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/guokr.com.txt | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..00255eb8 --- /dev/null +++ b/inc/3rdparty/site_config/standard/guokr.com.txt @@ -0,0 +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/ +test_url: http://www.guokr.com/article/338387/ \ No newline at end of file -- cgit v1.2.3