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/codinghorror.com.txt | 26 +++++++++++----------- 1 file changed, 13 insertions(+), 13 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 9c95f107..adf6e5a0 --- a/inc/3rdparty/site_config/standard/codinghorror.com.txt +++ b/inc/3rdparty/site_config/standard/codinghorror.com.txt @@ -1,15 +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::* +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