body: //table[@class='comment-tree'] date: substring-after(//a[contains(@href, 'item?id=')] , 'on ') strip_comments: no strip: //a[. = 'reply'] replace_string("comment"): "commdiv" next_page_link: //a[@class='morelink'] prune: no test_url: https://news.ycombinator.com/item?id=1516461