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/macworld.com.txt | 24 ++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/macworld.com.txt (limited to 'inc/3rdparty/site_config/standard/macworld.com.txt') diff --git a/inc/3rdparty/site_config/standard/macworld.com.txt b/inc/3rdparty/site_config/standard/macworld.com.txt new file mode 100644 index 00000000..96175872 --- /dev/null +++ b/inc/3rdparty/site_config/standard/macworld.com.txt @@ -0,0 +1,24 @@ +title: //article//h1 +date: //meta[@name="date"]/@content +author: //div[@class="author-name" or @class="article-byline"]/a[1] + +body: //section[@class="page"] + +# 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"] + +prune: no + +# copes less well with Review pages, seems fine for News +test_url: http://www.macworld.com/article/163184/2011/10/the_ipod_as_an_iconic_cultural_force.html \ No newline at end of file -- cgit v1.2.3