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/historytoday.com.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/historytoday.com.txt (limited to 'inc/3rdparty/site_config/standard/historytoday.com.txt') diff --git a/inc/3rdparty/site_config/standard/historytoday.com.txt b/inc/3rdparty/site_config/standard/historytoday.com.txt old mode 100644 new mode 100755 index dc687f3f..78fb60a6 --- a/inc/3rdparty/site_config/standard/historytoday.com.txt +++ b/inc/3rdparty/site_config/standard/historytoday.com.txt @@ -1,10 +1,10 @@ -body://div[@id = 'content'] -author://span[@class = 'authors'] -author://span[@class = 'ht-vtag'][1] -date:substring-before(//meta[@name = 'dc.date']/@content,'T') -strip://div[contains(@class, 'region-ubercontent')] -strip://h1 -strip://div[@id = 'ht-author'] -strip://ul[@class = 'links inline'] -strip://div[@id = 'ht-tools'] +body://div[@id = 'content'] +author://span[@class = 'authors'] +author://span[@class = 'ht-vtag'][1] +date:substring-before(//meta[@name = 'dc.date']/@content,'T') +strip://div[contains(@class, 'region-ubercontent')] +strip://h1 +strip://div[@id = 'ht-author'] +strip://ul[@class = 'links inline'] +strip://div[@id = 'ht-tools'] test_url: http://www.historytoday.com/carol-dyhouse/skin-deep-fall-fur \ No newline at end of file -- cgit v1.2.3