blob: 984d81ded357b66b945f35932cce46ac8eb20c1b (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1
date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]
author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]
strip_id_or_class: mod-article-byline
strip_id_or_class: mod-article-header
strip_id_or_class: mod-article-subtitle
#This leaves some crud after the article, but it's better than nothing.
#It would be ideal if we could set the body to every element matching //div[contains(@class, "mod-articletext")]/p, but it seems like body only takes the first matching element.
test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown
|
