aboutsummaryrefslogblamecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt
blob: 2102015d9e0db1c66cb26f2fbfc8e5de137f6671 (plain) (tree)
1
2
3
4
5
6
7
8
9
10
11
12
13
14













                                                                             

                                                                                                                       
# 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 <div> 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/