整个Html Document对象
>>> soup.name
u'[document]'
>>> soup
<html><body><blockquote>No loger bold</blockquote></body></html>
>>> type(soup)
<class 'bs4.BeautifulSoup'>

 

Comments and other special strings
markup = "<b><!--Hey, buddy. Want to buy a used parser?--></b>"
soup = BeautifulSoup(markup)
comment = soup.b.string
type(comment)
# <class 'bs4.element.Comment'>

print(soup.b.prettify())
# <b>
#  <!--Hey, buddy. Want to buy a used parser?-->
# </b>

 

解析HTML

准备

html_doc = """
<html><head><title>The Dormouse's story</title></head>

<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>
"""

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc)

最简单 -- 使用标签名

>>> soup.head
<head><title>The Dormouse's story</title></head>
>>> soup.body.b
<b>The Dormouse's story</b>
>>> soup.find_all('a')
[<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>]

总结:
    1. soup.head          # 获取第一个head标签
    2. soup.body.b        # 获取第一个body下第一个b标签
    3. soup.find_all('a') # 获取所有a标签

 

.contents and .children

html_doc = '''
<html>
 <body>
  <a>
   href1
  </a>
  <a>
   href2
  </a>
 </body>
</html>
'''

# 获取子标签的方法1 -- 使用 .contents   用contents[0], contents[1]访问
>>> soup2 = BeautifulSoup(html_doc)
>>> contents = soup2.body.contents
>>> contents[0]
<a>href1</a>
>>> contents[1]
<a>href2</a>


# 方法2 -- 使用 .children   用于遍历
>>> for child in soup2.body.children:
...     print(child)
... 
<a>href1</a>
<a>href2</a>

 

 

.descendants 
.children 和 .contents只能获取直接后代  而 .descendants可以获得所有后代
>>> head_tag.contents
[<title>The Dormouse's story</title>]
>>> for child in head_tag.descendants:
...     print(child)
... 
<title>The Dormouse's story</title>
The Dormouse's story

>>> head_tag
<head><title>The Dormouse's story</title></head>
>>> 


>>> len(list(soup.children))
1
>>> len(list(soup.descendants))
25
>>> 

 

.string
>>> title_tag
<title>The Dormouse's story</title>
>>> title_tag.string
u"The Dormouse's story"


>>> print(soup.html.string)
None



总结:
    1. 如果一个标签下面没有其他标签, 那么.string就是他的值
    2. 如果一个标签下面还有子标签, 那么.string为 None


 .strings and .stripped_strings

>>> for string in soup.strings:
...     print(repr(string))
... 
u"The Dormouse's story"
u'\n'
u"The Dormouse's story"
u'\n'
u'Once upon a time there were three little sisters; and their names were\n'
u'Elsie'
u',\n'
u'Lacie'
u' and\n'
u'Tillie'
u';\nand they lived at the bottom of a well.'
u'\n'
u'...'
u'\n'

>>> for string in soup.stripped_strings:
...     print(repr(string))
... 
u"The Dormouse's story"
u"The Dormouse's story"
u'Once upon a time there were three little sisters; and their names were'
u'Elsie'
u','
u'Lacie'
u'and'
u'Tillie'
u';\nand they lived at the bottom of a well.'
u'...'

总结:
    1. .strings 获取一个标签下面所有的string
    2. .stripped_strings: 忽略 值为'\n'的string
    3. 关于 repr --> 讲object转换成 string

 

.parent

# 例子1
>>> title_tag = soup.title
>>> title_tag
<title>The Dormouse's story</title>
>>> title_tag.parent
<head><title>The Dormouse's story</title></head>

# 例子2
>>> title_tag.string.parent
<title>The Dormouse's story</title>

# 例子3
>>> html_tag = soup.html
>>> type(html_tag.parent)
<class 'bs4.BeautifulSoup'>

# 例子4
>>> print(soup.parent)
None

总结:
    1. html标签的父标签是 BeautifulSoup对象
    2. BeautifulSoup没有父标签 (根节点)


