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/stalbansreview.co.uk.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt (limited to 'inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt') diff --git a/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt b/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt new file mode 100644 index 00000000..bde14217 --- /dev/null +++ b/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt @@ -0,0 +1,14 @@ +title: //div[@class='articleLeft']/h3 + +author: substring-after(//span[@class='articleAuthor']/a,'By ') + +date: substring-before(//span[@class='articleDateTime'],'in ') + +body: //div[@class='articleLeft'] +strip: //div[@class='articleMoreNews'] +strip: //div[@class='articleLeft']/h3 +strip: //div[@class='articleLeft']/p[@class='articleInfo clearfix'] + +# Remove duplicate title from text +strip: //div[@id='site']/div[5][@class='holder']/div[1][@class='hBlock']/div[1][@class='sglCol article']/h3 +test_url: http://www.stalbansreview.co.uk/news/9581446.New_roundabout_in_King_Harry_Lane/r/?ref=rss \ No newline at end of file -- cgit v1.2.3