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/pcworld.com.txt | 36 +++++++++++------------ 1 file changed, 18 insertions(+), 18 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/pcworld.com.txt (limited to 'inc/3rdparty/site_config/standard/pcworld.com.txt') diff --git a/inc/3rdparty/site_config/standard/pcworld.com.txt b/inc/3rdparty/site_config/standard/pcworld.com.txt old mode 100644 new mode 100755 index 30ccbb5f..7193f87e --- a/inc/3rdparty/site_config/standard/pcworld.com.txt +++ b/inc/3rdparty/site_config/standard/pcworld.com.txt @@ -1,19 +1,19 @@ -title: //div[@class='articleHead']//h1 -author: //div[@class="author-name"]/a[1] -body: //div[@class="main"] - -# remove 'From the Lab' and 'Recent posts' text -strip: //div[@class='blogLabel'] - -# remove byline and meta info -strip: //h1 -strip: //div[@class="article-meta"] -strip: //div[@class="author-info"] - -#strip tags and categories -strip: //div[@class="department"] - -#strip product cap links -strip: //div[@class="cap-main"] -strip: //div[@id="compare-lede"] +title: //div[@class='articleHead']//h1 +author: //div[@class="author-name"]/a[1] +body: //div[@class="main"] + +# remove 'From the Lab' and 'Recent posts' text +strip: //div[@class='blogLabel'] + +# remove byline and meta info +strip: //h1 +strip: //div[@class="article-meta"] +strip: //div[@class="author-info"] + +#strip tags and categories +strip: //div[@class="department"] + +#strip product cap links +strip: //div[@class="cap-main"] +strip: //div[@id="compare-lede"] test_url: http://www.pcworld.com/article/262034/are-printer-companies-gouging-us-on-laser-toner-pricing.html \ No newline at end of file -- cgit v1.2.3