 .parents

>>> link = soup.a
>>> link
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
>>> for parent in link.parents:
...     if parent is None:
...         print(parent)
...     else:
...         print(parent.name)
... 
p
body
html

 

 

兄弟节点

预备解析HTML

>>> sibling_soup = BeautifulSoup("<a><b>text1</b><c>text2</c></b></a>")
>>> print(sibling_soup.prettify())
<html>
 <body>
  <a>
   <b>
    text1
   </b>
   <c>
    text2
   </c>
  </a>
 </body>
</html>

 

.next_sibling and .previous_sibling

# 例子1 对照上面的prettify()输出
>>> sibling_soup.b.next_sibling
<c>text2</c>
>>> sibling_soup.c.previous_sibling
<b>text1</b>


# 例子2 看prettify()的输出, 可以看到 b标签上面没有兄弟标签 c标签下面也没有兄弟标签  因此输出是None
>>> print(sibling_soup.b.previous_sibling)
None
>>> print(sibling_soup.c.next_sibling)
None


# 例子3 注意点: text1没有兄弟节点   因为它和text2不是同一个父亲!
>>> sibling_soup.b.string
u'text1'
>>> sibling_soup.b.string.next_sibling
None

# 例子4 注意点: 第一个a标签的下一个兄弟节点是 '\n', 而不是 下一个<a>标签!(如果没有排版就不会)
先看所有的a标签
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a>
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>

>>> link = soup.a
>>> link
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
>>> link.next_sibling
u',\n'
>>> link.next_sibling.next_sibling
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>

# 例子5: 验证上面的说法 -- 没有排版的话, a标签的下一个标签就不是 “\n‘
>>> html_doc = '<a href="link1"></a><a href="link2"></a>'
>>> soup2 = BeautifulSoup(html_doc)
>>> link = soup2.a
>>> link
<a href="link1"></a>
>>> link.next_sibling
<a href="link2"></a>

 

 

.next_siblings and .previous_siblings

# 例子1
>>> for sibling in soup.a.next_siblings:
...     print(repr(sibling))
... 
u',\n'
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
u' and\n'
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
u';\nand they lived at the bottom of a well.'

# 例子2
>>> for sibling in soup.find(id='link3').previous_siblings:
...     print(repr(sibling))
... 
u' and\n'
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
u',\n'
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
u'Once upon a time there were three little sisters; and their names were\n'

 

.next_element and .previous_element

预备知识:
<html><head><title>The Dormouse's story</title></head></html>
HTML解析器如何解析这段?
打开html标签, 打开head标签, 打开title标签, 保存 'The Dormouse's stroy'这个string. 关闭 title标签, 关闭 head标签, 关闭html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>

# 例子
>>> second_a_tag = soup.find('a', id='link2')
>>> second_a_tag
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
>>> second_a_tag.next_sibling
u' and\n'
>>> second_a_tag.next_element
u'Lacie'

总结:
     HTML解析器读取到<a id='link2'>处, 所以下一个元素是 Lacie, 再下一个元素是 u' and\n'  (注: 结束标签不算在这里面)

 

.next_elements and .previous_elements

>>> last_a_tag = soup.find('a', id='link3')
>>> for element in last_a_tag.next_elements:
...     print(repr(element))
... 
u'Tillie'
u';\nand they lived at the bottom of a well.'
u'\n'
<p class="story">...</p>
u'...'
u'\n'

 

 

find() and find_all()

find_all() 的简单使用  Signature: find_all(name, attrs, recursive, text, limit, **kwargs)

# 例子1. 搜索所有title标签
>>> soup.find_all('title')
[<title>The Dormouse's story</title>]

# 例子2. 搜索所有class为title 的 p标签
>>> soup.find_all('p', 'title')
[<p class="title"><b>The Dormouse's story</b></p>]

# 例子3. 搜索所有a标签
>>> soup.find_all('a')
[<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>]

# 例子4. 搜索所有 id为link2的标签
>>> soup.find_all(id='link2')
[<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]

# 例子5. 搜索text中带有 sisters的标签
>>> import re
>>> soup.find(text=re.compile('sisters'))
u'Once upon a time there were three little sisters; and their names were\n'

