You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@community.apache.org by hu...@apache.org on 2020/03/05 22:41:36 UTC
svn commit: r1874859 -
/comdev/projects.apache.org/trunk/scripts/cronjobs/parsereleases.py
Author: humbedooh
Date: Thu Mar 5 22:41:36 2020
New Revision: 1874859
URL: http://svn.apache.org/viewvc?rev=1874859&view=rev
Log:
adjust behavior to match downloads.a.o
Modified:
comdev/projects.apache.org/trunk/scripts/cronjobs/parsereleases.py
Modified: comdev/projects.apache.org/trunk/scripts/cronjobs/parsereleases.py
URL: http://svn.apache.org/viewvc/comdev/projects.apache.org/trunk/scripts/cronjobs/parsereleases.py?rev=1874859&r1=1874858&r2=1874859&view=diff
==============================================================================
--- comdev/projects.apache.org/trunk/scripts/cronjobs/parsereleases.py (original)
+++ comdev/projects.apache.org/trunk/scripts/cronjobs/parsereleases.py Thu Mar 5 22:41:36 2020
@@ -44,7 +44,7 @@ x = 0
def getDirList(url):
try:
data = urllib.request.urlopen(url).read().decode('utf-8')
- for entry, xd, xdate in re.findall(r"<a href=\"([^\"/]+)(/?)\">.+</a>(?:<.+?>|\s+)(\d\d\d\d-\d\d-\d\d)", data, re.MULTILINE | re.UNICODE):
+ for entry, xd, xdate in re.findall(r"<a href=\"([^\"/]+)(/?)\">\S+</a>\s+(\d\d\d\d-\d\d-\d\d)", data, re.MULTILINE | re.UNICODE):
yield(entry, xdate, xd)
except:
pass