为什么我不能在我的Delphi程序中获取AOL验证码映像？

StackOverflow https://stackoverflow.com/questions/2724233

  •  02-10-2019
  •  | 
  •  

题

新的演示代码：

我正在尝试从AOL获取验证码图像，并且我不断出现错误418。

unit imageunit;
///
///  https://new.aol.com/productsweb/
///
interface

uses
  Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms,
  Dialogs, StdCtrls, IdIOHandler, IdIOHandlerSocket, IdIOHandlerStack, IdSSL,
  IdSSLOpenSSL, IdIntercept, IdZLibCompressorBase, IdCompressorZLib,
  IdCookieManager, IdBaseComponent, IdComponent, IdTCPConnection, IdTCPClient,
  IdHTTP,jpeg,GIFImg, ExtCtrls, PerlRegEx;

type
  TForm2 = class(TForm)
    IdHTTP1: TIdHTTP;
    IdCookieManager1: TIdCookieManager;
    IdCompressorZLib1: TIdCompressorZLib;
    IdConnectionIntercept1: TIdConnectionIntercept;
    IdSSLIOHandlerSocketOpenSSL1: TIdSSLIOHandlerSocketOpenSSL;
    Panel1: TPanel;
    Image1: TImage;
    Panel2: TPanel;
    Button1: TButton;
    PerlRegEx1: TPerlRegEx;
    Memo1: TMemo;
    procedure Button1Click(Sender: TObject);
  private
    { Private declarations }
  public
    { Public declarations }
  end;

var
  Form2: TForm2;

implementation

{$R *.dfm}

function getaimcaptchaimage(data:string):string;
var
    Regex: TPerlRegEx;
    ResultString: string;
begin
Regex := TPerlRegEx.Create(nil);
Regex.RegEx := '<img src="/productsweb/WordVerImage?(.*?)"';
Regex.Options := [preCaseless];
Regex.Subject := data;
if Regex.Match then begin
    if Regex.SubExpressionCount >= 1 then begin
        ResultString := Regex.SubExpressions[1];
    end;
  result:=Resultstring;
end;
end;


procedure TForm2.Button1Click(Sender: TObject);
var
  JPI : TJPEGImage;
  streamdata:TMemoryStream;
  SStream: Tstringstream;
  website:string;
begin
  streamdata := TMemoryStream.Create;
  SStream := tstringstream.Create ( '' );

  try
  idhttp1.Get('https://new.aol.com/productsweb/',SStream);
  memo1.Text:=UTF8ToWideString ( SStream.DataString );
  website:='https://new.aol.com/productsweb/WordVerImage'+getaimcaptchaimage( UTF8ToWideString ( SStream.DataString ));
  form2.Caption:=website;
  idhttp1.Get(website, Streamdata);
          Except
          { Handle exceptions }
          On E : Exception Do
               Begin
                MessageDlg('Exception: '+E.Message,mtError, [mbOK], 0);
               End;

          End;

  //https://new.aol.com/productsweb/WordVerImage?20890843
  //https://new.aol.com/productsweb/WordVerImage?91868359


  ///
  ///  gives error 418 unused
  ///

  streamdata.Position := 0;
  JPI := TJPEGImage.Create;
  Try
  JPI.LoadFromStream ( streamdata );
  Finally
  Image1.Picture.Assign ( JPI );
  JPI.Free;
  streamdata.Free;
  End;

end;

end.