 

使用函数作为参数

>>> def has_class_but_no_id(tag):
...     return tag.has_attr('class') and not tag.has_attr('id')
... 
>>> soup.find_all(has_class_but_no_id)
[<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>]

 

 

find_all()的进阶使用

# 例子1. 搜索所有有id属性的标签
>>> soup.find_all(id=True)
[<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>]

# 例子2. 搜索href中带有 elsie 并且 id的值为link1的标签
>>> soup.find_all(href=re.compile('elsie'), id='link1')
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]

# 例子3. 对于特殊的属性名 
>>> data_soup = BeautifulSoup('<div data-foo="value">foo!</div>')
>>> data_soup.find_all(data-foo='value')
  File "<stdin>", line 1
SyntaxError: keyword can't be an expression

这样是不行的
使用 attrs={}
>>> data_soup.find_all(attrs={'data-foo': 'value'})
[<div data-foo="value">foo!</div>]

 

 

Searching by CSS class

注意: class是Python的保留字, 所以使用的时候, 用 class_替代 (class的最后躲一下划线)
# 例子1 搜索所有class为sister的a标签
>>> soup.find_all('a', class_='sister')
[<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>]

# 例子2 搜索class中带 itl的标签
>>> soup.find_all(class_=re.compile('itl'))
[<p class="title"><b>The Dormouse's story</b></p>]

# 例子3 使用函数作为参数 如果返回结果为True, 则matches这个标签
>>> def has_six_characters(css_class):
...     return css_class is not None and len(css_class) == 6
... 
>>> soup.find_all(class_=has_six_characters)
[<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>]

# 例子4 一个标签可以有多个值的属性 比如 class
>>> css_soup = BeautifulSoup('<p class="body strikeout"></p>')
>>> css_soup.find_all('p', class_='strikeout')
[<p class="body strikeout"></p>]
>>> css_soup.find_all('p', class_='body')
[<p class="body strikeout"></p>]

注: 对于有多个值的属性, 我们可以通过其中的一个值搜索到它们

# 例子5 不过 如果一起搜索  顺序不能颠倒
>>> css_soup.find_all('p', class_='strikeout body')
[]

# 例子6 我们可以通过CSS selector选择我们要的标签
>>> css_soup.select('p.strikeout.body')
[<p class="body strikeout"></p>]

# 例子7 对于不支持 class_的早期版本, 使用 attrs={}
>>> soup.find_all('a', attrs={'class': 'sister'})
[<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>]

 

 

The text argument

With text you can search for strings instead of tags. As with name and the keyword arguments, you can pass in a string, a regular expression, a list, a function, or the value True. Here are some examples:

# 例子1. 使用string作为参数
>>> soup.find_all(text='Elsie')
[u'Elsie']

# 例子2. 使用List作为参数
>>> soup.find_all(text=['Tillie', 'Elsie', 'Lacie'])
[u'Elsie', u'Lacie', u'Tillie']

# 例子3. 使用正则表达式作为参数
>>> soup.find_all(text=re.compile('Dormouse'))
[u"The Dormouse's story", u"The Dormouse's story"]

# 例子4. 使用函数作为参数
>>> def is_the_only_string_within_a_tag(s):
...     return (s == s.parent.string)
... 
>>> soup.find_all(text=is_the_only_string_within_a_tag)
[u"The Dormouse's story", u"The Dormouse's story", u'Elsie', u'Lacie', u'Tillie', u'...']

