From 2e3681cbab7c6aa00690c64af8b9a658600986b3 Mon Sep 17 00:00:00 2001 From: bumatic Date: Thu, 20 Apr 2017 15:29:03 +0200 Subject: [PATCH] Fix of error due to Wikipedia API change New attribute '_idx' was added in the API response which broke the regular expression. This has been fixed. --- scripts/01_extract_discussions.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/01_extract_discussions.py b/scripts/01_extract_discussions.py index 5868465..9bc65b1 100644 --- a/scripts/01_extract_discussions.py +++ b/scripts/01_extract_discussions.py @@ -31,7 +31,7 @@ archive_box_template_re = re.compile(r'\{\{archive.*?\|.*?(\[\[/.*?)\}\}', re.DOTALL) #for xml link_re = re.compile(r'\[\[([^|]*?)(?:\|.*?)*?\]\]') -xml_metadata_re = re.compile('', re.DOTALL) +xml_metadata_re = re.compile('', re.DOTALL) xml_text_re = re.compile('(.*)', re.DOTALL) redirectP = re.compile(r'#REDIRECT \[\[(.*)\]\]')