[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / articles.courant.com.txt

title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1\r
date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]\r
author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]\r
\r
strip_id_or_class: mod-article-byline\r
strip_id_or_class: mod-article-header\r
strip_id_or_class: mod-article-subtitle\r
#This leaves some crud after the article, but it's better than nothing.\r
#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.\r

test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown
Commit	Line	Data
ac4d1142 NL	1	title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1\r
	2	date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]\r
	3	author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]\r
	4	\r
	5	strip_id_or_class: mod-article-byline\r
	6	strip_id_or_class: mod-article-header\r
	7	strip_id_or_class: mod-article-subtitle\r
	8	#This leaves some crud after the article, but it's better than nothing.\r
	9	#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.\r
	10
	11	test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown