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/buzzfeed.com.txt vendored Normal file → Executable file
View File

@ -1,15 +1,15 @@
# Creator: Greg Leuch <greg@...>
# It can be messy.
tidy:no
# The basic template.
title: //h1[@data-print='title']
author: //a[@data-print='author']
date: //time[@data-print='date']
body: //div[@data-print='body']
body: //section[@data-print='body']
# For various things...
# Creator: Greg Leuch <greg@...>
# It can be messy.
tidy:no
# The basic template.
title: //h1[@data-print='title']
author: //a[@data-print='author']
date: //time[@data-print='date']
body: //div[@data-print='body']
body: //section[@data-print='body']
# For various things...
strip: *[@data-print="ignore"]
test_url: http://www.buzzfeed.com/hgrant/35-reasons-why-dogs-hate-the-holidays