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/searchengineland.com.txt | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/searchengineland.com.txt (limited to 'inc/3rdparty/site_config/standard/searchengineland.com.txt') diff --git a/inc/3rdparty/site_config/standard/searchengineland.com.txt b/inc/3rdparty/site_config/standard/searchengineland.com.txt new file mode 100644 index 00000000..f176d7c7 --- /dev/null +++ b/inc/3rdparty/site_config/standard/searchengineland.com.txt @@ -0,0 +1,20 @@ +body: //div[@class="storyBox"] +title: //div[@class="storyBox"]/h1 +author: //a[@rel="author"] +date: substring-before(//span[@class="dateline"], 'by') + +#Removes related content but cleans up article text +strip: //h1 +strip: //p[@class="homeStory tdmSideInfo"] +strip: //div[@id="bylineShare"] +strip: //script +strip: //hr + +strip_id_or_class: homeStory +strip_id_or_class: authorpic +strip_id_or_class: insideComments +strip_id_or_class: authorbio +strip_id_or_class: gpt-ad-sel-cube +strip_id_or_class: smxTextAd + +test_url: http://searchengineland.com/googles-jaw-dropping-sponsored-post-campaign-for-chrome-106348 \ No newline at end of file -- cgit v1.2.3