很久沒寫過東西了,今天看了chinahuman 的《用asp自動解析網頁中的圖片地址,并將其保存到本地服務器》,于是優化了這個程序,并且將所有的功能都函數化了,希望對學習 XMLHTTP 的朋友有所幫助。 程序實現功能:自動將遠程頁面的文件中的圖片下載到本地。
<% '將本文保存為 save2local.asp '測試:save2local.asp?url=http://ent.sina.com.cn/s/m/2003-11-11/1411231388.html '本文根據 chinahuman 的《用asp自動解析網頁中的圖片地址,并將其保存到本地服務器》改編和優化 '自動創建目錄,自動將原文件名更名,文件格式的限制以及其他功能的一些優化 '自動保存網頁文件中 http://.... 格式的圖片到本地 '轉載請注明出處:http://www.jaron.cn http://www.csdn.net/develop '參數設置開始 url = request("url") localaddr = server.MapPath("images_remote/") '保存到本地的目錄 localdir = "images_remote/" 'http 訪問的相對路徑 AllowFileExt = "jpg|bmp|png|gif" '支持的文件名格式 '參數設置完畢
if createdir(localaddr) = false then response.Write "創建目錄失敗,請檢查目錄權限" response.End end if response.Write Convert2LocalAddr(url,localaddr,localdir)
function Convert2LocalAddr(url,localaddr,localdir) '參數說明 'url 頁面地址 'localaddr 保存本地的物理地址 'localdir 相對路徑 strContent = getHTTPPage(url) Set objRegExp = New Regexp objRegExp.IgnoreCase = True objRegExp.Global = True objRegExp.Pattern = "<img.+?>" Set Matches =objRegExp.Execute(strContent) For Each Match in Matches RetStr = RetStr & GetRemoteImages(Match.Value) Next ImagesArray=split(RetStr,"||") RemoteImage="" LocalImage="" for i=1 to ubound(ImagesArray) if ImagesArray(i)<>"" and instr(RemoteImage,ImagesArray(i))<1 then fname=baseurl&cstr(i&mid(ImagesArray(i),instrrev(ImagesArray(i),"."))) ImagesFileName = ImagesArray(i) AllowFileExtArray = split(AllowFileExt,"|") isGetFile = false for tmp = 0 to ubound(AllowFileExtArray) if lcase(GetFileExt(ImagesFileName)) = ALlowFileExtArray(tmp) then isGetFile=True end if next if isGetFile = true then newfilename = GenerateRandomFileName(fname) call Save2Local(ImagesFileName,localaddr & "/" & newfilename) RemoteImage=RemoteImage&"||"& ImagesFileName LocalImage=LocalImage&"||" & localdir & newfilename end if end if next arrnew=split(LocalImage,"||") arrall=split(RemoteImage,"||") for i=1 to ubound(arrnew) strContent=replace(strContent,arrall(i),arrnew(i)) next Convert2LocalAddr = strContent end function
function GetRemoteImages(str) Set objRegExp1 = New Regexp objRegExp1.IgnoreCase = True objRegExp1.Global = True objRegExp1.Pattern = "http://.+? " set mm=objRegExp1.Execute(str) For Each Match1 in mm tmpaddr = left(Match1.Value,len(Match1.Value)-1) GetRemoteImages=GetRemoteImages&"||" & replace(replace(tmpaddr,"""",""),"'","") next end function
function getHTTPPage(url) on error resume next dim http set http=Server.createobject("Msxml2.XMLHTTP") Http.open "GET",url,false Http.send() if Http.readystate<>4 thenexit function getHTTPPage=bytes2BSTR(Http.responseBody) set http=nothing if err.number<>0 then err.Clear end function
Function bytes2BSTR(vIn) dim strReturn dim i,ThisCharCode,NextCharCode strReturn = "" For i = 1 To LenB(vIn) ThisCharCode = AscB(MidB(vIn,i,1)) If ThisCharCode < &H80 Then strReturn = strReturn & Chr(ThisCharCode) Else NextCharCode = AscB(MidB(vIn,i+1,1)) strReturn = strReturn & Chr(CLng(ThisCharCode) * &H100 + CInt(NextCharCode)) i = i + 1 End If Next bytes2BSTR = strReturn End Function
