diff options
Diffstat (limited to 'blogs.scientificamerican.com.txt')
| -rw-r--r-- | blogs.scientificamerican.com.txt | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/blogs.scientificamerican.com.txt b/blogs.scientificamerican.com.txt new file mode 100644 index 0000000..2102015 --- /dev/null +++ b/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 <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/
\ No newline at end of file |