19 lines
739 B
Plaintext
19 lines
739 B
Plaintext
title: //h1[@class="sl-art-head-dek"]
|
|
body: //article//div[@class='sl-art-body']/div[contains(@class, 'body')]
|
|
strip: //div[@class="department_kicker"]
|
|
strip: //div[@id="insider_ad_wrapper" or @id="insider_ad_inner"]
|
|
strip: //div[@id="bottom_sponsored_links"]
|
|
strip: //div[@class="sl-art-ad-midflex"]
|
|
#strip: //dl
|
|
#strip: //p[em/a[contains(@href, 'facebook.com')]]
|
|
prune: no
|
|
|
|
author: //div[@id='author_bio']//a[contains(@href, '/author/')]
|
|
author: //a[contains(@href, '/authors.')]
|
|
|
|
date: substring-before(substring-after(//span[@class='sl-art-byline'], 'Posted '), ', at ')
|
|
|
|
single_page_link: //a[@class='sl-art-sinpage']
|
|
|
|
test_url: http://www.slate.com/id/2274583/pagenum/all/
|
|
test_url: http://www.slate.com/id/2293116/ |