function getHTTPimg(url) 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 getHTTPimg=Http.responseBody set http=nothing if err.number<>0 then err.Clear end function
function Save2Local(from,tofile) dim geturl,objStream,imgs geturl=trim(from) imgs=gethttpimg(geturl) Set objStream = Server.CreateObject("ADODB.Stream") objStream.Type =1 objStream.Open objstream.write imgs objstream.SaveToFile tofile,2 objstream.Close() set objstream=nothing end function
function geturlencodel(byval url)'中文文件名轉換 Dim i,code geturlencodel="" if trim(Url)="" then exit function for i=1 to len(Url) code=Asc(mid(Url,i,1)) if code<0 Then code = code + 65536 If code>255 Then geturlencodel=geturlencodel&"%"&Left(Hex(Code),2)&"%"&Right(Hex(Code),2) else geturlencodel=geturlencodel&mid(Url,i,1) end if next end function
Function GenerateRandomFileName(ByVal szFilename) '根據原文件名,自動以日期YYYY-MM-DD-RANDOM格式生成新文件名 Randomize ranNum = Int(90000 * Rnd) + 10000 If Month(Now) < 10 Then c_month = "0" & Month(Now) Else c_month = Month(Now) If Day(Now) < 10 Then c_day = "0" & Day(Now) Else c_day = Day(Now) If Hour(Now) < 10 Then c_hour = "0" & Hour(Now) Else c_hour = Hour(Now) If Minute(Now) < 10 Then c_minute = "0" & Minute(Now) Else c_minute = Minute(Now) If Second(Now) < 10 Then c_second = "0" & Second(Now) Else c_second = Minute(Now) fileExt_a = Split(szFilename, ".") FileExt = LCase(fileExt_a(UBound(fileExt_a))) GenerateRandomFileName = Year(Now) & c_month & c_day & c_hour & c_minute & c_second & "_" & ranNum & "." & FileExt End Function
Function CreateDIR(ByVal LocalPath) '建立目錄的程序,如果有多級目錄,則一級一級的創建 On Error Resume Next LocalPath = Replace(LocalPath, "\", "/") Set FileObject = server.CreateObject("Scripting.FileSystemObject") patharr = Split(LocalPath, "/") path_level = UBound(patharr) For I = 0 To path_level If I = 0 Then pathtmp = patharr(0) & "/" Else pathtmp = pathtmp & patharr(I) & "/" cpath = Left(pathtmp, Len(pathtmp) - 1) If Not FileObject.FolderExists(cpath) Then FileObject.CreateFolder cpath Next Set FileObject = Nothing If Err.Number <> 0 Then CreateDIR = False Err.Clear Else CreateDIR = True End If End Function
function GetfileExt(byval filename) fileExt_a=split(filename,".") GetfileExt=lcase(fileExt_a(ubound(fileExt_a))) end function %>
有一點要注意的是,這里只是分析了以 http開頭的圖片的地址。否則不下載圖片,可以轉換一下地址就行了,再提供幾個小函數,分析地址用的:
Function findurl(thisurl) if thisurl <> "" Then findurl="" strlen=InStr(8,thisurl,"/") If strlen=0 Then strlen =1 findurl=Mid(thisurl,strlen,28) end if end Function
function findurlpath(thisurl) thisurl = replace(thisurl,"//","@@") ary_tmp = split(thisurl,"/") for tmp = 0 to ubound(ary_tmp) if tmp < ubound(ary_tmp) then urltmp = urltmp & "/" & ary_tmp(tmp) end if next urltmp = right(urltmp,len(urltmp)-1) findurlpath = replace(urltmp,"@@","//") & "/" end function
function findurlhost(thisurl) thisurl = replace(thisurl,"//","@@") ary_tmp = split(thisurl,"/") urltmp = ary_tmp(0) findurlhost = replace(urltmp,"@@","//") & "/" findurlhost = left(findurlhost,len(findurlhost)-1) end function
|