11 lines
663 B
Plaintext
Executable File
11 lines
663 B
Plaintext
Executable File
title: //h1[@id='articlehed'] | //h2[@id="articleintro"]
|
|
body: //div[@id='articletext']
|
|
|
|
strip: //ul[@id="bc"] | //div[@id="yrail"] | //div[@class="entry-keywords"] | //div[@class="entry-categories"] | //div[@class="socialUtils"] | //div[@id="footer"] | //div[@class="cartoon"]
|
|
|
|
date: //h4[@id='articleauthor']/span[@class='dd dds']
|
|
date: //div[@id="pagebody"]/div[@class='hentry entry']/div[@class='published']
|
|
|
|
single_page_link: //div[@class='paginationViewSinglePage']/a
|
|
test_url: http://www.newyorker.com/online/blogs/culture/2012/06/mug-shot-web-sites.html
|
|
test_url: http://www.newyorker.com/reporting/2013/04/22/130422fa_fact_bilger?currentPage=all&mobify=0 |