c# - 从重定向 URL 下载文件

Question

我正在尝试从 http://www.audiodump.com/ 下载 mp3 .该网站有很多重定向。但是我设法让它的一部分工作。这是我获取所有信息(如 DL 链接、标题、mp3 持续时间)的方法。

private void _InetGetHTMLSearch(string sArtist)
{
    if(_AudioDumpQuery == string.Empty)
    {
        //return string.Empty;
    }
    string[] sStringArray;
    string sResearchURL = "http://www.audiodump.biz/music.html?" + _AudioDumpQuery + sArtist.Replace(" ", "+");
    string aRet;
    HttpWebRequest webReq = (HttpWebRequest)HttpWebRequest.Create(sResearchURL);
    webReq.Referer = "http://www.audiodump.com/";
    try
    {
        webReq.CookieContainer = new CookieContainer();
        webReq.Method = "GET";
        using (WebResponse response = webReq.GetResponse())
        {
            using (Stream stream = response.GetResponseStream())
            {
                StreamReader reader = new StreamReader(stream);
                aRet = reader.ReadToEnd();
                //Console.WriteLine(aRet);
                string[] aTable = _StringBetween(aRet, "<BR><table", "table><BR>", RegexOptions.Singleline);
                if (aTable != null)
                {
                    string[] aInfos = _StringBetween(aTable[0], ". <a href=\"", "<a href=\"");
                    if (aInfos != null)
                    {
                        for(int i = 0; i < aInfos.Length; i++)
                        {
                            aInfos[i] = aInfos[i].Replace("\">", "*");
                            aInfos[i] = aInfos[i].Replace("</a> (", "*");
                            aInfos[i] = aInfos[i].Remove(aInfos[i].Length - 2);

                            sStringArray = aInfos[i].Split('*');

                            aLinks.Add(sStringArray[0]);
                            aTitles.Add(sStringArray[1]);

                            sStringArray[2] = sStringArray[2].Replace("`", "'");
                            sStringArray[2] = sStringArray[2].Replace("dont", "don't");
                            sStringArray[2] = sStringArray[2].Replace("lets", "let's");
                            sStringArray[2] = sStringArray[2].Replace("cant", "can't");
                            sStringArray[2] = sStringArray[2].Replace("shes", "she's");
                            sStringArray[2] = sStringArray[2].Replace("aint", "ain't");
                            sStringArray[2] = sStringArray[2].Replace("didnt", "didn't");
                            sStringArray[2] = sStringArray[2].Replace("im", "i'm");
                            sStringArray[2] = sStringArray[2].Replace("youre", "you're");
                            sStringArray[2] = sStringArray[2].Replace("ive", "i've");
                            sStringArray[2] = sStringArray[2].Replace("youll", "you'll");
                            sStringArray[2] = sStringArray[2].Replace("&#39;", "'");
                            sStringArray[2] = sStringArray[2].Replace("'", "simplequotes");
                            sStringArray[2] = sStringArray[2].Replace("vk.com", "");
                            sStringArray[2] = _StringReplaceCyrillicChars(sStringArray[2]);
                            sStringArray[2] = Regex.Replace(sStringArray[2], @"<[^>]+>|&nbsp;", "").Trim();
                            sStringArray[2] = Regex.Replace(sStringArray[2], @"\s{2,}", " ");
                            sStringArray[2] = sStringArray[2].TrimStart('\'');
                            sStringArray[2] = sStringArray[2].TrimStart('-');
                            sStringArray[2] = sStringArray[2].TrimEnd('-');
                            sStringArray[2] = sStringArray[2].Replace("- -", "-");
                            sStringArray[2] = sStringArray[2].Replace("http", "");
                            sStringArray[2] = sStringArray[2].Replace("www", "");
                            sStringArray[2] = sStringArray[2].Replace("mp3", "");
                            sStringArray[2] = sStringArray[2].Replace("simplequotes", "'");

                            aDurations.Add(sStringArray[2]);
                        }
                    }
                    else
                    {
                        //Console.WriteLine("Debug");
                    }
                }
                else
                {
                    //Console.WriteLine("Debug 2");
                }

                //return aRet;
            }
        }
    }
    catch (Exception ex)
    {
        //return null;
        ////Console.WriteLine("Debug message: " + ex.Message);
    }
}

