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
|
#!/usr/bin/env python
"""
This file is part of Pyew
Copyright (C) 2009, 2010 Joxean Koret
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
"""
import re
import sys
import urllib
def toUnicode(buf):
ret = ""
for c in buf:
ret += c + "\x00"
return ret
def urlExtract(pyew, doprint=True):
""" Search URLs in the current document """
urlfinders = [
re.compile("((http|ftp|mailto|telnet|ssh)(s){0,1}\:\/\/[\w|\/|\.|\#|\?|\&|\=|\-|\%]+)+", re.IGNORECASE | re.MULTILINE)
]
moffset = pyew.offset
pyew.offset = 0
pyew.seek(0)
buf = pyew.f.read()
ret = []
for x in urlfinders:
ret += doFind(x, buf)
if doprint and len(ret) > 0:
print "ASCII URLs"
print
for url in ret:
print url
buf = buf.replace("\x00", "")
uniret = []
for x in urlfinders:
uniret += doFind(x, buf)
if doprint and len(uniret) > 0:
i = 0
for url in ret:
if url not in ret:
if i == 0:
print "UNICODE URLs"
print
i += 1
print url
tmp = {}
for x in ret:
tmp[x] = x
ret = tmp.values()
pyew.seek(moffset)
return ret
def doFind(x, buf):
ret = []
for l in x.findall(buf, re.IGNORECASE | re.MULTILINE):
for url in l:
if len(url) > 8 and url not in ret:
ret.append(url)
return ret
def checkUrls(pyew, doprint=True):
""" Check URLs of the current file """
oks = []
urls = urlExtract(pyew, doprint=False)
if len(urls) == 0:
print "***No URLs found"
return
for url in urls:
try:
if doprint:
sys.stdout.write("Checking %s ... " % url)
sys.stdout.flush()
r = urllib.urlopen(url)
if doprint:
sys.stdout.write("OK\n")
sys.stdout.flush()
oks.append(url)
except KeyboardInterrupt:
print "Aborted"
break
except:
sys.stdout.write("DOWN\n")
sys.stdout.flush()
return oks
def checkBad(pyew, doprint=True):
""" Check for known bad URLs """
returls = []
url = "http://www.malware.com.br/cgi/submit?action=list_adblock"
try:
l = urllib.urlopen(url).readlines()
except:
print "***Error fetching URL list from www.malware.com.br:", sys.exc_info()[1]
return
urls = urlExtract(pyew, doprint=False)
if len(urls) == 0:
print "***No URLs found"
return
for url in urls:
for badurl in l:
if badurl.startswith("["):
continue
badurl = badurl.strip("\n").strip("\r")
if url.lower().find(badurl) > -1:
if doprint:
print "***Found bad URL: %s" % url
returls.append(url)
break
return returls
functions = {"url":urlExtract, "chkurl":checkUrls, "chkbad":checkBad}
|
