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/inc.com.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/inc.com.txt (limited to 'inc/3rdparty/site_config/standard/inc.com.txt') diff --git a/inc/3rdparty/site_config/standard/inc.com.txt b/inc/3rdparty/site_config/standard/inc.com.txt new file mode 100644 index 00000000..0589aaae --- /dev/null +++ b/inc/3rdparty/site_config/standard/inc.com.txt @@ -0,0 +1,21 @@ +author: substring-after(substring-before(//div[@id='byline'],'|'),'By') +author: //div[@class='byline']/a +date: //span[@class='pubdate'] +# print friendly page +body: //div[@id='text'] +# regular page +body: //div[@id= 'articlecontent'] + +strip: //div[@id= 'articlecontent']/h1 +strip: //div[@id='articlecontent']/p[@class='deck'] +strip: //div[@id='articlecontent']/div[@class='byline'] +strip: //div[@id='articlespacer'] +strip: //div[@id='incsharebox'] +strip: //div[@id='articlesidebar'] + +prune: no + +single_page_link: //a[contains(@href, 'Printer_Friendly.html')] +strip: //a[contains(., 'Dig Deeper')] +test_url: http://www.inc.com/guides/2010/11/seven-tips-for-lobbying-politicians.html +test_url: http://www.inc.com/eric-schurenberg/startups-are-we-geting-irrationally-exuberant.html \ No newline at end of file -- cgit v1.2.3