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('<page pageid="(.+?)" ns="1" title="(.+?)">', re.DOTALL)
+xml_metadata_re = re.compile('<page .+? pageid="(.+?)" ns="1" title="(.+?)">', re.DOTALL)
 xml_text_re = re.compile('<rev .*? xml:space="preserve">(.*)</rev>', re.DOTALL)
 redirectP = re.compile(r'#REDIRECT \[\[(.*)\]\]')