Issue 3774 - Support multiple mirrors for the Malware Domains List

sitescripts/subscriptions/bin/updateMalwareDomainsList.py

 # coding: utf-8
 
 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2016 Eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus 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 Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
 
-import os, subprocess, codecs, urllib, zipfile, tempfile, shutil
+import os, subprocess, codecs, urllib2, zipfile, tempfile, shutil, sys
+import ConfigParser
 from StringIO import StringIO
 from sitescripts.utils import get_config
 
+
+FILTERLIST_HEADER = '''[Adblock Plus 1.1]
+! This is a list of malware domains generated from malwaredomains.com data.
+! Homepage: http://malwaredomains.com/?page_id=2
+! Last modified: %timestamp%
+! Expires: 1d
+!'''
+
+DEFAULT_MIRRORS_LIST = [
+    'http://mirror3.malwaredomains.com',
+    'http://mirror1.malwaredomains.com',
+    'http://mirror2.malwaredomains.com'
+]
+
+MALWAREDOMAINS_PATH = '/files/justdomains.zip'
+
+
+def try_mirror(mirror):
+  try:
+    response = urllib2.urlopen(mirror + MALWAREDOMAINS_PATH)
+    return response.read()
+  except urllib2.HTTPError:
+    return None
+
+
 if __name__ == '__main__':
-  repository = get_config().get('subscriptionDownloads', 'malwaredomains_repository')
+  config = get_config()
+  repository = config.get('subscriptionDownloads', 'malwaredomains_repository')
+  try:
+    mirrors = config.get('subscriptionDownloads', 'malwaredomains_mirrors')
+    mirrors_list = mirrors.split()
+  except ConfigParser.NoOptionError:
+    mirrors_list = DEFAULT_MIRRORS_LIST
+
   tempdir = tempfile.mkdtemp(prefix='malwaredomains')
   try:
     subprocess.check_call(['hg', '-q', 'clone',  '-U', repository, tempdir])
     subprocess.check_call(['hg', '-q', 'up', '-R', tempdir, '-r', 'default'])
 
     path = os.path.join(tempdir, 'malwaredomains_full.txt')
     file = codecs.open(path, 'wb', encoding='utf-8')
 
-    print >>file, '''[Adblock Plus 1.1]
-! This is a list of malware domains generated from malwaredomains.com data.
-! Homepage: http://malwaredomains.com/?page_id=2
-! Last modified: %timestamp%
-! Expires: 1d
-!'''
+    print >>file, FILTERLIST_HEADER
 
-    data = urllib.urlopen('http://mirror3.malwaredomains.com/files/justdomains.zip').read()
+    for mirror in mirrors_list:
+      data = try_mirror(mirror)
+      if data is not None:
+        break
+    else:
+      sys.exit('Unable to fetch malware domains list.')
+
     zip = zipfile.ZipFile(StringIO(data), 'r')
     info = zip.infolist()[0]
     for line in str(zip.read(info.filename)).splitlines():
       domain = line.strip()
       if not domain:
         continue
 
       print >>file, '||%s^' % domain.decode('idna')
     file.close();
 
     if subprocess.check_output(['hg', 'stat', '-R', tempdir]) != '':
       subprocess.check_call(['hg', '-q', 'commit', '-R', tempdir, '-A', '-u', 'hgbot', '-m', 'Updated malwaredomains.com data'])
       subprocess.check_call(['hg', '-q', 'push', '-R', tempdir])
   finally:
     shutil.rmtree(tempdir, ignore_errors=True)