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 +1,39 @@
+# 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 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([])
+
+  while True:
+    line = process.stdout.readline()
+    if line == "":
+      break
+
+    matches = re.match(r"[A-Z]:.*(https?://.*)", line)

[Wladimir Palant, 2012/09/14 14:42:14]

What if the URL is followed by some additional info? Maybe at least \S* and not
.*?

+    if not matches:
+      continue
+
+    url = matches.group(1).strip()
+    urls.add(url)
+
+  return urls
+
+def print_statements(urls):
+  for url in urls:
+    print "INSERT INTO crawler_sites (url) VALUES ('" + url + "');"

[Wladimir Palant, 2012/09/14 14:42:14]

SQL injection? :-(

+
+if __name__ == "__main__":
+  filter_list_dir = get_config().get("crawler", "filter_list_repository")
+  urls = extract_urls(filter_list_dir)
+  print_statements(urls)