From c775beb030a6bc01c268343721f04209bc3d5f25 Mon Sep 17 00:00:00 2001 From: Marvin Dickhaus Date: Wed, 8 Oct 2014 23:49:04 +0200 Subject: New config file for echo-online.de A german local news site for south Hessen. --- echo-online.de.txt | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 echo-online.de.txt diff --git a/echo-online.de.txt b/echo-online.de.txt new file mode 100644 index 0000000..e53de23 --- /dev/null +++ b/echo-online.de.txt @@ -0,0 +1,24 @@ +# Author: Marvin Dickhaus +# 2014-10-08 + +#Tidy just messes up the DOM +tidy: no + +title: //h1 +body: //h2 | //div[@id='artikelteaser'] | //div[@id='artikeltext'] + +#Strip +strip_image_src: artikel_a_merken.gif +strip: //div[@class='zusatzinfo'] + +#Author: substring is used to remove the " Von " prefix. +author: substring(//li[@class='artikelautor'], 5) + +date: //li[@class='artikeldatum'] + +#The first two URLs will at some point no longer show +#the full article. There is a time-based paywall +#installed. Using the feed should present valid output +test_url: http://www.echo-online.de/art1231,5503063 +test_url: http://www.echo-online.de/art1168,5502598 +test_url: http://www.echo-online.de/rss/darmstadt.xml -- cgit v1.3.1