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

# NOTE:  If testing this configuration yields bad results, including junk text like "Try BostonGlobe.com today" and "THIS STORY APPEARED IN", please replace the Test URL with a current-day headline link from bostonglobe.com.\r
\r
title: //div[@class="header"]/h1\r
author: substring-after(//div[@class="byline"]/h2[@class="author"],"By ")\r
date: //div[@class="byline"]/p[last()]\r
body: //div[@class="article-body"]\r
\r
strip_id_or_class: aside\r
strip_id_or_class: promo\r
strip_id_or_class: skip-nav\r
strip_id_or_class: article-more\r
strip_id_or_class: article-bar\r
\r
# This removes image captions.  If the parser starts saving images from bostonglobe.com (currently, it does not), then this directive should be removed.\r
strip_id_or_class: figure
test_url: http://bostonglobe.com/news/nation/2012/03/17/illinois-primary-could-pivotal/PsDzFZqvhEYyXbOcF9FOkO/story.html
Commit	Line	Data
ac4d1142 NL	1	# NOTE: If testing this configuration yields bad results, including junk text like "Try BostonGlobe.com today" and "THIS STORY APPEARED IN", please replace the Test URL with a current-day headline link from bostonglobe.com.\r
	2	\r
	3	title: //div[@class="header"]/h1\r
	4	author: substring-after(//div[@class="byline"]/h2[@class="author"],"By ")\r
	5	date: //div[@class="byline"]/p[last()]\r
	6	body: //div[@class="article-body"]\r
	7	\r
	8	strip_id_or_class: aside\r
	9	strip_id_or_class: promo\r
	10	strip_id_or_class: skip-nav\r
	11	strip_id_or_class: article-more\r
	12	strip_id_or_class: article-bar\r
	13	\r
	14	# This removes image captions. If the parser starts saving images from bostonglobe.com (currently, it does not), then this directive should be removed.\r
	15	strip_id_or_class: figure
	16	test_url: http://bostonglobe.com/news/nation/2012/03/17/illinois-primary-could-pivotal/PsDzFZqvhEYyXbOcF9FOkO/story.html