updated specific configuration for parsing

This commit is contained in:
Nicolas Lœuillet
2014-07-13 10:15:40 +02:00
parent 58dbe10388
commit 4e067ceabd
952 changed files with 7585 additions and 5682 deletions

26
inc/3rdparty/site_config/standard/codinghorror.com.txt vendored Normal file → Executable file
View File

@ -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