Asp 使用 Microsoft.XMLHTTP 抓取网页内容(没用乱码),并过滤需要的内容
示例源码:
复制代码 代码如下:
<%
Dim xmlUrl,http,strHTML,strBody
xmlUrl = Request.QueryString("u")
REM 异步读取XML源
Set http = server.CreateObject("Microsoft.XMLHTTP")
http.Open "POST",xmlUrl,false
http.setrequestheader "User-Agent", "Mozilla/4.0"
http.setrequestheader "Connection", "Keep-Alive"
http.setRequestHeader "Content-Type", "application/x-www-form-urlencoded"
http.Send()
strHTML = BytesToBstr(http.ResponseBody)
set http = nothing
REM 抓取主要内容
strBody = GetBody(strHTML,"<div id=""Div_newsContentc"" class=""cnt"">","</div>",0,0)
strBody =Replace(strBody,"(本文首发于","")
strBody =Replace(strBody,"财富动力网</a>,转载请注明出处。)","")
strBody =Replace(strBody,"本文首发于,转载请注明出处。)","")
strBody =Replace(strBody,"财富动力网</a>:http://www.927953.com","")
strBody =Replace(strBody,"本文首发于","")
Response.Write RegRemoveHref(strBody)
REM 获取对应网址响应的HTML
Function BytesToBstr(body)
dim objstream
set objstream = Server.CreateObject("adodb.stream")
objstream.Type = 1
objstream.Mode =3
objstream.Open
objstream.Write body
objstream.Position = 0
objstream.Type = 2
objstream.Charset = "UTF-8"
'转换原来默认的UTF-8编码转换成GB2312编码,否则直接用
'XMLHTTP调用有中文字符的网页得到的将是乱码
BytesToBstr = objstream.ReadText
objstream.Close
set objstream = nothing
End Function
REM 使用正则表达式,抓取之内标记的内容
Function GetBody(ConStr,StartStr,OverStr,IncluL,IncluR)
If ConStr="$False$" or ConStr="" or IsNull(ConStr)=True Or StartStr="" or IsNull(StartStr)=True Or OverStr="" or IsNull(OverStr)=True Then
GetBody="$False$"
Exit Function
End If
Dim ConStrTemp
Dim Start,Over
ConStrTemp=Lcase(ConStr)
StartStr=Lcase(StartStr)
OverStr=Lcase(OverStr)
Start = InStrB(1, ConStrTemp, StartStr, vbBinaryCompare)
If Start<=0 then
GetBody="$False$"
Exit Function
Else
If IncluL=False Then
Start=Start+LenB(StartStr)
End If
End If
Over=InStrB(Start,ConStrTemp,OverStr,vbBinaryCompare)
If Over<=0 Or Over<=Start then
GetBody="$False$"
Exit Function
Else
If IncluR=True Then
Over=Over+LenB(OverStr)
End If
End If
GetBody=MidB(ConStr,Start,Over-Start)
End Function
REM 过滤a超链接
Function RegRemoveHref(HTMLstr)
Set ra = New RegExp
ra.IgnoreCase = True
ra.Global = True
ra.Pattern = "<a[^>]+>(.+?)<\/a>"
RegRemoveHref = Replace(ra.replace(HTMLstr,"$1"),"href=""http://www.927953.com""","")
END Function
%>
效果图如下:
示例源码:
复制代码 代码如下:
<%
Dim xmlUrl,http,strHTML,strBody
xmlUrl = Request.QueryString("u")
REM 异步读取XML源
Set http = server.CreateObject("Microsoft.XMLHTTP")
http.Open "POST",xmlUrl,false
http.setrequestheader "User-Agent", "Mozilla/4.0"
http.setrequestheader "Connection", "Keep-Alive"