# 例子5. 联合其他参数一起搜索
>>> soup.find_all('a', text='Elsie')
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]

 

 

The limit arguement

# 如果HTML文件很多, 解析速度就慢 这个时候 可以指定BeautifulSoup搜索的个数

# 例子: 只搜索符合条件的前两个结果
>>> soup.find_all('a', limit=2)
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]

 

 The recursive argument

解析的HTML
<html>
 <head>
  <title>
   The Dormouse's story
  </title>
 </head>

# 例子:title是head下面的, 而不是html下面的(直接) 如果关闭递归, 就找不到title了。 也就是说, 开启递归, 不仅搜索儿子, 还搜索孙子。 如果关闭递归, 就只搜索儿子
>>> soup.html.find_all('title')
[<title>The Dormouse's story</title>]
>>> soup.html.find_all('title', recursive=False)
[]

 

 

Calling a tag is like calling find_all()

tag标签也可以使用find_all(), 像BeautifulSoup对象一样

# 下面这两个是相等的
soup.title.find_all(text=True)
soup.title(text=True)

 

find()

Signature: find(name, attrs, recursive, text, **kwargs)

find()的简单使用

# 例子1  这两个是等价 不过find_all返回的是所有结果中的前1个结果  而 find只是返回一个结果   find_all会搜索所有的文档 速度较慢 
>>> soup.find_all('title', limit=1)
[<title>The Dormouse's story</title>]
>>> soup.find('title')
<title>The Dormouse's story</title>


# 例子2 如果搜索不到相关的标签, find返回的是None  而find_all返回的是 list
>>> print(soup.find('nosuchtag'))
None
>>> print(soup.find_all('nosuchtag'))
[]

# 例子3  这两个是相等的
>>> soup.head.title
<title>The Dormouse's story</title>
>>> soup.find('head').find('title')
<title>The Dormouse's story</title>

 

 

find_parents() and find_parent()

Signature: find_parents(name, attrs, text, limit, **kwargs)

Signature: find_parent(name, attrs, text, **kwargs)

>>> a_string = soup.find(text='Lacie')
>>> a_string
u'Lacie'
>>> a_string.find_parents('a')
[<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
>>> a_string.find_parent('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>
>>> a_string.find_parents('p', class_='title')
[]

 

find_next_silbings() and find_next_sibling()

>>> first_link = soup.a
>>> first_link
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
>>> first_link.find_next_siblings('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>]
>>> first_stroy_paragraph = soup.find('p', 'story')
>>> first_stroy_paragraph.find_next_sibling('p')
<p class="story">...</p>

 

 

find_previous_siblings() and find_previous_sibling()

Signature: find_previous_siblings(name, attrs, text, limit, **kwargs)

Signature: find_previous_sibling(name, attrs, text, **kwargs)

>>> last_link = soup.find('a', id='link3')
>>> last_link
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
>>> last_link.find_previous_siblings('a')
[<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
>>> first_story_paragraph = soup.find('p', 'story')
>>> first_story_paragraph.find_previous_sibling('p')
<p class="title"><b>The Dormouse's story</b></p>

 

find_all_next() and find_next()

Signature: find_all_next(name, attrs, text, limit, **kwargs)

Signature: find_next(name, attrs, text, **kwargs)

>>> first_link = soup.a
>>> first_link
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
>>> first_link.find_all_next(text=True)
[u'Elsie', u',\n', u'Lacie', u' and\n', u'Tillie', u';\nand they lived at the bottom of a well.', u'\n', u'...', u'\n']
>>> first_link.find_next('p')
<p class="story">...</p>

 

 

find_all_previous() and find_previous()

>>> first_link = soup.a
>>> first_link
<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
>>> first_link.find_all_previous('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="title"><b>The Dormouse's story</b></p>]
>>> first_link.find_previous('title')
<title>The Dormouse's story</title>

 

 

CSS selector   略

对于HTML的修改删除添加   略

 

Beautiful Soup Documentation

http://www.crummy.com/software/BeautifulSoup/bs4/doc

posted on 2014-08-28 12:24 sw90 阅读(...) 评论(...) 编辑 收藏

导航