形式：

object Form2: TForm2
  Left = 0
  Top = 0
  Caption = 'Form2'
  ClientHeight = 247
  ClientWidth = 480
  Color = clBtnFace
  Font.Charset = DEFAULT_CHARSET
  Font.Color = clWindowText
  Font.Height = -11
  Font.Name = 'Tahoma'
  Font.Style = []
  OldCreateOrder = False
  PixelsPerInch = 96
  TextHeight = 13
  object Panel1: TPanel
    Left = 0
    Top = 41
    Width = 480
    Height = 206
    Align = alClient
    TabOrder = 0
    object Image1: TImage
      Left = 1
      Top = 1
      Width = 478
      Height = 115
      Align = alClient
      ExplicitLeft = 5
      ExplicitTop = 17
      ExplicitWidth = 200
      ExplicitHeight = 70
    end
    object Memo1: TMemo
      Left = 1
      Top = 116
      Width = 478
      Height = 89
      Align = alBottom
      TabOrder = 0
      ExplicitLeft = 80
      ExplicitTop = 152
      ExplicitWidth = 185
    end
  end
  object Panel2: TPanel
    Left = 0
    Top = 0
    Width = 480
    Height = 41
    Align = alTop
    TabOrder = 1
    object Button1: TButton
      Left = 239
      Top = 6
      Width = 75
      Height = 25
      Caption = 'Button1'
      TabOrder = 0
      OnClick = Button1Click
    end
  end
  object IdHTTP1: TIdHTTP
    Intercept = IdConnectionIntercept1
    IOHandler = IdSSLIOHandlerSocketOpenSSL1
    MaxAuthRetries = 100
    AllowCookies = True
    HandleRedirects = True
    RedirectMaximum = 100
    ProxyParams.BasicAuthentication = False
    ProxyParams.ProxyPort = 0
    Request.ContentLength = -1
    Request.Accept = 
      'image/gif, image/jpeg, image/pjpeg, image/pjpeg, application/x-s' +
      'hockwave-flash, application/cade, application/xaml+xml, applicat' +
      'ion/vnd.ms-xpsdocument, application/x-ms-xbap, application/x-ms-' +
      'application, */*'
    Request.BasicAuthentication = False
    Request.Referer = 'http://www.yahoo.com'
    Request.UserAgent = 
      'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.1) Gecko/201001' +
      '22 firefox/3.6.1'
    HTTPOptions = [hoForceEncodeParams]
    CookieManager = IdCookieManager1
    Compressor = IdCompressorZLib1
    Left = 40
    Top = 160
  end
  object IdCookieManager1: TIdCookieManager
    Left = 360
    Top = 136
  end
  object IdCompressorZLib1: TIdCompressorZLib
    Left = 408
    Top = 56
  end
  object IdConnectionIntercept1: TIdConnectionIntercept
    Left = 304
    Top = 72
  end
  object IdSSLIOHandlerSocketOpenSSL1: TIdSSLIOHandlerSocketOpenSSL
    Intercept = IdConnectionIntercept1
    MaxLineAction = maException
    Port = 0
    DefaultPort = 0
    SSLOptions.Mode = sslmUnassigned
    SSLOptions.VerifyMode = []
    SSLOptions.VerifyDepth = 0
    Left = 192
    Top = 136
  end
  object PerlRegEx1: TPerlRegEx
    Options = []
    Left = 120
    Top = 56
  end
end

如果你去 https://new.aol.com/productsweb/您会注意到验证码图像具有类似的URL https://new.aol.com/productsweb/wordverimage?91868359

我将该URL放在编辑框中，并获得错误。

此代码有什么问题？

有帮助吗？

解决方案

在我的旧项目中，我从网络上读取了Captcha。我使用嵌入式Web浏览器组件缓存过程进行了此操作。因此，如果您可以从代码中读取临时Internet文件，则可以从缓存中读取图像数据。我在下面添加了一个简单的代码，

tembeddedwebbrowser单元宣布了getCachedFileFromurl和Clearallentries功能。我在解决方案中仅使用了我的复制代码，以使EXE尺寸较低。但是您可以使用组件更新的源。组件是开源。

uses
 WinInet;

