| Left: | ||
| Right: |
| LEFT | RIGHT |
|---|---|
| 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, |
| (...skipping 19 matching lines...) Expand all Loading... | |
| 30 | 30 |
| 31 DEFAULT_MIRRORS_LIST = [ | 31 DEFAULT_MIRRORS_LIST = [ |
| 32 'http://mirror3.malwaredomains.com', | 32 'http://mirror3.malwaredomains.com', |
| 33 'http://mirror1.malwaredomains.com', | 33 'http://mirror1.malwaredomains.com', |
| 34 'http://mirror2.malwaredomains.com' | 34 'http://mirror2.malwaredomains.com' |
| 35 ] | 35 ] |
| 36 | 36 |
| 37 MALWAREDOMAINS_PATH = '/files/justdomains.zip' | 37 MALWAREDOMAINS_PATH = '/files/justdomains.zip' |
| 38 | 38 |
| 39 | 39 |
| 40 def try_mirror(mirror, path): | 40 def try_mirror(mirror): |
| 41 try: | 41 try: |
| 42 response = urllib2.urlopen(mirror + path) | 42 response = urllib2.urlopen(mirror + MALWAREDOMAINS_PATH) |
| 43 return response.read() | 43 return response.read() |
| 44 except urllib2.HTTPError: | 44 except urllib2.HTTPError: |
| 45 return None | 45 return None |
| 46 | 46 |
| 47 | 47 |
| 48 if __name__ == '__main__': | 48 if __name__ == '__main__': |
| 49 config = get_config() | 49 config = get_config() |
| 50 repository = config.get('subscriptionDownloads', 'malwaredomains_repository') | 50 repository = config.get('subscriptionDownloads', 'malwaredomains_repository') |
| 51 try: | 51 try: |
| 52 mirrors = config.get('subscriptionDownloads', 'malwaredomains_mirrors') | 52 mirrors = config.get('subscriptionDownloads', 'malwaredomains_mirrors') |
| 53 mirrors_list = filter(None, [mirror.strip() for mirror in mirrors.split()]) | 53 mirrors_list = mirrors.split() |
| 54 except ConfigParser.NoOptionError: | 54 except ConfigParser.NoOptionError: |
| 55 mirrors_list = DEFAULT_MIRRORS_LIST | 55 mirrors_list = DEFAULT_MIRRORS_LIST |
| 56 | 56 |
| 57 tempdir = tempfile.mkdtemp(prefix='malwaredomains') | 57 tempdir = tempfile.mkdtemp(prefix='malwaredomains') |
| 58 try: | 58 try: |
| 59 subprocess.check_call(['hg', '-q', 'clone', '-U', repository, tempdir]) | 59 subprocess.check_call(['hg', '-q', 'clone', '-U', repository, tempdir]) |
| 60 subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default']) | 60 subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default']) |
| 61 | 61 |
| 62 path = os.path.join(tempdir, 'malwaredomains_full.txt') | 62 path = os.path.join(tempdir, 'malwaredomains_full.txt') |
| 63 file = codecs.open(path, 'wb', encoding='utf-8') | 63 file = codecs.open(path, 'wb', encoding='utf-8') |
| 64 | 64 |
| 65 print >>file, FILTERLIST_HEADER | 65 print >>file, FILTERLIST_HEADER |
| 66 | 66 |
| 67 for mirror in mirrors_list: | 67 for mirror in mirrors_list: |
| 68 data = try_mirror(mirror, MALWAREDOMAINS_PATH) | 68 data = try_mirror(mirror) |
|
Sebastian Noack
2016/03/14 15:40:12
Since MALWAREDOMAINS_PATH is a global anyway, ther
Vasily Kuznetsov
2016/03/14 16:20:38
Yeah, I was thinking about it. I guess try_mirror
| |
| 69 if data is not None: | 69 if data is not None: |
| 70 break | 70 break |
| 71 else: | 71 else: |
| 72 print >>sys.stderr, 'Unable to fetch malware domains list.' | 72 sys.exit('Unable to fetch malware domains list.') |
| 73 sys.exit(1) | |
| 74 | 73 |
| 75 zip = zipfile.ZipFile(StringIO(data), 'r') | 74 zip = zipfile.ZipFile(StringIO(data), 'r') |
| 76 info = zip.infolist()[0] | 75 info = zip.infolist()[0] |
| 77 for line in str(zip.read(info.filename)).splitlines(): | 76 for line in str(zip.read(info.filename)).splitlines(): |
| 78 domain = line.strip() | 77 domain = line.strip() |
| 79 if not domain: | 78 if not domain: |
| 80 continue | 79 continue |
| 81 | 80 |
| 82 print >>file, '||%s^' % domain.decode('idna') | 81 print >>file, '||%s^' % domain.decode('idna') |
| 83 file.close(); | 82 file.close(); |
| 84 | 83 |
| 85 if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '': | 84 if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '': |
| 86 subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-u', 'h gbot', '-m', 'Updated malwaredomains.com data']) | 85 subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-u', 'h gbot', '-m', 'Updated malwaredomains.com data']) |
| 87 subprocess.check_call(['hg', '-q', 'push', '-R', tempdir]) | 86 subprocess.check_call(['hg', '-q', 'push', '-R', tempdir]) |
| 88 finally: | 87 finally: |
| 89 shutil.rmtree(tempdir, ignore_errors=True) | 88 shutil.rmtree(tempdir, ignore_errors=True) |
| LEFT | RIGHT |