wallabag/inc/3rdparty/site_config/standard/blogs.scientificamerican.com.txt
2014-07-13 10:15:40 +02:00

16 lines
No EOL
591 B
Text
Executable file

# 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/