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/newsmill.se.txt | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/newsmill.se.txt (limited to 'inc/3rdparty/site_config/standard/newsmill.se.txt') diff --git a/inc/3rdparty/site_config/standard/newsmill.se.txt b/inc/3rdparty/site_config/standard/newsmill.se.txt new file mode 100644 index 00000000..eb7d3350 --- /dev/null +++ b/inc/3rdparty/site_config/standard/newsmill.se.txt @@ -0,0 +1,12 @@ +title: //h1 +body: (//div[@class='articleImg']//img)[1] | //p[contains(@class, 'commentTextArticle') or contains(@class, 'articlePublished')] | //div[@id='articleLeftContent'] +author: //div[@class='byline']//a[contains(@href, '/user/')] + +strip_id_or_class: facts +strip_id_or_class: articleBlogsHolder +strip_id_or_class: byline + +prune: no +tidy: no + +test_url: http://www.newsmill.se/artikel/2012/05/06/medielogiken-v-ger-tyngre-n-reportrarnas-sikter \ No newline at end of file -- cgit v1.2.3