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/brookings.edu.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/brookings.edu.txt (limited to 'inc/3rdparty/site_config/standard/brookings.edu.txt') diff --git a/inc/3rdparty/site_config/standard/brookings.edu.txt b/inc/3rdparty/site_config/standard/brookings.edu.txt new file mode 100644 index 00000000..9f4fc4e3 --- /dev/null +++ b/inc/3rdparty/site_config/standard/brookings.edu.txt @@ -0,0 +1,13 @@ +title: //div[@id='contentheader']/h1 +author: //p[@class='attribution']/span[@class='author']/* +# Is there a way to pull multiple authors? My XPath here is just grabbing the first + +date: /html/head/meta[@name="date"]/@content +body: //div[@class='main-content'] + +strip: //p[@class='byline'] +strip: //div[@class='img-gallery'] +strip: //div[@class='callout'] +strip: //div[@class='add-your-view'] +convert_double_br_tags: yes +test_url: http://www.brookings.edu/opinions/2011/1018_cyberattack_libya_goldsmith.aspx \ No newline at end of file -- cgit v1.2.3