From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- prospectmagazine.co.uk.txt | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 prospectmagazine.co.uk.txt (limited to 'prospectmagazine.co.uk.txt') diff --git a/prospectmagazine.co.uk.txt b/prospectmagazine.co.uk.txt new file mode 100644 index 0000000..739d1b9 --- /dev/null +++ b/prospectmagazine.co.uk.txt @@ -0,0 +1,26 @@ +#basics +author: (//div[contains(@class,'author')])[1] +date: substring-before(//a[@class='issue'], '—') +#body://div[@class = 'entry'] +# use this until move_into support is ready +body: //div[@class = 'entry' or @class='standfirst' or @class='lead_image'] + +#moves header image and tagline into body +move_into(//div[@class='entry']/div)://div[@class = 'lead_image'] +move_into(//div[@class='entry']/div)://div[@class = 'standfirst'] + + +# moves author info to end of text +move_into(//p[strong[string(.) = 'Follow Prospect on Twitter']])://div[@id='sidebar_content']/p/em + +prune: no + +# strips social links +strip_id_or_class:login-status +strip_id_or_class:shareinpost +strip_id_or_class:content_subscribe +strip_id_or_class:postinfo +strip_id_or_class:postutils +strip_id_or_class:comments +strip://strong[string(.) = 'Follow Prospect on Twitter'] +test_url: http://www.prospectmagazine.co.uk/2011/07/postmodernism-is-dead-va-exhibition-age-of-authenticism/ \ No newline at end of file -- cgit v1.3.1