blob: 7e43d63cbc941e1a1fcd7121e6a2c2c4e9a3062c (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
|
title: //*[@class="article"]/h1
date: //*[@class="article"]/div[@class="date"]
# strip the title and date from the article text
strip: //*[@class="article"]/h1
strip: //*[@class="article"]/div[@class="date"]
# strip annoying <br> between metadata and article
strip: //*[@class="article"]/div[@class="date"]/following-sibling::br
test_url: http://minnesota.publicradio.org/display/web/2012/06/19/health/senators-want-health-care-ruling-on-tv/
|
