Fixes 4784 - Improve error reporting in updateMalwareDomainsList and add tests

sitescripts/subscriptions/bin/updateMalwareDomainsList.py

 # 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
 import subprocess
 import codecs
+import contextlib
 import urllib2
 import zipfile
 import tempfile
 import shutil
 import sys
 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
 !'''
 
 MALWAREDOMAINS_PATH = '/files/justdomains.zip'
 
 
 def try_mirror(mirror):
+    url = mirror + MALWAREDOMAINS_PATH
     try:
-        response = urllib2.urlopen(mirror + MALWAREDOMAINS_PATH)
-        return response.read()
-    except urllib2.HTTPError:
-        return None
+        with contextlib.closing(urllib2.urlopen(url)) as response:
+            return None, response.read()
+    except urllib2.URLError as exc:
+        error_message = 'Failed to fetch {}: {}'.format(url, exc)
+        if hasattr(exc, 'close'):

[Vasily Kuznetsov, 2017/01/19 16:34:08]

I tried to do it with two separate except clauses but that creates too much
repetition. How about a duck typish check instead!

[Sebastian Noack, 2017/01/19 17:13:33]

I don't see how that creates any duplication.

  try:
      ...
  except urllib2.HTTPError as e:
      e.close()
  except urllib2.URLError as e:
      pass
  return 'Failed to fetch {}: {}'.format(url, e), None

[Vasily Kuznetsov, 2017/01/20 13:44:49]

Yeah, this is better. Thanks.

+            exc.close()
+        return error_message, None
 
 
-if __name__ == '__main__':
+def main():
     config = get_config()
     section = 'subscriptionDownloads'
     repository = config.get(section, 'malwaredomains_repository')
     mirrors = config.get(section, 'malwaredomains_mirrors').split()
 
     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, FILTERLIST_HEADER
 
+        error_report = ['Unable to fetch malware domains list', 'Errors:']
         for mirror in mirrors:
-            data = try_mirror(mirror)
+            error_message, data = try_mirror(mirror)
             if data is not None:
                 break
+            error_report.append(error_message)
         else:
-            sys.exit('Unable to fetch malware domains list.')
+            sys.exit('\n'.join(error_report))
 
-        zip = zipfile.ZipFile(StringIO(data), 'r')
-        info = zip.infolist()[0]
-        for line in str(zip.read(info.filename)).splitlines():
+        zf = zipfile.ZipFile(StringIO(data), 'r')
+        info = zf.infolist()[0]
+        for line in str(zf.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)
+
+
+if __name__ == '__main__':
+    main()