From f1caf12124ad5625f38627bbb6b977840ad278c0 Mon Sep 17 00:00:00 2001
From: Julie Pichon <julie.pichon@gmail.com>
Date: Mon, 21 Sep 2009 20:26:37 +0100
Subject: [PATCH 1/2] Fix article retrieval (#1348)
---
infoslicer/processing/MediaWiki_Parser.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/infoslicer/processing/MediaWiki_Parser.py b/infoslicer/processing/MediaWiki_Parser.py
index 913f03e..dcf559a 100644
a
|
b
|
class MediaWiki_Parser(HTML_Parser): |
17 | 17 | |
18 | 18 | logger.debug('MediaWiki_Parser: %s' % source_url) |
19 | 19 | |
20 | | header, input_content = document_to_parse.split("<text>") |
| 20 | header, input_content = document_to_parse.split("<text xml:space=\"preserve\">") |
21 | 21 | |
22 | 22 | #find the revision id in the xml the wiki API returns |
23 | 23 | revid = re.findall(re.compile('\<parse.*revid\=\"(?P<rid>[0-9]*)\"'), |