2014-07-13 10:15:40 +02:00
|
|
|
title: //hgroup//h1
|
|
|
|
|
title: //span[@class='mainarttitle']
|
|
|
|
|
|
|
|
|
|
body: //div[@id='leftRail']//div[contains(@class, 'body')]
|
|
|
|
|
|
|
|
|
|
author: //meta[@name="author"]/@content
|
|
|
|
|
author: //span[@class='mainartauthor']
|
|
|
|
|
|
|
|
|
|
date: substring-before(//hgroup//h6, '@')
|
|
|
|
|
date: //span[@class='mainartdate']
|
|
|
|
|
|
|
|
|
|
prune: no
|
|
|
|
|
strip: //aside
|
|
|
|
|
strip_id_or_class: sticky_sharing
|
|
|
|
|
strip_id_or_class: pagination
|
|
|
|
|
strip_id_or_class: controlsbox
|
|
|
|
|
strip_id_or_class: storyboxes
|
|
|
|
|
strip_id_or_class: sponsoredlinks
|
|
|
|
|
strip_id_or_class: nextpage
|
|
|
|
|
strip_id_or_class: contextuallinks
|
|
|
|
|
strip_id_or_class: article_actions
|
|
|
|
|
strip_id_or_class: engagement_block
|
|
|
|
|
|
|
|
|
|
single_page_link: //a[contains(@href, '/print/')]
|
|
|
|
|
|
|
|
|
|
test_url: http://www.forbes.com/forbes/2011/0509/technology-frog-design-jan-chipchase-ethnographer-birth-cool_print.html
|
|
|
|
|
test_url: http://www.forbes.com/sites/bruceupbin/2012/09/11/the-iphone-5-winners-and-losers/
|
