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 --- inc/3rdparty/site_config/standard/dr.dk.txt | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/dr.dk.txt (limited to 'inc/3rdparty/site_config/standard/dr.dk.txt') diff --git a/inc/3rdparty/site_config/standard/dr.dk.txt b/inc/3rdparty/site_config/standard/dr.dk.txt old mode 100644 new mode 100755 index 7e46b0d6..d8ec1acf --- a/inc/3rdparty/site_config/standard/dr.dk.txt +++ b/inc/3rdparty/site_config/standard/dr.dk.txt @@ -1,9 +1,9 @@ -title: //meta[@property='og:title']/@content -author: //div[@class='articleFunctions']//a -date: //meta[@name='pubdate']/@content - -# Can you strip elements from the body only? It is required here (`//div[@class='articleContent']/p` breaks for some reason) -body: //div[@class='articleContent'] - +title: //meta[@property='og:title']/@content +author: //div[@class='articleFunctions']//a +date: //meta[@name='pubdate']/@content + +# Can you strip elements from the body only? It is required here (`//div[@class='articleContent']/p` breaks for some reason) +body: //div[@class='articleContent'] + tidy: no test_url: http://www.dr.dk/Nyheder/Udland/2011/10/24/150115.htm \ No newline at end of file -- cgit v1.2.3