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 --- .../site_config/standard/abcnews.go.com.txt | 27 ++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/abcnews.go.com.txt (limited to 'inc/3rdparty/site_config/standard/abcnews.go.com.txt') diff --git a/inc/3rdparty/site_config/standard/abcnews.go.com.txt b/inc/3rdparty/site_config/standard/abcnews.go.com.txt new file mode 100644 index 00000000..c515d3e4 --- /dev/null +++ b/inc/3rdparty/site_config/standard/abcnews.go.com.txt @@ -0,0 +1,27 @@ +title: //h1[@class='headline'] +body: //div[@id='storyText'] +# for video entries +body: //img[@id='ff-img'] | //div[@id='meta']//div[contains(@class, 'overview')] +author: //div[@class='byline'] +date: //div[@class='date'] +strip: //*[@id='date_partner'] + +strip: //div[@class='breadcrumb'] +strip: //div[contains(@class,'show_tools')] +strip: //div[@id='sponsoredByAd'] +strip: //div[contains(@class,'rel_container')] +strip: //p[a[starts-with(@href, 'http://www.twitter.com')]] +strip: //p[a[starts-with(@href, 'http://www.facebook.com')]] +strip: //p[contains(., 'Click here to return to')] +#strip_id_or_class: media +strip_id_or_class: mediaplayer + +replace_string(