1
0
mirror of https://github.com/moparisthebest/wallabag synced 2024-11-13 12:55:05 -05:00
wallabag/inc/3rdparty/site_config/standard/articles.courant.com.txt
2013-12-06 10:13:03 +01:00

11 lines
745 B
Plaintext

title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1
date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]
author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]
strip_id_or_class: mod-article-byline
strip_id_or_class: mod-article-header
strip_id_or_class: mod-article-subtitle
#This leaves some crud after the article, but it's better than nothing.
#It would be ideal if we could set the body to every element matching //div[contains(@class, "mod-articletext")]/p, but it seems like body only takes the first matching element.
test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown