OLD | NEW |
1 # coding: utf-8 | 1 # coding: utf-8 |
2 | 2 |
3 # This file is part of the Adblock Plus web scripts, | 3 # This file is part of the Adblock Plus web scripts, |
4 # Copyright (C) 2006-2016 Eyeo GmbH | 4 # Copyright (C) 2006-2016 Eyeo GmbH |
5 # | 5 # |
6 # Adblock Plus is free software: you can redistribute it and/or modify | 6 # Adblock Plus is free software: you can redistribute it and/or modify |
7 # it under the terms of the GNU General Public License version 3 as | 7 # it under the terms of the GNU General Public License version 3 as |
8 # published by the Free Software Foundation. | 8 # published by the Free Software Foundation. |
9 # | 9 # |
10 # Adblock Plus is distributed in the hope that it will be useful, | 10 # Adblock Plus is distributed in the hope that it will be useful, |
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 11 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
13 # GNU General Public License for more details. | 13 # GNU General Public License for more details. |
14 # | 14 # |
15 # You should have received a copy of the GNU General Public License | 15 # You should have received a copy of the GNU General Public License |
16 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. | 16 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. |
17 | 17 |
18 import os, subprocess, codecs, urllib2, zipfile, tempfile, shutil, sys | 18 import os, subprocess, codecs, urllib2, zipfile, tempfile, shutil, sys |
19 import ConfigParser | |
20 from StringIO import StringIO | 19 from StringIO import StringIO |
21 from sitescripts.utils import get_config | 20 from sitescripts.utils import get_config |
22 | 21 |
23 | 22 |
24 FILTERLIST_HEADER = '''[Adblock Plus 1.1] | 23 FILTERLIST_HEADER = '''[Adblock Plus 1.1] |
25 ! This is a list of malware domains generated from malwaredomains.com data. | 24 ! This is a list of malware domains generated from malwaredomains.com data. |
26 ! Homepage: http://malwaredomains.com/?page_id=2 | 25 ! Homepage: http://malwaredomains.com/?page_id=2 |
27 ! Last modified: %timestamp% | 26 ! Last modified: %timestamp% |
28 ! Expires: 1d | 27 ! Expires: 1d |
29 !''' | 28 !''' |
30 | 29 |
31 DEFAULT_MIRRORS_LIST = [ | |
32 'http://mirror3.malwaredomains.com', | |
33 'http://mirror1.malwaredomains.com', | |
34 'http://mirror2.malwaredomains.com' | |
35 ] | |
36 | |
37 MALWAREDOMAINS_PATH = '/files/justdomains.zip' | 30 MALWAREDOMAINS_PATH = '/files/justdomains.zip' |
38 | 31 |
39 | 32 |
40 def try_mirror(mirror): | 33 def try_mirror(mirror): |
41 try: | 34 try: |
42 response = urllib2.urlopen(mirror + MALWAREDOMAINS_PATH) | 35 response = urllib2.urlopen(mirror + MALWAREDOMAINS_PATH) |
43 return response.read() | 36 return response.read() |
44 except urllib2.HTTPError: | 37 except urllib2.HTTPError: |
45 return None | 38 return None |
46 | 39 |
47 | 40 |
48 if __name__ == '__main__': | 41 if __name__ == '__main__': |
49 config = get_config() | 42 config = get_config() |
50 repository = config.get('subscriptionDownloads', 'malwaredomains_repository') | 43 section = 'subscriptionDownloads' |
51 try: | 44 repository = config.get(section, 'malwaredomains_repository') |
52 mirrors = config.get('subscriptionDownloads', 'malwaredomains_mirrors') | 45 mirrors = config.get(section, 'malwaredomains_mirrors').split() |
53 mirrors_list = mirrors.split() | |
54 except ConfigParser.NoOptionError: | |
55 mirrors_list = DEFAULT_MIRRORS_LIST | |
56 | 46 |
57 tempdir = tempfile.mkdtemp(prefix='malwaredomains') | 47 tempdir = tempfile.mkdtemp(prefix='malwaredomains') |
58 try: | 48 try: |
59 subprocess.check_call(['hg', '-q', 'clone', '-U', repository, tempdir]) | 49 subprocess.check_call(['hg', '-q', 'clone', '-U', repository, tempdir]) |
60 subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default']) | 50 subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default']) |
61 | 51 |
62 path = os.path.join(tempdir, 'malwaredomains_full.txt') | 52 path = os.path.join(tempdir, 'malwaredomains_full.txt') |
63 file = codecs.open(path, 'wb', encoding='utf-8') | 53 file = codecs.open(path, 'wb', encoding='utf-8') |
64 | 54 |
65 print >>file, FILTERLIST_HEADER | 55 print >>file, FILTERLIST_HEADER |
66 | 56 |
67 for mirror in mirrors_list: | 57 for mirror in mirrors: |
68 data = try_mirror(mirror) | 58 data = try_mirror(mirror) |
69 if data is not None: | 59 if data is not None: |
70 break | 60 break |
71 else: | 61 else: |
72 sys.exit('Unable to fetch malware domains list.') | 62 sys.exit('Unable to fetch malware domains list.') |
73 | 63 |
74 zip = zipfile.ZipFile(StringIO(data), 'r') | 64 zip = zipfile.ZipFile(StringIO(data), 'r') |
75 info = zip.infolist()[0] | 65 info = zip.infolist()[0] |
76 for line in str(zip.read(info.filename)).splitlines(): | 66 for line in str(zip.read(info.filename)).splitlines(): |
77 domain = line.strip() | 67 domain = line.strip() |
78 if not domain: | 68 if not domain: |
79 continue | 69 continue |
80 | 70 |
81 print >>file, '||%s^' % domain.decode('idna') | 71 print >>file, '||%s^' % domain.decode('idna') |
82 file.close(); | 72 file.close(); |
83 | 73 |
84 if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '': | 74 if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '': |
85 subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-u', 'h
gbot', '-m', 'Updated malwaredomains.com data']) | 75 subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-u', 'h
gbot', '-m', 'Updated malwaredomains.com data']) |
86 subprocess.check_call(['hg', '-q', 'push', '-R', tempdir]) | 76 subprocess.check_call(['hg', '-q', 'push', '-R', tempdir]) |
87 finally: | 77 finally: |
88 shutil.rmtree(tempdir, ignore_errors=True) | 78 shutil.rmtree(tempdir, ignore_errors=True) |
OLD | NEW |