forked from w3h/Beebeeto2
/
update.py
198 lines (156 loc) · 4.79 KB
/
update.py
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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
#!/usr/bin/env python
#coding=utf-8
import urllib
import urllib2
import os
import sys
import socket
from utils.BeautifulSoup import BeautifulSoup
import re
import time
import platform
g_cookie = 'csrftoken=jLySq58kvH7DW23sxIUwkVPpsOMStUdX; sessionid=8g49ri43mn8fgmic41gd1nt9x1ati6v1; CNZZDATA1253290531=1433061732-1414286034-%7C1414824533'
g_readme_head = ''' <html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<style type="text/css">
<!--
body { FONT-FAMILY: verdana; font-size: 10pt; color: #000000}
-->
</style>
<title>POC LIST</title>
</head>
<body bgcolor="#FFFFFF">
'''
def isWindow():
return "Window" in platform.platform()
def format_dos(info):
if not isWindow():
return info
try:
return str(info).decode("utf8").encode("gbk")
except:
return info
def strip_tags(html):
html = html.replace(' ', ' ')
html = html.replace('>', '>')
html = html.replace('<', '<')
html = html.replace('"', '"')
html = html.replace(''', "'")
html = html.replace('&', "&")
html = ''.join(html)
html = html[html.find('#!/'):]
return format_dos(html)
def getHtml(url):
info= ''
for i in range(3):
try:
req = urllib2.Request(url)
req.add_header('Cookie', g_cookie)
info = urllib2.urlopen(req).read()
break
except Exception,e:
time.sleep(i+1)
continue
return info
def getPoc(poc):
info = getHtml("http://beebeeto.com/pdb/" + poc + "/")
if '' == info:
return ''
if '<img src="/static/img/test.jpg"' in info:
return ''
if "立即查看" in info:
return ''
try:
bt = BeautifulSoup(info)
ret = bt.find('pre', {'class' : "brush: python;"})
ret = ret.renderContents()
if ret:
return strip_tags(ret)
else:
return ''
except:
return ''
def makeReadme(name, info):
ret = re.findall("'name'.*", info)
if ret == '':
return
info = ret[0].replace("'name'", "")
info = info.replace(":", "")
info = info.replace("'", "")
info = info.replace(",", "")
info = info.strip()
if not os.path.exists("./Beebeeto-framework/demo/readme.html"):
with open("./Beebeeto-framework/demo/readme.html", 'w') as fp:
fp.write(g_readme_head)
info = "[<a href=%s>%s<a>]%s\r\n<br>" % ("http://beebeeto.com/pdb/"+name, name, info)
with open("./Beebeeto-framework/demo/readme.html", 'a') as fp: fp.write(info)
def savePoc(name, info):
if '' == info:
return
name = name.replace("-", "_")
sname = "./Beebeeto-framework/demo/" + name + ".py"
if os.path.exists(sname):
return
with open(sname, "wb") as fp:
fp.write(str(info))
makeReadme(name, info)
def get_onepage_poclist(page):
info = getHtml("http://beebeeto.com/pdb" + '/?page=' + str(page))
if '' == info:
return ''
bt = BeautifulSoup(info)
end = bt.find('a', {'style' : "font-size: 20px;font-weight: bold; border-bottom: 3px solid #777777;"})
if '1' == end.renderContents() and page != 1:
return ''
ret = bt.find('div', {'class' : 'mainlist'})
ret = ret.renderContents()
if ret == "":
return ""
retlist = []
rets = re.findall('<a href=.*?>', ret)
for one in rets:
if "poc-" in one:
one = one.replace('<a href="', "")
one = one.replace('">', "")
one = one.strip()
retlist.append(one)
return retlist
def main():
sum = 0
socket.setdefaulttimeout(10)
info = getHtml("http://beebeeto.com/")
if "注册" in info and "登录" in info:
print "[ERR] The cookie is error!"
return
readme = ""
if os.path.exists("./Beebeeto-framework/demo/readme.html"):
with open("./Beebeeto-framework/demo/readme.html", 'r') as fp: readme = fp.read()
for i in range(1,1000):
pocs = get_onepage_poclist(i)
if "" == pocs:
break
for t in pocs:
name = t.replace("-", "_")
if name in readme:
#print "[*] Get Poc -> %s " % t
continue
info = getPoc(t)
if info == "":
print "[*] Get Poc -> %s failed" % t
continue
print "[+] Get Poc -> %s " % t
savePoc(t, info)
sum = sum + 1
#return
print "[+] The total number of POC is %d " % sum
if __name__ == "__main__":
if len(sys.argv) < 2:
print "usage: update.py cookie"
sys.exit()
else:
g_cookie = sys.argv[1]
main()
#info = getPoc("poc-2014-0115")
#savePoc('poc-2014-0115', info)
#open('txt.html', 'w').write(str(info))