From 87ed057bf5863c2eb9e8c00529538bda869223f0 Mon Sep 17 00:00:00 2001 From: Stefan Siegl Date: Sun, 5 Jul 2015 16:14:21 +0000 Subject: taz.de: pick first body only + strip ads --- taz.de.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/taz.de.txt b/taz.de.txt index cf85366..a336856 100644 --- a/taz.de.txt +++ b/taz.de.txt @@ -1,8 +1,9 @@ date: //div[@class='secthead'] -body: //div[@class='sectbody'] +body: (//div[@class='sectbody'])[1] title: concat(//div[@class='sectbody']/h4,': ',//div[@class='sectbody']/h1) author: //span[@class='author'] strip: //p[@class='caption'] +strip_id_or_class: ad_bin strip_id_or_class: rack test_url: http://www.taz.de/Protestbewegung-Occupy/!80188/ \ No newline at end of file -- cgit v1.3.1