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/techhive.com.txt | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/techhive.com.txt (limited to 'inc/3rdparty/site_config/standard/techhive.com.txt') diff --git a/inc/3rdparty/site_config/standard/techhive.com.txt b/inc/3rdparty/site_config/standard/techhive.com.txt new file mode 100755 index 00000000..29720b0b --- /dev/null +++ b/inc/3rdparty/site_config/standard/techhive.com.txt @@ -0,0 +1,18 @@ +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: //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.techhive.com/article/2010549/up-close-with-blackberry-10.html \ No newline at end of file -- cgit v1.2.3