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/businessinsider.com.txt | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/businessinsider.com.txt (limited to 'inc/3rdparty/site_config/standard/businessinsider.com.txt') diff --git a/inc/3rdparty/site_config/standard/businessinsider.com.txt b/inc/3rdparty/site_config/standard/businessinsider.com.txt new file mode 100644 index 00000000..c773db8b --- /dev/null +++ b/inc/3rdparty/site_config/standard/businessinsider.com.txt @@ -0,0 +1,12 @@ +title://div[@class="sl-layout-post"]/h1 +body: //div[contains(@class, 'post-content') or contains(@class, 'KonaBody')] +strip: //div[contains(@class, "post-sidebar")] +strip: //div[@id='related-links'] +author://div[@class="byline"]/a +date://div[@class="byline"]/span[@class="date"] +prune: no + +strip://*[contains(@class,'sponsored-text')] +strip: //div[@id='post_footer'] + +test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1 \ No newline at end of file -- cgit v1.2.3