From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- nintendoworldreport.com.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 nintendoworldreport.com.txt (limited to 'nintendoworldreport.com.txt') diff --git a/nintendoworldreport.com.txt b/nintendoworldreport.com.txt new file mode 100644 index 0000000..f0e28af --- /dev/null +++ b/nintendoworldreport.com.txt @@ -0,0 +1,13 @@ +body: //div[@id="main"] +title: //div[@id="main"]/h3 + +# Remove ‘Review’ and ‘Wii’. +strip: //div[@class="badge"] + +# Remove duplicate title and country flag. +strip: //h3 + +# Commented out below are attempts to extract the author and date, which did not work. +# author: //p[@class="extra "]/a +# date: //p[@class="extra "]/span[@class="when"] +test_url: http://www.nintendoworldreport.com/review/28400 \ No newline at end of file -- cgit v1.3.1