From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- .../site_config/standard/allthingsd.com.txt | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index cd52498f..f8c67d02 --- a/inc/3rdparty/site_config/standard/allthingsd.com.txt +++ b/inc/3rdparty/site_config/standard/allthingsd.com.txt @@ -1,10 +1,13 @@ -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"] +title://div[@class="article-title"]/h1[@class="title"] +date: //p[@class="article-date"] +body://div[contains(@class, "article-body")] +# Trim out related posts at bottom of article +strip://blockquote[@class="memo"] + +tidy: no + +# 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 +test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/ +test_url: http://allthingsd.com/20131010/google-cio-ben-fried-on-how-google-works/ \ No newline at end of file -- cgit v1.2.3