[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / neh.gov.txt

#host configuration should be http://www.neh.gov/news/humanities/\r
\r
\r
#meta data \r
title:substring-after(substring-after(//title,':'),':')\r
author:substring-after(//h2[@class = 'subHead'],'By')\r
date:substring-before(substring-after(//title,':'),':')\r
\r
#img and caption handling\r
wrap_in(small)://div[@id = 'mainContent']/table/descendant::p/descendant::text()\r
wrap_in(fieldset)://div[@id = 'mainContent']/table\r
\r
# clean up\r
strip: //table[@class = 'marginpaddingTop']\r
strip: //h2[@class = 'subHead']\r

test_url: http://www.neh.gov/news/humanities/2011-11/IslamicScholar.html
Commit	Line	Data
ac4d1142 NL	1	#host configuration should be http://www.neh.gov/news/humanities/\r
	2	\r
	3	\r
	4	#meta data \r
	5	title:substring-after(substring-after(//title,':'),':')\r
	6	author:substring-after(//h2[@class = 'subHead'],'By')\r
	7	date:substring-before(substring-after(//title,':'),':')\r
	8	\r
	9	#img and caption handling\r
	10	wrap_in(small)://div[@id = 'mainContent']/table/descendant::p/descendant::text()\r
	11	wrap_in(fieldset)://div[@id = 'mainContent']/table\r
	12	\r
	13	# clean up\r
	14	strip: //table[@class = 'marginpaddingTop']\r
	15	strip: //h2[@class = 'subHead']\r
	16
	17	test_url: http://www.neh.gov/news/humanities/2011-11/IslamicScholar.html