From c78c1a3f08815aab99752026ccdf1dcf63cf43c1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Mon, 19 Jan 2015 21:27:22 +0100 Subject: @fivefilters via composer --- .../site_config/standard/smithsonianmag.com.txt | 20 -------------------- 1 file changed, 20 deletions(-) delete mode 100755 inc/3rdparty/site_config/standard/smithsonianmag.com.txt (limited to 'inc/3rdparty/site_config/standard/smithsonianmag.com.txt') diff --git a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt deleted file mode 100755 index 3e8fee95..00000000 --- a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt +++ /dev/null @@ -1,20 +0,0 @@ -# meta data -title://h1[@id = 'articleTitle'] -author:substring-after(//ul[@id = 'byLine']/li[1],'By ') -date:substring-before(substring-after(//ul[@id = 'byLine']/li[last()],','),',') -body://div[@id = 'article-body'] - -# full content -single_page_link://td/li[@class = 'article-singlepage']/a - -# caption clean up -wrap_in(i)://span[@class='articleImageCaptionwide'] -move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p - - -# clean up -strip://p[@id = 'articlePaginationWrapper'] -strip://ul[contains(@class, 'cat-breadcrumb')] -strip://div [@class= 'viewMorePhotos'] - -test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html \ No newline at end of file -- cgit v1.2.3