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 --- inc/3rdparty/site_config/standard/guokr.com.txt | 42 ++++++++++++------------- 1 file changed, 21 insertions(+), 21 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/guokr.com.txt (limited to 'inc/3rdparty/site_config/standard/guokr.com.txt') diff --git a/inc/3rdparty/site_config/standard/guokr.com.txt b/inc/3rdparty/site_config/standard/guokr.com.txt old mode 100644 new mode 100755 index 00255eb8..f8327bea --- a/inc/3rdparty/site_config/standard/guokr.com.txt +++ b/inc/3rdparty/site_config/standard/guokr.com.txt @@ -1,22 +1,22 @@ -# To administrator: -# Please change the hostname to "www.guokr.com/article/*" -# Not working for "www.guokr.com/post/" pages configured by carlosliu913@gmail.com - -# This filter is tested on: -# http://www.guokr.com/article/274325/ -# http://www.guokr.com/article/275013/ - -title://h1 -author://div[contains(@class, 'content-th-info')]/a -date://div[contains(@class, 'content-th-info')]/span -body://div[contains(@class, 'Content')] - -strip://div[contains(@class, 'bottom-i')] -strip://div[contains(@class, 'copyright')] -strip://div[contains(@class, 'fr')] -strip://div[contains(@class, 'content-th-info')] -strip://h1[contains(@id, 'articleTitle')] -strip://div[contains(@class, 'side')] -strip://div[contains(@class, 'top-wp')] -test_url: http://www.guokr.com/article/275013/ +# To administrator: +# Please change the hostname to "www.guokr.com/article/*" +# Not working for "www.guokr.com/post/" pages configured by carlosliu913@gmail.com + +# This filter is tested on: +# http://www.guokr.com/article/274325/ +# http://www.guokr.com/article/275013/ + +title://h1 +author://div[contains(@class, 'content-th-info')]/a +date://div[contains(@class, 'content-th-info')]/span +body://div[contains(@class, 'Content')] + +strip://div[contains(@class, 'bottom-i')] +strip://div[contains(@class, 'copyright')] +strip://div[contains(@class, 'fr')] +strip://div[contains(@class, 'content-th-info')] +strip://h1[contains(@id, 'articleTitle')] +strip://div[contains(@class, 'side')] +strip://div[contains(@class, 'top-wp')] +test_url: http://www.guokr.com/article/275013/ test_url: http://www.guokr.com/article/338387/ \ No newline at end of file -- cgit v1.2.3