From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- allthingsd.com.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 allthingsd.com.txt (limited to 'allthingsd.com.txt') diff --git a/allthingsd.com.txt b/allthingsd.com.txt new file mode 100644 index 0000000..581f9da --- /dev/null +++ b/allthingsd.com.txt @@ -0,0 +1,10 @@ +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/ \ No newline at end of file -- cgit v1.3.1