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 --- .../standard/sportsillustrated.cnn.com.txt | 26 ++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/sportsillustrated.cnn.com.txt (limited to 'inc/3rdparty/site_config/standard/sportsillustrated.cnn.com.txt') diff --git a/inc/3rdparty/site_config/standard/sportsillustrated.cnn.com.txt b/inc/3rdparty/site_config/standard/sportsillustrated.cnn.com.txt new file mode 100644 index 00000000..afc5879f --- /dev/null +++ b/inc/3rdparty/site_config/standard/sportsillustrated.cnn.com.txt @@ -0,0 +1,26 @@ +# main sportsillustrated.com articles +# +body: //div[@id="cnnStoryContent"] +title: //div[@id="cnnStoryHeadline"]//h1 +author: //div[@id="cnnSubBanner"]//strong +date: substring-after(//div[@id="cnnTimeStamp"], "Updated: ") +date: substring-after(//div[@id="cnnTimeStamp"], "Posted: ") + +# kill ugly font buttons +strip: //div[@id="cnnSCFontButtons"] + +# kill misc filler videos & etc +strip: //div[@class="cnnDivideContent"] +strip: //*[@class="cnnTMbox"] + +# si vault articles +# ------------- +body: //div[@class="siv_artPara"] +title: //div[@class="siv_artHeader"]//h1 +author: //div[@class="byline"] +date: //div[@class="date"] + +next_page_link: //div[@id='cnnStoryContinue']/a +strip_id_or_class: cnnstorypagination + +test_url: http://sportsillustrated.cnn.com/2012/writers/peter_king/02/27/combine/index.html \ No newline at end of file -- cgit v1.2.3