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/newsunspun.org.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/newsunspun.org.txt (limited to 'inc/3rdparty/site_config/standard/newsunspun.org.txt') diff --git a/inc/3rdparty/site_config/standard/newsunspun.org.txt b/inc/3rdparty/site_config/standard/newsunspun.org.txt new file mode 100644 index 00000000..860ad66b --- /dev/null +++ b/inc/3rdparty/site_config/standard/newsunspun.org.txt @@ -0,0 +1,10 @@ +body: //div[@class='right']//div[@class='articles'] +author: //div[@id='artinfo']//a[contains(@href, '/author/')] +strip: //div[@id='artinfo'] +strip: //table[//a[contains(@href, 'twitter.com')]] +strip_id_or_class: twitter + +prune: no +tidy: no + +test_url: http://www.newsunspun.org/eotn/bbc-headline-change-iran-goes-from-not-building-to-undecided-on-nuclear-bomb \ No newline at end of file -- cgit v1.2.3