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

#\r
# After site revisions at SciAm, this configuration does\r
# not work, especially for multi-page articles. For\r
# every article there is now a "Print" link which\r
# is far more reliable. So this configuration should be\r
# removed or  disabled.\r
# 2/3/13\r
#\r
\r
# meta data\r
title://h1[@class = 'articleTitle']\r
author:substring-after(//span[@class = 'byline'],'By ')\r
date:substring-before(//span[@class = 'datestamp'],'|')\r
\r
#body content\r
body://div[@id = 'articleContent']\r
#next_page_link://li[@id = 'flairPagination']/a[last()]\r
\r
single_page_link: //a[contains(@href, 'print=true')]\r
\r
#cleanup\r
strip://div[@class = 'fsgBooks']\r
\r
test_url: http://www.scientificamerican.com/article.cfm?id=do-brain-scans-comatose-patients-reveal-conscious-state\r
test_url: http://www.scientificamerican.com/article.cfm?id=solar-wind-transforms-venus-into-shape-of-comet
Commit	Line	Data
ac4d1142 NL	1	#\r
	2	# After site revisions at SciAm, this configuration does\r
	3	# not work, especially for multi-page articles. For\r
	4	# every article there is now a "Print" link which\r
	5	# is far more reliable. So this configuration should be\r
	6	# removed or disabled.\r
	7	# 2/3/13\r
	8	#\r
	9	\r
	10	# meta data\r
	11	title://h1[@class = 'articleTitle']\r
	12	author:substring-after(//span[@class = 'byline'],'By ')\r
	13	date:substring-before(//span[@class = 'datestamp'],'\|')\r
	14	\r
	15	#body content\r
	16	body://div[@id = 'articleContent']\r
	17	#next_page_link://li[@id = 'flairPagination']/a[last()]\r
	18	\r
	19	single_page_link: //a[contains(@href, 'print=true')]\r
	20	\r
	21	#cleanup\r
	22	strip://div[@class = 'fsgBooks']\r
	23	\r
	24	test_url: http://www.scientificamerican.com/article.cfm?id=do-brain-scans-comatose-patients-reveal-conscious-state\r
	25	test_url: http://www.scientificamerican.com/article.cfm?id=solar-wind-transforms-venus-into-shape-of-comet