# coding=utf-8
import urllib
from bs4 import BeautifulSoup

url ='http://www.baidu.com/s'
values ={'wd':'網(wǎng)球'}
encoded_param = urllib.urlencode(values)
full_url = url +'?'+ encoded_param
response = urllib.urlopen(full_url)
soup =BeautifulSoup(response)
alinks = soup.find_all('a')

上面可以抓取百度搜出來結(jié)果是網(wǎng)球的記錄。

beautifulSoup內(nèi)置了很多非常有用的方法。

幾個(gè)比較好用的特性：

構(gòu)造一個(gè)node元素

復(fù)制代碼代碼如下:

soup = BeautifulSoup('<b class="boldest">Extremely bold</b>')

tag = soup.b

type(tag)

# <class 'bs4.element.Tag'>

屬性可以使用attr拿到，結(jié)果是字典

復(fù)制代碼代碼如下:

tag.attrs

# {u'class': u'boldest'}

或者直接tag.class取屬性也可。

也可以自由操作屬性

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>

tag['class']
# KeyError: 'class'
print(tag.get('class'))
# None

還可以隨便操作，查找dom元素，比如下面的例子

1.構(gòu)建一份文檔

html_doc = """
&lt;html&gt;&lt;head&gt;&lt;title&gt;The Dormouse's story&lt;/title&gt;&lt;/head&gt;

&lt;p&gt;&lt;b&gt;The Dormouse's story&lt;/b&gt;&lt;/p&gt;

&lt;p&gt;Once upon a time there were three little sisters; and their names were
&lt;a  id="link1"&gt;Elsie&lt;/a&gt;,
&lt;a  id="link2"&gt;Lacie&lt;/a&gt; and
&lt;a  id="link3"&gt;Tillie&lt;/a&gt;;
and they lived at the bottom of a well.&lt;/p&gt;

&lt;p&gt;...&lt;/p&gt;
"""

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc)

2.各種搞

soup.head
# <head><title>The Dormouse's story</title></head>
soup.title
# <title>The Dormouse's story</title>
soup.body.b
# <b>The Dormouse's story</b>
soup.a
# <a class="sister"  id="link1">Elsie</a>
soup.find_all('a')
# [<a class="sister"  id="link1">Elsie</a>,
# <a class="sister"  id="link2">Lacie</a>,
# <a class="sister"  id="link3">Tillie</a>]
head_tag = soup.head
head_tag
# <head><title>The Dormouse's story</title></head>

head_tag.contents
[<title>The Dormouse's story</title>]

title_tag = head_tag.contents[0]
title_tag
# <title>The Dormouse's story</title>
title_tag.contents
# [u'The Dormouse's story']
len(soup.contents)
# 1
soup.contents[0].name
# u'html'
text = title_tag.contents[0]
text.contents

for child in title_tag.children:
  print(child)
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

len(list(soup.children))
# 1
len(list(soup.descendants))
# 25
title_tag.string
# u'The Dormouse's story'

您可能感興趣的文章: