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

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