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
|
#!/usr/bin/env python
"""
Copyright (c) 2006-2019 sqlmap developers (http://sqlmap.org/)
See the file 'LICENSE' for copying permission
"""
from __future__ import print_function
import cookielib
import re
import socket
import sys
import urllib
import urllib2
import ConfigParser
from operator import itemgetter
TIMEOUT = 10
CONFIG_FILE = 'sqlharvest.cfg'
TABLES_FILE = 'tables.txt'
USER_AGENT = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; AskTB5.3)'
SEARCH_URL = 'http://www.google.com/m?source=mobileproducts&dc=gorganic'
MAX_FILE_SIZE = 2 * 1024 * 1024 # if a result (.sql) file for downloading is more than 2MB in size just skip it
QUERY = 'CREATE TABLE ext:sql'
REGEX_URLS = r';u=([^"]+?)&q='
REGEX_RESULT = r'(?i)CREATE TABLE\s*(/\*.*\*/)?\s*(IF NOT EXISTS)?\s*(?P<result>[^\(;]+)'
def main():
tables = dict()
cookies = cookielib.CookieJar()
cookie_processor = urllib2.HTTPCookieProcessor(cookies)
opener = urllib2.build_opener(cookie_processor)
opener.addheaders = [("User-Agent", USER_AGENT)]
conn = opener.open(SEARCH_URL)
page = conn.read() # set initial cookie values
config = ConfigParser.ConfigParser()
config.read(CONFIG_FILE)
if not config.has_section("options"):
config.add_section("options")
if not config.has_option("options", "index"):
config.set("options", "index", "0")
i = int(config.get("options", "index"))
try:
with open(TABLES_FILE, 'r') as f:
for line in f.xreadlines():
if len(line) > 0 and ',' in line:
temp = line.split(',')
tables[temp[0]] = int(temp[1])
except:
pass
socket.setdefaulttimeout(TIMEOUT)
files, old_files = None, None
try:
while True:
abort = False
old_files = files
files = []
try:
conn = opener.open("%s&q=%s&start=%d&sa=N" % (SEARCH_URL, QUERY.replace(' ', '+'), i * 10))
page = conn.read()
for match in re.finditer(REGEX_URLS, page):
files.append(urllib.unquote(match.group(1)))
if len(files) >= 10:
break
abort = (files == old_files)
except KeyboardInterrupt:
raise
except Exception as ex:
print(ex)
if abort:
break
sys.stdout.write("\n---------------\n")
sys.stdout.write("Result page #%d\n" % (i + 1))
sys.stdout.write("---------------\n")
for sqlfile in files:
print(sqlfile)
try:
req = urllib2.Request(sqlfile)
response = urllib2.urlopen(req)
if "Content-Length" in response.headers:
if int(response.headers.get("Content-Length")) > MAX_FILE_SIZE:
continue
page = response.read()
found = False
counter = 0
for match in re.finditer(REGEX_RESULT, page):
counter += 1
table = match.group("result").strip().strip("`\"'").replace('"."', ".").replace("].[", ".").strip('[]')
if table and not any(_ in table for _ in ('>', '<', '--', ' ')):
found = True
sys.stdout.write('*')
if table in tables:
tables[table] += 1
else:
tables[table] = 1
if found:
sys.stdout.write("\n")
except KeyboardInterrupt:
raise
except Exception as ex:
print(ex)
else:
i += 1
except KeyboardInterrupt:
pass
finally:
with open(TABLES_FILE, 'w+') as f:
tables = sorted(tables.items(), key=itemgetter(1), reverse=True)
for table, count in tables:
f.write("%s,%d\n" % (table, count))
config.set("options", "index", str(i + 1))
with open(CONFIG_FILE, 'w+') as f:
config.write(f)
if __name__ == "__main__":
main()
|