我只需添加引荐来源网址即可防止搜索重定向 webReq.Referer = "http://www.audiodump.com/";但是，当我想下载 mp3 时，我无法让它工作。这些 url 是正确的，并与我手动而不是以编程方式下载时获得的 url 进行了核对。这是我的mp3下载部分:

private void _DoDownload(string dArtist, ref string dPath)
{
    if (!Contain && skip <= 3 && !Downloading)
    {
        Random rnd = new Random();
        int Link = rnd.Next(5);
        _InetGetHTMLSearch(dArtist);
        Console.WriteLine("--------------------------------> " + aLinks[0]);
        string path = mp3Path + "\\" + dArtist + ".mp3";
        if (DownloadOne(aLinks[Link], path, false))
        {
            hTimmer.Start();
            Downloading = true;
        }
    }
    else if (Downloading)
    {
        int actualBytes = strm.Read(barr, 0, arrSize);
        fs.Write(barr, 0, actualBytes);
        bytesCounter += actualBytes;
        double percent = 0d;
        if (fileLength > 0)
           percent =
                100.0d * bytesCounter /
                (preloadedLength + fileLength);
        label1.Text = Math.Round(percent).ToString() + "%";
        if (Math.Round(percent) >= 100)
        {
            string path = mp3Path + "\\" + dArtist + ".mp3";
            label1.Text = "";
            dPath = path;
            aLinks.Clear();
            hTimmer.Stop();
            hTimmer.Reset();
            fs.Flush();
            fs.Close();
            lastArtistName = "N/A";
            Downloading = false;
        }
        if (Math.Round(percent) <= 1)
        {
            if (hTimmer.ElapsedMilliseconds >= 3000)
            {
                string path = mp3Path + "\\" + dArtist + ".mp3";
                hTimmer.Stop();
                hTimmer.Reset();
                fs.Flush();
                fs.Close();
                File.Delete(path);
                Contain = false;
                skip += 1;
                Downloading = false;
            }
        }
    }
}

private static string ConvertUrlToFileName(string url)
{
    string[] terms = url.Split(
        new string[] { ":", "//" },
        StringSplitOptions.RemoveEmptyEntries);
    string fname = terms[terms.Length - 1];
    fname = fname.Replace('/', '.');
    return fname;
} //ConvertUrlToFileName

private static long GetExistingFileLength(string filename)
{
    if (!File.Exists(filename)) return 0;
    FileInfo info = new FileInfo(filename);
    return info.Length;
} //GetExistingFileLength

private static bool DownloadOne(string url, string existingFilename, bool quiet)
{
    ServicePointManager.DefaultConnectionLimit = 20;
    HttpWebRequest webRequest;
    HttpWebResponse webResponse;
    IWebProxy proxy = null; //SA???
                            //fmt = CreateFormat(
                            //"{0}: {1:#} of {2:#} ({3:g3}%)", "#");
    try
    {
        fname = existingFilename;
        if (fname == null)
            fname = ConvertUrlToFileName(url);
        if (File.Exists(existingFilename))
        {
            File.Delete(existingFilename);
        }
        webRequest = (HttpWebRequest)WebRequest.Create(url);
        webRequest.UserAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/7046A194A";
        webRequest.Referer = "http://www.audiodump.com/";
        preloadedLength = GetExistingFileLength(fname);
        if (preloadedLength > 0)
            webRequest.AddRange((int)preloadedLength);
        webRequest.Proxy = proxy; //SA??? or DefineProxy
        webResponse = (HttpWebResponse)webRequest.GetResponse();
        fs = new FileStream(fname, FileMode.Append, FileAccess.Write);
        fileLength = webResponse.ContentLength;
        strm = webResponse.GetResponseStream();
        if (strm != null)
        {
            bytesCounter = preloadedLength;
            return true;
        }
        else
        {
            return false;
        }
    }
    catch (Exception e)
    {
        //Console.WriteLine(
        //"{0}: {1} '{2}'",
        // url, e.GetType().FullName,
        //e.Message);
        return false;
    }
    //exception
} //DownloadOne

_DoDownload() 方法由每 250 毫秒运行一次的计时器执行。这种方式在其他网站上完美运行。然而，audiodump 让我很难处理这些重定向。

我不是 httprequest 的天才。我设法解决了搜索问题，但是下载部分让我很害怕。有关如何管理下载问题的任何建议？

Answer 1

您只需将引荐来源网址设置为您获得下载链接的页面。例如，您从页面“http://www.audiodump.biz/music.html?q=whatever”获取文件链接，然后在下载文件时将其设置为 Referrer，而不仅仅是“http://www.audiodump.biz”。