aboutsummaryrefslogblamecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/politico.com.txt
blob: c5302d1bac527785345b3ec4e1f58fccff63d32c (plain) (tree)
1
2
3
4
5
6
7





                                                                                                               
                                                                                                                   





                                                                                          


                                                 
                                                             
title://div[contains(@class, "article")]/h1
body://div[contains(@class,"story-text")]

# Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"]

next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a
next_page_link://div[contains(@class,"pagination")]/ol/li[contains(@class, "current")]/following-sibling::node()/a
date://meta[@name="publish_date"]/@content

strip://div[contains(@class, "breadcrumbs")]
strip://a[contains(@class, "hidden")]
strip://div[contains(@class, "story-embed")]
strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/..
strip://div[contains(@class, "story-interrupt")]
strip://footer[contains(@class, "author-bio")]

test_url: http://www.politico.com/news/stories/0712/78105.html