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/news.cnet.com.txt | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/news.cnet.com.txt (limited to 'inc/3rdparty/site_config/standard/news.cnet.com.txt') diff --git a/inc/3rdparty/site_config/standard/news.cnet.com.txt b/inc/3rdparty/site_config/standard/news.cnet.com.txt old mode 100644 new mode 100755 index b7ab224a..78af70f4 --- a/inc/3rdparty/site_config/standard/news.cnet.com.txt +++ b/inc/3rdparty/site_config/standard/news.cnet.com.txt @@ -1,12 +1,12 @@ -#This should apply to *.cnet.com. Not just news.cnet.com. -title: //h1 -author: //img[@class="mugshot"]/@alt -strip: //h1 -strip_id_or_class: breadcrumb -strip: //p[@id="introP"] -strip: //div[@class="postByline"] -strip: //div[@class="editorBio"] -strip: //div[@class="inline-slideshow"] -strip: //div[@class="related"] +#This should apply to *.cnet.com. Not just news.cnet.com. +title: //h1 +author: //img[@class="mugshot"]/@alt +strip: //h1 +strip_id_or_class: breadcrumb +strip: //p[@id="introP"] +strip: //div[@class="postByline"] +strip: //div[@class="editorBio"] +strip: //div[@class="inline-slideshow"] +strip: //div[@class="related"] body: //div[@class="postBody txtWrap"] test_url: http://news.cnet.com/8301-27076_3-57405303-248/apple-ipad-charging-fine-keep-it-plugged-in/?tag=mncol;posts \ No newline at end of file -- cgit v1.2.3