From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- brookings.edu.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 brookings.edu.txt (limited to 'brookings.edu.txt') diff --git a/brookings.edu.txt b/brookings.edu.txt new file mode 100644 index 0000000..17a4760 --- /dev/null +++ b/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 v1.3.1