sitescripts: Collect unmatched filters

sitescripts/crawler/bin/import_sites.py

Index: sitescripts/crawler/bin/import_sites.py
===================================================================
new file mode 100644
--- /dev/null
+++ b/sitescripts/crawler/bin/import_sites.py
@@ -0,0 +1,52 @@
+# coding: utf-8
+
+# This Source Code is subject to the terms of the Mozilla Public License
+# version 2.0 (the "License"). You can obtain a copy of the License at
+# http://mozilla.org/MPL/2.0/.
+
+import MySQLdb, os, re, subprocess
+from sitescripts.utils import cached, get_config
+
+@cached(600)
+def _get_db():
+  database = get_config().get("crawler", "database")
+  dbuser = get_config().get("crawler", "dbuser")
+  dbpasswd = get_config().get("crawler", "dbpassword")
+  if os.name == "nt":
+    return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database,
+                           use_unicode=True, charset="utf8", named_pipe=True)
+  else:
+    return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database,
+                           use_unicode=True, charset="utf8")
+
+def _get_cursor():
+  return _get_db().cursor(MySQLdb.cursors.DictCursor)
+
+def _hg(args):
+  return subprocess.Popen(["hg"] + args, stdout = subprocess.PIPE)
+
+def _extract_sites(easylist_dir):
+  os.chdir(easylist_dir)
+  process = _hg(["log", "--template", "{desc}\n"])
+  urls = set([])
+
+  for line in process.stdout:
+    match = re.search(r"\b(https?://\S*)", line)
+    if not match:
+      continue
+
+    url = match.group(1).strip()
+    urls.add(url)
+
+  return urls
+
+def _insert_sites(site_urls):
+  cursor = _get_cursor()
+  for url in site_urls:
+    cursor.execute("INSERT INTO crawler_sites (url) VALUES (%s)", url)
+
+if __name__ == "__main__":
+  easylist_dir = get_config().get("crawler", "easylist_repository")
+  site_urls = _extract_sites(easylist_dir)
+  _insert_sites(site_urls)
+