blob: 2b47f7443b3b8f3bba9ed77f14350d120587bf63 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
title: //meta[@property='og:title']/@content
author: (//span[@class="byline"]/a)[1]
date: //span[contains(@class, "toLocalTime")]
body: (//div[contains(@class, "articleInner")]//img[contains(@src, 'media.salon.com') and contains(@src, '460x')])[1] | //div[contains(@class, "articleContent") or contains(@class, "writerMeta")]
prune: no
# deal with singleton links
single_page_link: (//h1/a[contains(@href, '/singleton')])[1]
test_url: http://www.salon.com/2011/10/25/occupying_the_rust_belt/singleton/
|
