[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / domusweb.it.txt

# TODO: clean up the extra junk at the end of articles

# general text formatting
prune: no
convert_double_br_tags:yes

# where to find the basic metadata
author://a[@class='articleauthor']
date://a[starts-with(@href,'/en/search/published/')]
title:substring-before(//h2[@class='title'],'&mdash;')
body://div[@id='maincontainer']

dissolve://div[starts-with(@id,'commentableblock')]

# clean up the crap
strip://div[contains(@class,'domusnetwork')]
strip://div[contains(@class,'relative_wrapper')]

strip://div[contains(@class,'captionsubimage')]/img[contains(@class,'arrow')]
wrap_in(em): //div[contains(@class,'captionsubimage')]/span
test_url: http://www.domusweb.it/en/design/in-praise-of-lost-time/
Commit	Line	Data
4e067cea NL	1	# TODO: clean up the extra junk at the end of articles
	2
	3	# general text formatting
	4	prune: no
	5	convert_double_br_tags:yes
	6
	7	# where to find the basic metadata
	8	author://a[@class='articleauthor']
	9	date://a[starts-with(@href,'/en/search/published/')]
	10	title:substring-before(//h2[@class='title'],'—')
	11	body://div[@id='maincontainer']
	12
	13	dissolve://div[starts-with(@id,'commentableblock')]
	14
	15	# clean up the crap
	16	strip://div[contains(@class,'domusnetwork')]
	17	strip://div[contains(@class,'relative_wrapper')]
	18
	19	strip://div[contains(@class,'captionsubimage')]/img[contains(@class,'arrow')]
ac4d1142 NL	20	wrap_in(em): //div[contains(@class,'captionsubimage')]/span
ac4d1142 NL	21	test_url: http://www.domusweb.it/en/design/in-praise-of-lost-time/