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/aljazeera.com.txt | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/aljazeera.com.txt (limited to 'inc/3rdparty/site_config/standard/aljazeera.com.txt') diff --git a/inc/3rdparty/site_config/standard/aljazeera.com.txt b/inc/3rdparty/site_config/standard/aljazeera.com.txt new file mode 100644 index 00000000..4f0148f4 --- /dev/null +++ b/inc/3rdparty/site_config/standard/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 v1.2.3