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/anandtech.com.txt | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/anandtech.com.txt (limited to 'inc/3rdparty/site_config/standard/anandtech.com.txt') diff --git a/inc/3rdparty/site_config/standard/anandtech.com.txt b/inc/3rdparty/site_config/standard/anandtech.com.txt old mode 100644 new mode 100755 index 8067e03c..7d804918 --- a/inc/3rdparty/site_config/standard/anandtech.com.txt +++ b/inc/3rdparty/site_config/standard/anandtech.com.txt @@ -1,11 +1,11 @@ -author: //a[@class='b'][1] -date: substring-after(substring-before(//div, 'Posted in'), ' on ') -strip_image_src: /content/images/globals/ -strip: //h2[. = 'Page 1']/preceding::p -strip: //h2 - -prune: no - -single_page_link: concat('http://www.anandtech.com/print/', substring-after(//meta[@property='og:url']/@content, '/show/')) - +author: //a[@class='b'][1] +date: substring-after(substring-before(//div, 'Posted in'), ' on ') +strip_image_src: /content/images/globals/ +strip: //h2[. = 'Page 1']/preceding::p +strip: //h2 + +prune: no + +single_page_link: concat('http://www.anandtech.com/print/', substring-after(//meta[@property='og:url']/@content, '/show/')) + test_url: http://www.anandtech.com/show/5812/eurocom-monster-10-clevos-little-monster/ \ No newline at end of file -- cgit v1.2.3