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/codinghorror.com.txt | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/codinghorror.com.txt (limited to 'inc/3rdparty/site_config/standard/codinghorror.com.txt') diff --git a/inc/3rdparty/site_config/standard/codinghorror.com.txt b/inc/3rdparty/site_config/standard/codinghorror.com.txt new file mode 100644 index 00000000..9c95f107 --- /dev/null +++ b/inc/3rdparty/site_config/standard/codinghorror.com.txt @@ -0,0 +1,15 @@ +body: //div[@class='blogbody'] +strip: //h3[@class='title'] +date: //h2[@class='date'] +#Should Atwood just be a literal? +author: substring-before( substring-after(//div[@class='posted'], 'y'), 'V') + +# tim.kingman@... 2011-07-26 +# Prune:no to retain all-link ULs that are part of the body content like +# http://www.codinghorror.com/blog/2011/07/building-a-pc-part-vii-rebooting.html +# Then explicitly strip the "Posted By" and prev/next links that Prune:yes would have removed. + +prune: no +strip: //div[@class='posted']/following-sibling::* +strip: //div[@class='posted'] +test_url: http://www.codinghorror.com/blog/2011/07/building-a-pc-part-vii-rebooting.html \ No newline at end of file -- cgit v1.2.3