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/rogerebert.com.txt | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/rogerebert.com.txt (limited to 'inc/3rdparty/site_config/standard/rogerebert.com.txt') diff --git a/inc/3rdparty/site_config/standard/rogerebert.com.txt b/inc/3rdparty/site_config/standard/rogerebert.com.txt old mode 100644 new mode 100755 index 26792330..da215109 --- a/inc/3rdparty/site_config/standard/rogerebert.com.txt +++ b/inc/3rdparty/site_config/standard/rogerebert.com.txt @@ -1,8 +1,8 @@ -title: substring-before(//title,':') -author: substring-after(substring-before(//div[@class='text']/b,'/'),'BY') - -body: //div[@class='text'] - -strip: //a[contains(@href,'printart')] +title: substring-before(//title,':') +author: substring-after(substring-before(//div[@class='text']/b,'/'),'BY') + +body: //div[@class='text'] + +strip: //a[contains(@href,'printart')] strip_id_or_class: enlarge_photo test_url: http://rogerebert.com/apps/pbcs.dll/article?AID=/20120411/REVIEWS/120419998/1005/GLOSSARY \ No newline at end of file -- cgit v1.2.3