From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- .../site_config/standard/stalbansreview.co.uk.txt | 26 +++++++++++----------- 1 file changed, 13 insertions(+), 13 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index bde14217..a0f1587c --- a/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt +++ b/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt @@ -1,14 +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 +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