2014-07-13 04:15:40 -04:00
|
|
|
# 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']
|
2013-12-06 04:13:03 -05:00
|
|
|
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/
|
