From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/allthingsd.com.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/allthingsd.com.txt (limited to 'inc/3rdparty/site_config/standard/allthingsd.com.txt') diff --git a/inc/3rdparty/site_config/standard/allthingsd.com.txt b/inc/3rdparty/site_config/standard/allthingsd.com.txt new file mode 100644 index 00000000..cd52498f --- /dev/null +++ b/inc/3rdparty/site_config/standard/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 v1.2.3