http.setRequestHeader "Content-Type", "application/x-www-form-urlencoded"
http.Send()
strHTML = BytesToBstr(http.ResponseBody)
set http = nothing
REM 抓取主要内容
strBody = GetBody(strHTML,"<div id=""Div_newsContentc"" class=""cnt"">","</div>",0,0)
strBody =Replace(strBody,"(本文首发于","")
strBody =Replace(strBody,"财富动力网</a>,转载请注明出处。)","")
strBody =Replace(strBody,"本文首发于,转载请注明出处。)","")
strBody =Replace(strBody,"财富动力网</a>:http://www.927953.com","")
strBody =Replace(strBody,"本文首发于","")
Response.Write RegRemoveHref(strBody)
REM 获取对应网址响应的HTML
Function BytesToBstr(body)
dim objstream
set objstream = Server.CreateObject("adodb.stream")
objstream.Type = 1
objstream.Mode =3
objstream.Open
objstream.Write body
objstream.Position = 0
objstream.Type = 2
objstream.Charset = "UTF-8"
'转换原来默认的UTF-8编码转换成GB2312编码,否则直接用
'XMLHTTP调用有中文字符的网页得到的将是乱码
BytesToBstr = objstream.ReadText
objstream.Close
set objstream = nothing
End Function
REM 使用正则表达式,抓取之内标记的内容
Function GetBody(ConStr,StartStr,OverStr,IncluL,IncluR)
If ConStr="$False$" or ConStr="" or IsNull(ConStr)=True Or StartStr="" or IsNull(StartStr)=True Or OverStr="" or IsNull(OverStr)=True Then
GetBody="$False$"
Exit Function
End If
Dim ConStrTemp
Dim Start,Over
ConStrTemp=Lcase(ConStr)
StartStr=Lcase(StartStr)
OverStr=Lcase(OverStr)
Start = InStrB(1, ConStrTemp, StartStr, vbBinaryCompare)
If Start<=0 then
GetBody="$False$"
Exit Function
Else
If IncluL=False Then
Start=Start+LenB(StartStr)
End If
End If
Over=InStrB(Start,ConStrTemp,OverStr,vbBinaryCompare)
If Over<=0 Or Over<=Start then
GetBody="$False$"
Exit Function
Else
If IncluR=True Then
Over=Over+LenB(OverStr)
End If
End If
GetBody=MidB(ConStr,Start,Over-Start)
End Function
REM 过滤a超链接
Function RegRemoveHref(HTMLstr)
Set ra = New RegExp
ra.IgnoreCase = True
ra.Global = True
ra.Pattern = "<a[^>]+>(.+?)<\/a>"
RegRemoveHref = Replace(ra.replace(HTMLstr,"$1"),"href=""http://www.927953.com""","")
END Function
%>
效果图如下:
华山资源网 Design By www.eoogi.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
华山资源网 Design By www.eoogi.com
暂无评论...
更新日志
2024年09月23日
2024年09月23日
- 金池VS刘罡2009《双声情》[WAV+CUE]
- 冯奥迪《卄》[320K/MP3][67.08MB]
- 冯奥迪《卄》[FLAC/分轨][172.46MB]
- Merryland《Merryland》[320K/MP3][69.48MB]
- 苏芮.1991-停在我心里的温柔【福茂】【WAV+CUE】
- 苏慧伦.2020-面面Every.Side.of.Me【相信音乐】【WAV+CUE】
- 群星.1991-不一样的感觉REMIX【宝丽金】【WAV+CUE】
- 银霞.1983-《你那好冷的小手》珍藏纪念版[WAV分轨]
- 银霞.2002-《国语巨星专辑VOL.3》2CD台湾版[WAV+CUE]
- 金池刘罡《昨日情歌HQ》头版限量编号[低速原抓WAV+CUE]
- 段奥娟.2024-23·岁碎念【白米范】【FLAC分轨】
- 顺子.2001-昨日·唯一·更多·顺子自选辑【魔岩】【WAV+CUE】
- 无印良品.1999-私藏三首·原创相对论(EP)【滚石】【WAV+CUE】
- Merryland《Merryland》[FLAC/分轨][170.22MB]
- 庄锭欣 ELKIE《没有你的未来》[320K/MP3][15.78MB]