clean-sina-weibo/clean_sina_weibo_httplib.py at master · ifduyue/clean-sina-weibo · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
#coding: utf8

import re
import time
from urlparse import parse_qsl, urljoin

from urlfetch import *

URL_LOGIN = 'http://3g.sina.com.cn/prog/wapsite/sso/login_submit.php'
TIME_SLEEP = 1 # sec

class Sina(object):

    def __init__(self, username, password):
        self.cookies = None
        self.username = username
        self.password = password

    def login(self):
        response = fetch(URL_LOGIN)
        data = response.body

        vk = re.search(r'''name="vk"\s+?value="(.*?)"''', data).group(1)
        pname = re.search(r'''name="password_(\d+)"''', data).group(1)

        post = {
            'mobile': self.username,
            'password_'+pname: self.password,
            #'capId': capid,
            'vk': vk,
            'remember': 'on',
            'submit': '1'
        }
        response = fetch(URL_LOGIN, data=post)
        data = response.body
        captcha = re.search(r'''captcha/show.php\?cpt=(\w+)''', data)
        if captcha:
            url = '''http://weibo.cn/interface/f/ttt/captcha/show.php?cpt=''' + captcha.group(1)
            print url
            captcha = raw_input("open the url and input the captcha:")
            vk = re.search(r'''name="vk"\s+?value="(.*?)"''', data).group(1)
            pname = re.search(r'''name="password_(\d+)"''', data).group(1)
            capid = re.search(r'''name="capId"\s+?value="(.*?)"''', data).group(1)
            post = {
                'mobile': self.username,
                'password_'+pname: self.password,
                'capId': capid,
                'vk': vk,
                'remember': 'on',
                'submit': '1',
                'code': captcha.strip(),
            }
            response = fetch(URL_LOGIN, data=post)
        self.cookies = response.cookiestring
        print self.cookies
        response = fetch(
            'http://weibo.cn/',
            headers = {'Cookie': self.cookies, 'User-Agent': 'Android'},
        )
        self.uid = re.search(r'''uid=(\d+)''', response.body).group(1)
        print self.uid
        return self.cookies

    def del_tweets(self):
        while True:
            time.sleep(2 * TIME_SLEEP)
            response = fetch(
                'http://weibo.cn/%s/profile' % self.uid,
                headers={'Cookie': self.cookies}
            )
            data = re.findall(r'href="http://weibo.cn/mblog/del\?(.*?)"', response.body)
            if not data:
                break
            for i in data:
                time.sleep(TIME_SLEEP)
                j = parse_qsl(i)
                qs = dict(j)
                qs['act'] = 'delc'
                qs = '&'.join(['='.join(k) for k in qs.items()])
                url = 'http://weibo.cn/mblog/del?' + qs
                try:
                    fetch(
                        url,
                        headers = {'Cookie': self.cookies}
                    )
                    print url
                except:pass

    def unfollow(self):
        while True:
            time.sleep(2 * TIME_SLEEP)
            response = fetch(
                'http://weibo.cn/%s/follow' % self.uid,
                headers={'Cookie': self.cookies}
            )

            data = re.findall(r'href="/attention/del\?(.*?)"', response.body)
            if not data:
                break
            for i in data:
                time.sleep(TIME_SLEEP)
                j = parse_qsl(i)
                qs = dict(j)
                qs['act'] = 'delc'
                qs = '&'.join(['='.join(k) for k in qs.items()])
                url = 'http://weibo.cn/attention/del?' + qs
                try:
                    fetch(
                        url,
                        headers = {'Cookie': self.cookies}
                    )
                    print url
                except:pass

    def remove_followers(self, black=False):
        while True:
            time.sleep(2 * TIME_SLEEP)
            response = fetch(
                'http://weibo.cn/%s/fans' % self.uid,
                headers={'Cookie': self.cookies}
            )

            data = re.findall(r'href="/attention/remove\?(.*?)"', response.body)
            if not data:
                break
            for i in data:
                time.sleep(TIME_SLEEP)
                j = parse_qsl(i)
                qs = dict(j)
                qs['act'] = 'removec'
                if black:
                    qs['black'] = 1
                qs = '&'.join(['='.join(k) for k in qs.items()])
                url = 'http://weibo.cn/attention/remove?' + qs
                try:
                    fetch(
                        url,
                        headers = {'Cookie': self.cookies}
                    )
                    print url
                except:pass

if __name__ == '__main__':
    def sigint():
        def _sigint(a,b):
            print a, b
            import os, sys
            os.kill(0, signal.SIGTERM)
            sys.exit()
        import signal
        signal.signal(signal.SIGINT, _sigint)
    import sys
    sigint()
    username, password = sys.argv[1:]
    sina = Sina(username, password)
    sina.login()
    sina.del_tweets()
    #sina.unfollow()
    #sina.remove_followers()