2014-07-13 04:15:40 -04:00
|
|
|
title: //div[@id='contentheader']/h1
|
|
|
|
|
author: //p[@class='attribution']/span[@class='author']/*
|
|
|
|
|
# Is there a way to pull multiple authors? My XPath here is just grabbing the first
|
|
|
|
|
|
|
|
|
|
date: /html/head/meta[@name="date"]/@content
|
|
|
|
|
body: //div[@class='main-content']
|
|
|
|
|
|
|
|
|
|
strip: //p[@class='byline']
|
|
|
|
|
strip: //div[@class='img-gallery']
|
|
|
|
|
strip: //div[@class='callout']
|
|
|
|
|
strip: //div[@class='add-your-view']
|
2013-12-06 04:13:03 -05:00
|
|
|
convert_double_br_tags: yes
|
|
|
|
|
test_url: http://www.brookings.edu/opinions/2011/1018_cyberattack_libya_goldsmith.aspx
|
