From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- domusweb.it.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 domusweb.it.txt (limited to 'domusweb.it.txt') diff --git a/domusweb.it.txt b/domusweb.it.txt new file mode 100644 index 0000000..20566ee --- /dev/null +++ b/domusweb.it.txt @@ -0,0 +1,21 @@ +# 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'],'—') +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/ \ No newline at end of file -- cgit v1.3.1