[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.

title: //div[@class="header"]/h1
author: substring-after(//div[@class="byline"]/h2[@class="author"],"By ")
date: //div[@class="byline"]/p[last()]
body: //div[@class="article-body"]

strip_id_or_class: aside
strip_id_or_class: promo
strip_id_or_class: skip-nav
strip_id_or_class: article-more
strip_id_or_class: article-bar

# This removes image captions.  If the parser starts saving images from bostonglobe.com (currently, it does not), then this directive should be removed.
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
4e067cea 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.
	2
	3	title: //div[@class="header"]/h1
	4	author: substring-after(//div[@class="byline"]/h2[@class="author"],"By ")
	5	date: //div[@class="byline"]/p[last()]
	6	body: //div[@class="article-body"]
	7
	8	strip_id_or_class: aside
	9	strip_id_or_class: promo
	10	strip_id_or_class: skip-nav
	11	strip_id_or_class: article-more
	12	strip_id_or_class: article-bar
	13
	14	# This removes image captions. If the parser starts saving images from bostonglobe.com (currently, it does not), then this directive should be removed.
ac4d1142 NL	15	strip_id_or_class: figure
ac4d1142 NL	16	test_url: http://bostonglobe.com/news/nation/2012/03/17/illinois-primary-could-pivotal/PsDzFZqvhEYyXbOcF9FOkO/story.html