From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/pcworld.com.txt | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..30ccbb5f --- /dev/null +++ b/inc/3rdparty/site_config/standard/pcworld.com.txt @@ -0,0 +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"] +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