2014-10-27 01:46:13 -04:00
|
|
|
body: //div[contains(concat(' ',normalize-space(@class),' '),' article ') and (contains(concat(' ',normalize-space(@class),' '),' clear '))]
|
2014-07-13 04:15:40 -04:00
|
|
|
title: //div[@class="storyBox"]/h1
|
|
|
|
|
author: //a[@rel="author"]
|
|
|
|
|
date: substring-before(//span[@class="dateline"], 'by')
|
|
|
|
|
|
|
|
|
|
#Removes related content but cleans up article text
|
|
|
|
|
strip: //h1
|
|
|
|
|
strip: //p[@class="homeStory tdmSideInfo"]
|
|
|
|
|
strip: //div[@id="bylineShare"]
|
|
|
|
|
strip: //script
|
|
|
|
|
strip: //hr
|
|
|
|
|
|
|
|
|
|
strip_id_or_class: homeStory
|
|
|
|
|
strip_id_or_class: authorpic
|
|
|
|
|
strip_id_or_class: insideComments
|
|
|
|
|
strip_id_or_class: authorbio
|
|
|
|
|
strip_id_or_class: gpt-ad-sel-cube
|
|
|
|
|
strip_id_or_class: smxTextAd
|
2013-12-06 04:13:03 -05:00
|
|
|
|
|
|
|
|
test_url: http://searchengineland.com/googles-jaw-dropping-sponsored-post-campaign-for-chrome-106348
|
