x/stackalytics
Code Issues Proposed changes

Fix pattern in member page parser

Browse Source 
Change-Id: Iff564b781de3562e0bb41be7f4dfa955d36ae9a5
This commit is contained in:
Ilya Shakhat
2015-01-17 00:33:04 +03:00
parent 55cc1877b2
commit 953ab3164c
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
stackalytics/processor/mps.py
View File

@@ -26,7 +26,7 @@ from stackalytics.processor import utils
LOG = logging.getLogger(__name__)
NAME_AND_DATE_PATTERN = (r'<h3>(?P<member_name>[^<]*)[\s\S]*?'
r'<div class="span-7 last">(?P<date_joined>[^<]*)')
r'<div class="span-\d last">(?P<date_joined>[^<]*)')
COMPANY_PATTERN = (r'<strong>Date\sJoined[\s\S]*?<b>(?P<company_draft>[^<]*)'
r'[\s\S]*?From\s(?P<date_from>[\s\S]*?)\(Current\)')
GARBAGE_PATTERN = r'[/\\~%^\*_]+'