OLD | NEW |
1 # This file is part of the Adblock Plus web scripts, | 1 # This file is part of the Adblock Plus web scripts, |
2 # Copyright (C) 2006-2016 Eyeo GmbH | 2 # Copyright (C) 2006-2016 Eyeo GmbH |
3 # | 3 # |
4 # Adblock Plus is free software: you can redistribute it and/or modify | 4 # Adblock Plus is free software: you can redistribute it and/or modify |
5 # it under the terms of the GNU General Public License version 3 as | 5 # it under the terms of the GNU General Public License version 3 as |
6 # published by the Free Software Foundation. | 6 # published by the Free Software Foundation. |
7 # | 7 # |
8 # Adblock Plus is distributed in the hope that it will be useful, | 8 # Adblock Plus is distributed in the hope that it will be useful, |
9 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 9 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
11 # GNU General Public License for more details. | 11 # GNU General Public License for more details. |
12 # | 12 # |
13 # You should have received a copy of the GNU General Public License | 13 # You should have received a copy of the GNU General Public License |
14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. | 14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. |
15 | 15 |
16 import os | 16 import os |
17 import subprocess | 17 import subprocess |
18 import codecs | 18 import codecs |
| 19 import contextlib |
19 import urllib2 | 20 import urllib2 |
20 import zipfile | 21 import zipfile |
21 import tempfile | 22 import tempfile |
22 import shutil | 23 import shutil |
23 import sys | 24 import sys |
24 from StringIO import StringIO | 25 from StringIO import StringIO |
25 from sitescripts.utils import get_config | 26 from sitescripts.utils import get_config |
26 | 27 |
27 | 28 |
28 FILTERLIST_HEADER = '''[Adblock Plus 1.1] | 29 FILTERLIST_HEADER = '''[Adblock Plus 1.1] |
29 ! This is a list of malware domains generated from malwaredomains.com data. | 30 ! This is a list of malware domains generated from malwaredomains.com data. |
30 ! Homepage: http://malwaredomains.com/?page_id=2 | 31 ! Homepage: http://malwaredomains.com/?page_id=2 |
31 ! Last modified: %timestamp% | 32 ! Last modified: %timestamp% |
32 ! Expires: 1d | 33 ! Expires: 1d |
33 !''' | 34 !''' |
34 | 35 |
35 MALWAREDOMAINS_PATH = '/files/justdomains.zip' | 36 MALWAREDOMAINS_PATH = '/files/justdomains.zip' |
36 | 37 |
37 | 38 |
38 def try_mirror(mirror): | 39 def try_mirror(mirror): |
| 40 url = mirror + MALWAREDOMAINS_PATH |
39 try: | 41 try: |
40 response = urllib2.urlopen(mirror + MALWAREDOMAINS_PATH) | 42 with contextlib.closing(urllib2.urlopen(url)) as response: |
41 return response.read() | 43 return None, response.read() |
42 except urllib2.HTTPError: | 44 except urllib2.HTTPError as exc: |
43 return None | 45 exc.close() |
| 46 except urllib2.URLError as exc: |
| 47 pass |
| 48 return 'Failed to fetch {}: {}'.format(url, exc), None |
44 | 49 |
45 | 50 |
46 if __name__ == '__main__': | 51 def main(): |
47 config = get_config() | 52 config = get_config() |
48 section = 'subscriptionDownloads' | 53 section = 'subscriptionDownloads' |
49 repository = config.get(section, 'malwaredomains_repository') | 54 repository = config.get(section, 'malwaredomains_repository') |
50 mirrors = config.get(section, 'malwaredomains_mirrors').split() | 55 mirrors = config.get(section, 'malwaredomains_mirrors').split() |
51 | 56 |
52 tempdir = tempfile.mkdtemp(prefix='malwaredomains') | 57 tempdir = tempfile.mkdtemp(prefix='malwaredomains') |
53 try: | 58 try: |
54 subprocess.check_call(['hg', '-q', 'clone', '-U', repository, tempdir]) | 59 subprocess.check_call(['hg', '-q', 'clone', '-U', repository, tempdir]) |
55 subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default']
) | 60 subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default']
) |
56 | 61 |
57 path = os.path.join(tempdir, 'malwaredomains_full.txt') | 62 path = os.path.join(tempdir, 'malwaredomains_full.txt') |
58 file = codecs.open(path, 'wb', encoding='utf-8') | 63 file = codecs.open(path, 'wb', encoding='utf-8') |
59 | 64 |
60 print >>file, FILTERLIST_HEADER | 65 print >>file, FILTERLIST_HEADER |
61 | 66 |
| 67 error_report = ['Unable to fetch malware domains list', 'Errors:'] |
62 for mirror in mirrors: | 68 for mirror in mirrors: |
63 data = try_mirror(mirror) | 69 error_message, data = try_mirror(mirror) |
64 if data is not None: | 70 if data is not None: |
65 break | 71 break |
| 72 error_report.append(error_message) |
66 else: | 73 else: |
67 sys.exit('Unable to fetch malware domains list.') | 74 sys.exit('\n'.join(error_report)) |
68 | 75 |
69 zip = zipfile.ZipFile(StringIO(data), 'r') | 76 zf = zipfile.ZipFile(StringIO(data), 'r') |
70 info = zip.infolist()[0] | 77 info = zf.infolist()[0] |
71 for line in str(zip.read(info.filename)).splitlines(): | 78 for line in str(zf.read(info.filename)).splitlines(): |
72 domain = line.strip() | 79 domain = line.strip() |
73 if not domain: | 80 if not domain: |
74 continue | 81 continue |
75 | 82 |
76 print >>file, '||%s^' % domain.decode('idna') | 83 print >>file, '||%s^' % domain.decode('idna') |
77 file.close() | 84 file.close() |
78 | 85 |
79 if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '': | 86 if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '': |
80 subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-
u', 'hgbot', '-m', 'Updated malwaredomains.com data']) | 87 subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-
u', 'hgbot', '-m', 'Updated malwaredomains.com data']) |
81 subprocess.check_call(['hg', '-q', 'push', '-R', tempdir]) | 88 subprocess.check_call(['hg', '-q', 'push', '-R', tempdir]) |
82 finally: | 89 finally: |
83 shutil.rmtree(tempdir, ignore_errors=True) | 90 shutil.rmtree(tempdir, ignore_errors=True) |
| 91 |
| 92 |
| 93 if __name__ == '__main__': |
| 94 main() |
OLD | NEW |