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

title: normalize(//h1)\r
\r
author: //td/p[position()=last()]/em\r
\r
# I swear, this is really the best way to do this\r
date: normalize(//td[contains(@style, "color: #ffffff")])\r
\r
# my god, it's full of tables\r
body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td\r
strip: //h1\r
\r
# the following two lines strip the byline at the end of the article (the byline is a <p> that consists of an em dash and then some text in an <em>). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output.\r
strip: //p[position()=last()]/em\r
strip: //p[position()=last()]/child::text()
test_url: http://www.fnal.gov/pub/today/archive_2011/today11-11-09_MuonDepartmentReadMore.html
Commit	Line	Data
ac4d1142 NL	1	title: normalize(//h1)\r
	2	\r
	3	author: //td/p[position()=last()]/em\r
	4	\r
	5	# I swear, this is really the best way to do this\r
	6	date: normalize(//td[contains(@style, "color: #ffffff")])\r
	7	\r
	8	# my god, it's full of tables\r
	9	body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td\r
	10	strip: //h1\r
	11	\r
	12	# the following two lines strip the byline at the end of the article (the byline is a <p> that consists of an em dash and then some text in an <em>). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output.\r
	13	strip: //p[position()=last()]/em\r
	14	strip: //p[position()=last()]/child::text()
	15	test_url: http://www.fnal.gov/pub/today/archive_2011/today11-11-09_MuonDepartmentReadMore.html