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/msnbc.msn.com.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/msnbc.msn.com.txt (limited to 'inc/3rdparty/site_config/standard/msnbc.msn.com.txt') diff --git a/inc/3rdparty/site_config/standard/msnbc.msn.com.txt b/inc/3rdparty/site_config/standard/msnbc.msn.com.txt new file mode 100644 index 00000000..ad89cda8 --- /dev/null +++ b/inc/3rdparty/site_config/standard/msnbc.msn.com.txt @@ -0,0 +1,21 @@ +title: //title +author: //div[@id='byline'] + +date: //div[contains(@class,'timestamp')]/abbr/text() + +body: //div[@id='intellitTXT'] + +strip: //div[@id='byline'] +strip: //div[contains(@class,'timestamp')] +strip: //div[contains(@class, 'ad-label')] +strip: //div[contains(@class, 'ad-break')] +strip: //span[contains(@class, 'x-video')] +strip: //span[contains(@class, 'inline')] +strip: //div[contains(@class, 'video')] +strip: //div[contains(@class, 'discuss')] +strip: //div[@id='most-popular'] +strip: //div[contains(@class,'drawer')] +strip: //*[contains(@class, 'hide')] + +footnotes: no +test_url: http://www.msnbc.msn.com/id/44748412/ns/business-world_business/#.TolUv-vfDbE \ No newline at end of file -- cgit v1.2.3