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 --- inc/3rdparty/site_config/standard/reuters.com.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/reuters.com.txt (limited to 'inc/3rdparty/site_config/standard/reuters.com.txt') diff --git a/inc/3rdparty/site_config/standard/reuters.com.txt b/inc/3rdparty/site_config/standard/reuters.com.txt old mode 100644 new mode 100755 index c5c94a4f..7411e62b --- a/inc/3rdparty/site_config/standard/reuters.com.txt +++ b/inc/3rdparty/site_config/standard/reuters.com.txt @@ -1,10 +1,10 @@ -title: //h1[@class='headline3'] -author: substring-after(//p[@class="byline"], 'By ') -date: //meta[@name="REVISION_DATE"]/@content -body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] -strip: //li[@class='next'] -strip: //span[@class='articleLocation'] -prune: no -tidy: no - +title: //h1[@class='headline3'] +author: substring-after(//p[@class="byline"], 'By ') +date: //meta[@name="REVISION_DATE"]/@content +body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] +strip: //li[@class='next'] +strip: //span[@class='articleLocation'] +prune: no +tidy: no + test_url: http://www.reuters.com/article/2011/04/08/us-ivorycoast-killings-idUSTRE73732A20110408 \ No newline at end of file -- cgit v1.2.3