From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- aljazeera.com.txt | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 aljazeera.com.txt (limited to 'aljazeera.com.txt') diff --git a/aljazeera.com.txt b/aljazeera.com.txt new file mode 100644 index 0000000..d3bf401 --- /dev/null +++ b/aljazeera.com.txt @@ -0,0 +1,8 @@ +title: //span[@id='DetailedTitle'] +body: //td[@id='tdTextContent'] +strip_id_or_class: Skyscrapper_Body +date: //span[@id='ctl00_cphBody_lblDate'] +author: //div[@id="dvAuthorInfo"]//a/text() +strip: //table[ tbody/tr/td/object ] +prune: no +test_url: http://www.aljazeera.com/indepth/opinion/2012/01/2012114121925380575.html \ No newline at end of file -- cgit v1.3.1