function GetCachedFileFromURL(strUL: string; var strLocalFile: string): Boolean;
var
   lpEntryInfo: PInternetCacheEntryInfo;
   hCacheDir: LongWord;
   dwEntrySize: LongWord;
   dwLastError: LongWord;
begin
   Result := False;
   dwEntrySize := 0;
  // Begin the enumeration of the Internet cache.
   FindFirstUrlCacheEntry(nil, TInternetCacheEntryInfo(nil^), dwEntrySize);
   GetMem(lpEntryInfo, dwEntrySize);
   hCacheDir := FindFirstUrlCacheEntry(nil, lpEntryInfo^, dwEntrySize);
   if (hCacheDir <> 0) and (strUL = lpEntryInfo^.lpszSourceUrlName) then
      begin
         strLocalFile := lpEntryInfo^.lpszLocalFileName;
         Result := True;
      end;
   FreeMem(lpEntryInfo);
   if Result = False then
      repeat
         dwEntrySize := 0;
      // Retrieves the next cache group in a cache group enumeration
         FindNextUrlCacheEntry(hCacheDir, TInternetCacheEntryInfo(nil^), dwEntrySize);
         dwLastError := GetLastError();
         if (GetLastError = ERROR_INSUFFICIENT_BUFFER) then
            begin
               GetMem(lpEntryInfo, dwEntrySize);
               if (FindNextUrlCacheEntry(hCacheDir, lpEntryInfo^, dwEntrySize)) then
                  begin
                     if strUL = lpEntryInfo^.lpszSourceUrlName then
                        begin
                           strLocalFile := lpEntryInfo^.lpszLocalFileName;
                           Result := True;
                           Break;
                        end;
                  end;
               FreeMem(lpEntryInfo);
            end;
      until (dwLastError = ERROR_NO_MORE_ITEMS);
end;

procedure TForm1.ClearCache();
begin
  SearchPattern := spAll;
  ClearAllEntries;
end;

用法

procedure TForm1.Button1Click(Sender: TObject);
var
 fname:string;
 jpImg:TJPEGImage;
begin
  ClearCache;
  try
   jpImg:=TJPEGImage.Create; 
   GetCachedFileFromURL('https://ebildirge.ssk.gov.tr/WPEB/PG',fname);
   jpImg.LoadFromFile(fname);
  finally
   FreeAndNil(jpgImg);
  end;
end;

其他提示

涉及饼干。如果您直接去验证码URL https://new.aol.com/productsweb/wordverimage?91868359 在尚未访问的浏览器中 https://new.aol.com/productsweb/ 然后您得到（刷新后）：

<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN"> 
<html><head> 
<title>418 unused</title> 
</head><body> 
<h1>unused</h1> 
<p>The server encountered an internal error or
misconfiguration and was unable to complete
your request.</p> 
<p>Please contact the server administrator,
 null and inform them of the time the error occurred,
and anything you might have done that may have
caused the error.</p> 
<p>More information about this error may be available
in the server error log.</p> 
</body></html>

但是如果你访问 https://new.aol.com/productsweb/ 首先，您将获得图像。清除cookie，然后再收到错误（尽管正如Francois指出的那样，您没有首先得到响应，然后在刷新时您会得到图像。）

Indy支持Cookie，因此您需要添加对Cookie的支持，然后首先访问ProductSweb或从已知值中模拟cookie。

您会注意到，生成的图像不是基于仅作为参数传递的数字，而是基于cookie。有两个不同的浏览器（Chrome和Firefox），每个浏览器都有不同的cookie，然后访问相同的验证码URL，您将获得两个不同的图像。

好奇您想完成的工作。

我认为这意味着“走开”。不知何故，通过您的要求中的标题或其他内容，它确定您闻起来像机器人。也许是因为您要寻找它知道它不仅为您创造的图像。是的，可能就是这样。如果我在浏览器中转到您的URL，我也会得到418。

这不是您的代码。在浏览器中尝试...
（显然，您需要从'http s''...中删除空白...）

这个网址 https://new.aol.com/productsweb/ 显然需要打电话给您才能获得验证码图像。否则您会遇到（不正确）错误 418 Unused.
有时我不得不尝试两次图像＃，因为我第一次得到一个 420 Unused 错误...

您最好问他们，因为他们的API似乎并不稳定...

回复：HTTP 418笑话。如果您想对HTTP错误代码进行一些乐趣 网络开发人员和他的女友

许可以下： CC-BY-SA 和 归因
不隶属于 StackOverflow
scroll top