1
0
mirror of https://github.com/moparisthebest/wallabag synced 2024-11-23 17:42:15 -05:00
wallabag/inc/3rdparty/site_config/standard/searchengineland.com.txt
2014-10-27 06:46:13 +01:00

20 lines
714 B
Plaintext
Executable File

body: //div[contains(concat(' ',normalize-space(@class),' '),' article ') and (contains(concat(' ',normalize-space(@class),' '),' clear '))]
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
test_url: http://searchengineland.com/googles-jaw-dropping-sponsored-post-campaign-for-chrome-106348