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 --- .../standard/blogs.scientificamerican.com.txt | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt (limited to 'inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt') diff --git a/inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt b/inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt new file mode 100644 index 00000000..a7d15081 --- /dev/null +++ b/inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt @@ -0,0 +1,16 @@ +# meta data +title://h1[@class = 'postTitle'] +author:substring-before(substring-after(//span[@class = 'byline'],'By '),'|') +date://span[@class = 'datestamp'] + +#body content +body://div[@id = 'singleBlogPost'] + +#reclaim author info +move_into(//div[@id = 'singleBlogPost'])://div[@id = 'aboutAuthorDiv'] +strip://p[@class = 'moreLink mobileHide'] + +#cleanup comments, there might be some open
sections +strip://div[@id = 'comments2'] +strip://h3[a[@href = '#add-comment']] +test_url: http://blogs.scientificamerican.com/a-blog-around-the-clock/2012/07/10/science-blogs-definition-and-a-history/ \ No newline at end of file -- cgit v1.2.3