www.searchengineguide.com~2

垂直搜索的网络爬虫

define pattern year="[0-9][0-9][0-9][0-9]"
do (a)-(b).$startwith"By"-.-year.-(c).$until[-,$startwith"Discuss this article "](d);(e)-(d).$l("title",(a)).$l("text",(c),(e)).$l("_new",(a),(e))
do (a).$to.text.(b).(c)link(d).$l("li",(d))$l("_li",(a),(d))
set article=_new[title,text,link?=_li.li]
output article