Crawler backend

sitescripts/crawler/bin/extract_crawler_sites.py

Index: sitescripts/crawler/bin/extract_crawler_sites.py
===================================================================
new file mode 100644
--- /dev/null
+++ b/sitescripts/crawler/bin/extract_crawler_sites.py
@@ -0,0 +1,36 @@
+# 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 get_config
+
+def hg(args):
+  return subprocess.Popen(["hg"] + args, stdout = subprocess.PIPE)
+
+def extract_urls(filter_list_dir):
+  os.chdir(filter_list_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 print_statements(urls):
+  for url in urls:
+    escaped_url = MySQLdb.escape_string(url)
+    print "INSERT INTO crawler_sites (url) VALUES ('" + escaped_url + "');"
+
+if __name__ == "__main__":
+  filter_list_dir = get_config().get("crawler", "filter_list_repository")
+  urls = extract_urls(filter_list_dir)
+  print_statements(urls)