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

title: //div[@id='main-article-info']//h1
body: //div[@id='article-wrapper']
date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate]
strip: //div[contains(@class, 'email-subscription')]
strip: //div[contains(@class, 'kindleWidget')]
#strip: //a[not(text())]
strip_id_or_class: pocket-btn
author: //li[@class='byline']
native_ad_clue: //meta[@property="article:tag" and contains(@content, "Partner zone")]
native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zone")]
prune: no
tidy: no

test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
test_contains: The National Security Agency has made repeated attempts to develop
test_contains: The agency did not directly address those questions, instead providing a statement.

test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester
test_contains: In August, the editor of the Guardian rang me up and asked if I would spend a week in New York
test_contains: As the second most senior judge in the country, Lord Hoffmann, said in 2004 about a previous version of our anti-terrorism laws

test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey
# Native ad
test_url: http://www.theguardian.com/sustainable-business/2014/jul/18/ben-jerry-turn-ice-cream-into-energy
Commit	Line	Data
4e067cea NL	1	title: //div[@id='main-article-info']//h1
	2	body: //div[@id='article-wrapper']
	3	date: //li[@class='publication']//time[@pubdate] \| //li[@class='publication']//data[@pubdate]
	4	strip: //div[contains(@class, 'email-subscription')]
	5	strip: //div[contains(@class, 'kindleWidget')]
	6	#strip: //a[not(text())]
	7	strip_id_or_class: pocket-btn
	8	author: //li[@class='byline']
90a1a78b NL	9	native_ad_clue: //meta[@property="article:tag" and contains(@content, "Partner zone")]
90a1a78b NL	10	native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zone")]
4e067cea NL	11	prune: no
4e067cea NL	12	tidy: no
90a1a78b	13
4e067cea	14	test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
90a1a78b NL	15	test_contains: The National Security Agency has made repeated attempts to develop
	16	test_contains: The agency did not directly address those questions, instead providing a statement.
	17
4e067cea	18	test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester
90a1a78b NL	19	test_contains: In August, the editor of the Guardian rang me up and asked if I would spend a week in New York
	20	test_contains: As the second most senior judge in the country, Lord Hoffmann, said in 2004 about a previous version of our anti-terrorism laws
	21
	22	test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey
	23	# Native ad
	24	test_url: http://www.theguardian.com/sustainable-business/2014/jul/18/ben-jerry-turn-ice-cream-into-energy