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/collegehumor.com.txt | 24 +++++++++++----------- 1 file changed, 12 insertions(+), 12 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/collegehumor.com.txt (limited to 'inc/3rdparty/site_config/standard/collegehumor.com.txt') diff --git a/inc/3rdparty/site_config/standard/collegehumor.com.txt b/inc/3rdparty/site_config/standard/collegehumor.com.txt old mode 100644 new mode 100755 index 9d75d641..318e6ff4 --- a/inc/3rdparty/site_config/standard/collegehumor.com.txt +++ b/inc/3rdparty/site_config/standard/collegehumor.com.txt @@ -1,14 +1,14 @@ -title: //h1[@class='title'] -author: //p[@class='byline']/a[1] -date: //*[@class='date'] - -body: //div[@class='article_body'] -strip: //p[@class='ca_intro'] -strip: //div[@id='action_bar'] -strip: //div[@class='below_content'] -strip: //div[@id='announcement'] -strip: //div[@id='leftovers'] -strip: //div[@class='form'] -strip: //div[@id='email_overlay'] +title: //h1[@class='title'] +author: //p[@class='byline']/a[1] +date: //*[@class='date'] + +body: //div[@class='article_body'] +strip: //p[@class='ca_intro'] +strip: //div[@id='action_bar'] +strip: //div[@class='below_content'] +strip: //div[@id='announcement'] +strip: //div[@id='leftovers'] +strip: //div[@class='form'] +strip: //div[@id='email_overlay'] strip: //a[@class='close'] test_url: http://www.collegehumor.com/article/6599562/how-it-happened-the-necktie \ No newline at end of file -- cgit v1.2.3