2014-07-13 04:15:40 -04:00
|
|
|
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
|
|
|
|
|
date://meta[@name="publish_date"]/@content
|
|
|
|
|
|
|
|
|
|
strip://div[contains(@class, "breadcrumbs")]
|
|
|
|
|
strip://a[contains(@class, "hidden")]
|
|
|
|
|
strip://div[contains(@class, "story-embed")]
|
2013-12-06 04:13:03 -05:00
|
|
|
strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/..
|
|
|
|
|
test_url: http://www.politico.com/news/stories/0712/78105.html
|
