Python 模拟登录及表单提交

01

#
-*- coding:utf-8 -*-

02

import

re

03

import

urllib

04

import

urllib2

05

import

cookielib

06

07

#获取CSDN博客标题和正文

08

url

=

"http://blog.csdn.net/[username]/archive/2010/07/05/5712850.aspx"

09

sock

=

urllib.urlopen(url)

10

html

=

sock.read()

11

sock.close()

12

content

=

re.findall(

'(?<=blogstory">).*(?=<p
class="right artical)'

,
html,re.S)

13

content

=

re.findall(

'<script.*>.*</script>(.*)'

,
content[

0

],
re.S)

14

title

=

re.findall(

'(?<=<title>)(.*)-.*
- CSDN.*(?=</title>)'

,
html,re.S)

15

#根据上文获取内容新建表单值

16

blog

=

{

'spBlogTitle'

:
title[

0

].decode(

'utf-8'

).encode(

'gbk'

),

#百度博客标题

17

'spBlogText'

:
content[

0

].decode(

'utf-8'

).encode(

'gbk'

),

#百度博客内容

18

'ct'

:

"1"

,

19

'cm'

:

"1"

}

20

del

content

21

del

title

22

23

#模拟登录

24

cj

=

cookielib.CookieJar()

25

#用户名和密码

26

post_data

=

urllib.urlencode({

'username'

:

'[username]'

,

'password'

:

'[password]'

,

'pwd'

:

'1'

})

27

#登录路径

28

path

=

'https://passport.baidu.com/?login'

29

opener

=

urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))

30

opener.addheaders

=

[(

'User-agent'

,

'Opera/9.23'

)]

31

urllib2.install_opener(opener)

32

req

=

urllib2.Request(path,
post_data)

33

conn

=

urllib2.urlopen(req)

34

35

#获取百度发布博客的认证令牌

36

bd

=

urllib2.urlopen(urllib2.Request(

'http://hi.baidu.com/[username]/creat/blog'

)).read()

37

bd

=

re.findall(

'(?<=bdstoken\"
value=\").*(?=ct)'

,
bd,re.S) 

38

blog[

'bdstoken'

]

=

bd[

0

][:

32

]

39

#设置分类名

40

blog[

'spBlogCatName'

]

=

'php'

41

#比较表单发布博客

42

req2

=

urllib2.Request(

'http://hi.baidu.com/[username]/commit'

,
urllib.urlencode(blog))

43

44

#查看表单提交后返回内容

45

print

urllib2.urlopen(req2).read()

46

47

#请将[username]/[password]替换为您的真实用户名和密码