Issue 3168 - Add a script for generating new content blocker lists

generate_lists.py

Index: generate_lists.py
===================================================================
new file mode 100755
--- /dev/null
+++ b/generate_lists.py
@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# This file is part of Adblock Plus <https://adblockplus.org/>,
+# Copyright (C) 2006-2015 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 shutil
+import subprocess
+import tempfile
+import urllib2
+
+BASE_PATH = os.path.dirname(os.path.abspath(__file__))
+ABP2BLOCKLIST_URL = "https://hg.adblockplus.org/abp2blocklist"
+ABP2BLOCKLIST_PATH = os.path.join(BASE_PATH, "abp2blocklist")
+EASYLIST_URL = "https://easylist-downloads.adblockplus.org/easylist_noadult.txt"
+EXCEPTIONRULES_URL = "https://easylist-downloads.adblockplus.org/exceptionrules.txt"
+EASYLIST_CONTENT_BLOCKER_PATH = os.path.join(BASE_PATH, "easylist_content_blocker.json")
+COMBINED_CONTENT_BLOCKER_PATH = os.path.join(BASE_PATH, "easylist+exceptionrules_content_blocker.json")
+
+def _update_abp2blocklist():
+  if os.path.isdir(ABP2BLOCKLIST_PATH):
+    subprocess.check_call(["hg", "pull", "-u", "-R", ABP2BLOCKLIST_PATH])
+  else:
+    subprocess.check_call(["hg", "clone", ABP2BLOCKLIST_URL,
+                           ABP2BLOCKLIST_PATH])
+  subprocess.check_call(["npm", "install"], cwd=ABP2BLOCKLIST_PATH)
+
+def _download_filter_lists():
+  try:
+    easylist_response = urllib2.urlopen(EASYLIST_URL)
+    easylist_file = tempfile.NamedTemporaryFile(mode="w+")
+    shutil.copyfileobj(easylist_response, easylist_file)
+  finally:
+    easylist_response.close()

[Sebastian Noack, 2015/10/21 20:56:23]

Nit: An empty line after each finally block would improve the readability.

[Felix Dahlke, 2015/10/22 02:43:45]

Done.

+  try:
+    exceptionrules_response = urllib2.urlopen(EXCEPTIONRULES_URL)
+    exceptionrules_file = tempfile.NamedTemporaryFile(mode="w+")
+    shutil.copyfileobj(exceptionrules_response, exceptionrules_file)
+  finally:
+    exceptionrules_response.close()
+  return (easylist_file, exceptionrules_file)
+
+def _convert_filter_list(source_file, destination_path):
+  source_file.seek(0)
+  with open(destination_path, "w") as destination_file:
+    subprocess.check_call(["node", "abp2blocklist.js"],
+                          cwd=ABP2BLOCKLIST_PATH, stdin=source_file,
+                          stdout=destination_file)
+
+def _concatenate_files(*source_files):
+  destination_file = tempfile.NamedTemporaryFile(mode="w+")
+  for source_file in source_files:
+    source_file.seek(0)
+    shutil.copyfileobj(source_file, destination_file)
+  return destination_file
+
+if __name__ == "__main__":
+  print "Fetching/updating abp2blocklist ..."
+  _update_abp2blocklist()
+
+  print "Downloading filter lists ..."
+  easylist_file, exceptionrules_file = _download_filter_lists()

[Sebastian Noack, 2015/10/21 21:14:35]

Mind closing the temporary files again?

[Felix Dahlke, 2015/10/22 02:43:45]

The OS is closing the files when the runtime terminates anyway, so I thought
that wasn't necessary. However, I've learned that the files aren't necessarily
flushed - that has to happen in the runtime, and while CPython seems to do it, I
guess not all do.

I'm closing them explicitly now, but I'm not really convinced, now it looks a
lot like the old variant where I was explicitly removing the temporary files
again. Anyway, I'm fine with this, I don't think it's worth more gold plating.

+
+  print "Generating %s ..." % os.path.basename(EASYLIST_CONTENT_BLOCKER_PATH)
+  _convert_filter_list(easylist_file, EASYLIST_CONTENT_BLOCKER_PATH)
+
+  print "Generating %s ..." % os.path.basename(COMBINED_CONTENT_BLOCKER_PATH)
+  combined_file = _concatenate_files(easylist_file, exceptionrules_file)
+  _convert_filter_list(combined_file, COMBINED_CONTENT_BLOCKER_PATH)