高端网站建设-写了段批量抓取某个列表页的东东

dim content_pagecode,content_tempcode

dim content_categoryid,content_categoryname,borderid,classid,bordername,classname

dim articletitle,articleauthor,articlefrom,articlecontent

url = "http://www.webasp.net/article/class/1.htm"

list_pagecode = gethttppage(url)

list_pagecode = regexptext(list_pagecode,"打印</th></tr>","</table><table border=0 cellpadding=5",0)

list_pagecode = regexptext(list_pagecode,"<td align=left><a href="../",""><img border=0 src="../images/authortype0.gif"",1) "取得当前列表页的文章链接，以,分隔

array_articleid = split(list_pagecode,",") "创建数组，存储文章id

for i=0 to ubound(array_articleid)-1

articleid = array_articleid(i) "文章id

content_pagecode = gethttppage("http://www.webasp.net/article/"&articleid) "取得文章页的内容

"=========取文章分类及相关id参数 开始=======================

content_tempcode = regexptext(content_pagecode,"<a href=""/article/"">技术教程</a> >> ",">> 内容</td>",0)

content_categoryid = regexptext(content_pagecode,"<a href="../class","/">",1)

borderid = split(content_categoryid,",")(0) "大类id

classid = split(content_categoryid,",")(1) "子类id

"==========检查大类是否存在 开始===============

"如果不存在则入库

"==========检查大类是否存在 结束===============

"response.write(borderid & "," & classid & "<br />")

content_categoryname = regexptext(content_pagecode,"/">","</a>",1)

bordername = split(content_categoryname,",")(0) "大类名称

classname = split(content_categoryname,",")(1) "子类名称

"==========检查子类是否存在 开始===============

"如果不存在则入库

"==========检查子类是否存在 结束===============

"=========取文章分类及相关id参数 结束=======================

"=========取文章标题及内容 开始=============================

articletitle = regexptext(content_pagecode,"<tr><td align=center bgcolor=#dee2f5><strong>","</strong></td></tr>",0)

articleauthor = regexptext(content_pagecode,"<tr><td><span class=blue>作者：</span>","</td></tr>",0)

articlefrom = regexptext(content_pagecode,"<tr><td><span class=blue>来源：</span>","</td></tr>",0)

articlecontent = regexptext(content_pagecode,"<tr><td class=content style=""word-wrap: break-word"" id=zoom>","</td></tr>"&vbcrlf&" </table>"&vbcrlf&" </td></tr></table>",0)

"=========取文章标题及内容 结束=============================

response.write(articletitle& "<br /><br />")

response.flush()

next

附几个函数：

function gethttppage(url) 

if(isobjinstalled("microsoft.xmlhttp") = false)then

response.write "<br><br>服务器不支持microsoft.xmlhttp组件" 

err.clear

response.end

end if

on error resume next

dim http 

set http=server.createobject("msxml2.xmlhttp") 

http.open "get",url,false 

http.send() 

if(http.readystate<>4)then

exit function 

end if 

gethttppage=bytestobstr(http.responsebody,"gb2312")

set http=nothing

if(err.number<>0)then

response.write "<br><br>获取文件内容出错" 

"response.end

err.clear

end if 

end function

function bytestobstr(codebody,codeset)

dim objstream

set objstream = server.createobject("adodb.stream")

objstream.type = 1

objstream.mode =3

objstream.open

objstream.write codebody

objstream.position = 0

objstream.type = 2

objstream.charset = codeset

bytestobstr = objstream.readtext 

objstream.close

set objstream = nothing

end function^^^^^6

高端网站建设价格套餐：

500元成品模板网站套餐1000元基础型网站套餐1800元标准定制设计套餐2800元精美定制设计套餐3800-8000元商务型套餐行业门户型套餐其它定制套餐 文章由重庆一佰互联高端网站建设http://www.rzxsoft.cn编辑整理，转载请注明出处