blob: cd52498fa00d13524d8a93109e242cc3534ca955 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
|
title://div[@class="article-title"]/h1[@class="title"]
date: //p[@class="article-date"]
body://*[@class="article-body article-text"]
# Trim out related posts at bottom of article
strip://blockquote[@class="memo"]
# Yup, no idea why author won't work...
author://div[@class="page-header article-header clearfix"]/p[@class="title"]
# [Marco:] Author won't work here because the page defines the "home" link under the author's name as rel="author", which always gets priority if the page has defined it.
test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/
|