[Pywikipedia-l] SVN: [4843] trunk/pywikipedia/noreferences.py
wikipedian at svn.wikimedia.org
wikipedian at svn.wikimedia.org
Thu Jan 10 12:26:50 UTC 2008
Revision: 4843
Author: wikipedian
Date: 2008-01-10 12:26:49 +0000 (Thu, 10 Jan 2008)
Log Message:
-----------
while parsing the XML dump, ignore commented-out parts
Modified Paths:
--------------
trunk/pywikipedia/noreferences.py
Modified: trunk/pywikipedia/noreferences.py
===================================================================
--- trunk/pywikipedia/noreferences.py 2008-01-10 01:52:11 UTC (rev 4842)
+++ trunk/pywikipedia/noreferences.py 2008-01-10 12:26:49 UTC (rev 4843)
@@ -138,7 +138,8 @@
mysite = wikipedia.getSite()
dump = xmlreader.XmlDump(self.xmlFilename)
for entry in dump.parse():
- if self.refR.search(entry.text) and not self.referencesR.search(entry.text):
+ text = wikipedia.removeDisabledParts(entry.text)
+ if self.refR.search(text) and not self.referencesR.search(text):
yield wikipedia.Page(mysite, entry.title)
class NoReferencesBot:
More information about the Pywikipedia-l
mailing list