From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- dr.dk.txt | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 dr.dk.txt (limited to 'dr.dk.txt') diff --git a/dr.dk.txt b/dr.dk.txt new file mode 100644 index 0000000..d8ec1ac --- /dev/null +++ b/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 v1.3.1