Crawler backend

sitescripts/crawler/bin/extract_crawler_sites.py

+# 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:
+    matches = re.match(r".*\b(https?://\S*)", line)

[Wladimir Palant, 2012/09/27 07:34:17]

Please use re.search() rather than re.match() here (and then without .* at the
start). re.match() will always match the complete string - we are actually
interested in a substring.

Generally, I consider re.match() in Python's standard library a bug - it's
confusing and typically useless.

Side-note: I would probably name the result variable match and not matches - it
is really only one match unlike when calling re.findall().

[Felix Dahlke, 2012/09/27 09:26:24]

Done. You're right, I'm used to calling it "matches" because it's an array with
the matched string and all groups in JS. It's really just one though.

+    if not matches:
+      continue
+
+    url = matches.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)