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/dr.dk.txt | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..7e46b0d6 --- /dev/null +++ b/inc/3rdparty/site_config/standard/dr.dk.txt @@ -0,0 +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'] + +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