You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@community.apache.org by se...@apache.org on 2015/11/14 12:59:13 UTC
svn commit: r1714305 -
/comdev/projects.apache.org/scripts/cronjobs/parsecommitters.py
Author: sebb
Date: Sat Nov 14 11:59:13 2015
New Revision: 1714305
URL: http://svn.apache.org/viewvc?rev=1714305&view=rev
Log:
Add caching for the HTML file
Mainly for testing purposes, as the time between runs is much longer than the interval
Modified:
comdev/projects.apache.org/scripts/cronjobs/parsecommitters.py
Modified: comdev/projects.apache.org/scripts/cronjobs/parsecommitters.py
URL: http://svn.apache.org/viewvc/comdev/projects.apache.org/scripts/cronjobs/parsecommitters.py?rev=1714305&r1=1714304&r2=1714305&view=diff
==============================================================================
--- comdev/projects.apache.org/scripts/cronjobs/parsecommitters.py (original)
+++ comdev/projects.apache.org/scripts/cronjobs/parsecommitters.py Sat Nov 14 11:59:13 2015
@@ -11,11 +11,14 @@ Reads http://people.apache.org/committer
import re
import urllib.request
import json
+import urlutils
+fc = urlutils.UrlCache(interval=600)
people = {}
people_name = {}
groups = {}
-data = urllib.request.urlopen("http://people.apache.org/committer-index.html").read().decode('utf-8')
+data = fc.get("http://people.apache.org/committer-index.html","committer-index.html", encoding='utf-8').read()
+#data = urllib.request.urlopen("http://people.apache.org/committer-index.html").read().decode('utf-8')
x = 0
for committer in re.findall(r"<tr>([\S\s]+?)</tr>", data, re.MULTILINE | re.UNICODE):
x += 1