如果大小超过50MB,WebClient不会完全下载文件

时间:2017-06-06 23:15:16

标签: c# webclient

我使用WebClient下载文件。 但是,当它试图下载超过50mb大小的更大文件时,有些可疑,下载在39kb之后立即完成,并且不会下载到最后。 任何人都知道可能是什么问题?

using (webClient = new WebClient())
{
    webClient.Proxy = null;
    webClient.Headers.Add("user-agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)");
    webClient.DownloadFileCompleted += new AsyncCompletedEventHandler(Completed);
    webClient.DownloadProgressChanged += new DownloadProgressChangedEventHandler(ProgressChanged);

    // The variable that will be holding the url address (making sure it starts with http://)
    Uri URL = urlAddress.StartsWith("http://", StringComparison.OrdinalIgnoreCase) ? new Uri(urlAddress) : new Uri("http://" + urlAddress);

    // Start the stopwatch which we will be using to calculate the download speed
    sw.Start();

    try
    {
        // Start downloading the file
        webClient.DownloadFileAsync(URL, _mainWindow.outputDirComboBox.SelectedItem.ToString() + "\\" + _compressedClientFileDownloadRelativePath, new List<object>
        {
            _compressedClientFileDownloadRelativePath,
            _decompressedClientFileDownloadRelativePath,
            _lastDownloadedFilePath,
            _compressedSize,
            _lastCompressedFilePartRelativePath,
            _filePartsRelativePath,
            urlAddress,
            _clientFilePack,
            _clientFile
        });
    }
    catch (Exception ex)
    {
        MessageBox.Show(ex.Message);
    }
}

DownloadFileCompleted仅检查错误以及何时完成,但没有任何错误报告。只有它完成下载,好像下载大小只有39kb

EDIT1: 挖掘时我最终到了这里:Downloading Large Google Drive files with WebClient in C#

看起来Google云端硬盘提供了某种确认链接,但我还不知道如何将所有内容整合在一起。

EDIT2: 我刚刚确认,39kb是html页面确认

2 个答案:

答案 0 :(得分:3)

谢谢大家!

检查此问题后: Downloading Large Google Drive files with WebClient in C# 我搜索了使用c#从google驱动器获取更大的文件并找到了this

using System;
using System.IO;
using System.Net;

public static class FileDownloader
{
    private const string GOOGLE_DRIVE_DOMAIN = "drive.google.com";
    private const string GOOGLE_DRIVE_DOMAIN2 = "https://drive.google.com";

    // Normal example: FileDownloader.DownloadFileFromURLToPath( "http://example.com/file/download/link", @"C:\file.txt" );
    // Drive example: FileDownloader.DownloadFileFromURLToPath( "http://drive.google.com/file/d/FILEID/view?usp=sharing", @"C:\file.txt" );
    public static FileInfo DownloadFileFromURLToPath( string url, string path )
    {
        if( url.StartsWith( GOOGLE_DRIVE_DOMAIN ) || url.StartsWith( GOOGLE_DRIVE_DOMAIN2 ) )
            return DownloadGoogleDriveFileFromURLToPath( url, path );
        else
            return DownloadFileFromURLToPath( url, path, null );
    }

    private static FileInfo DownloadFileFromURLToPath( string url, string path, WebClient webClient )
    {
        try
        {
            if( webClient == null )
            {
                using( webClient = new WebClient() )
                {
                    webClient.DownloadFile( url, path );
                    return new FileInfo( path );
                }
            }
            else
            {
                webClient.DownloadFile( url, path );
                return new FileInfo( path );
            }
        }
        catch( WebException )
        {
            return null;
        }
    }

    // Downloading large files from Google Drive prompts a warning screen and
    // requires manual confirmation. Consider that case and try to confirm the download automatically
    // if warning prompt occurs
    private static FileInfo DownloadGoogleDriveFileFromURLToPath( string url, string path )
    {
        // You can comment the statement below if the provided url is guaranteed to be in the following format:
        // https://drive.google.com/uc?id=FILEID&export=download
        url = GetGoogleDriveDownloadLinkFromUrl( url );

        using( CookieAwareWebClient webClient = new CookieAwareWebClient() )
        {
            FileInfo downloadedFile;

            // Sometimes Drive returns an NID cookie instead of a download_warning cookie at first attempt,
            // but works in the second attempt
            for( int i = 0; i < 2; i++ )
            {
                downloadedFile = DownloadFileFromURLToPath( url, path, webClient );
                if( downloadedFile == null )
                    return null;

                // Confirmation page is around 50KB, shouldn't be larger than 60KB
                if( downloadedFile.Length > 60000 )
                    return downloadedFile;

                // Downloaded file might be the confirmation page, check it
                string content;
                using( var reader = downloadedFile.OpenText() )
                {
                    // Confirmation page starts with <!DOCTYPE html>, which can be preceeded by a newline
                    char[] header = new char[20];
                    int readCount = reader.ReadBlock( header, 0, 20 );
                    if( readCount < 20 || !( new string( header ).Contains( "<!DOCTYPE html>" ) ) )
                        return downloadedFile;

                    content = reader.ReadToEnd();
                }

                int linkIndex = content.LastIndexOf( "href=\"/uc?" );
                if( linkIndex < 0 )
                    return downloadedFile;

                linkIndex += 6;
                int linkEnd = content.IndexOf( '"', linkIndex );
                if( linkEnd < 0 )
                    return downloadedFile;

                url = "https://drive.google.com" + content.Substring( linkIndex, linkEnd - linkIndex ).Replace( "&amp;", "&" );
            }

            downloadedFile = DownloadFileFromURLToPath( url, path, webClient );

            return downloadedFile;
        }
    }

    // Handles 3 kinds of links (they can be preceeded by https://):
    // - drive.google.com/open?id=FILEID
    // - drive.google.com/file/d/FILEID/view?usp=sharing
    // - drive.google.com/uc?id=FILEID&export=download
    public static string GetGoogleDriveDownloadLinkFromUrl( string url )
    {
        int index = url.IndexOf( "id=" );
        int closingIndex;
        if( index > 0 )
        {
            index += 3;
            closingIndex = url.IndexOf( '&', index );
            if( closingIndex < 0 )
                closingIndex = url.Length;
        }
        else
        {
            index = url.IndexOf( "file/d/" );
            if( index < 0 ) // url is not in any of the supported forms
                return string.Empty;

            index += 7;

            closingIndex = url.IndexOf( '/', index );
            if( closingIndex < 0 )
            {
                closingIndex = url.IndexOf( '?', index );
                if( closingIndex < 0 )
                    closingIndex = url.Length;
            }
        }

        return string.Format( "https://drive.google.com/uc?id={0}&export=download", url.Substring( index, closingIndex - index ) );
    }
}

// Web client used for Google Drive
public class CookieAwareWebClient : WebClient
{
    private class CookieContainer
    {
        Dictionary<string, string> _cookies;

        public string this[Uri url]
        {
            get
            {
                string cookie;
                if( _cookies.TryGetValue( url.Host, out cookie ) )
                    return cookie;

                return null;
            }
            set
            {
                _cookies[url.Host] = value;
            }
        }

        public CookieContainer()
        {
            _cookies = new Dictionary<string, string>();
        }
    }

    private CookieContainer cookies;

    public CookieAwareWebClient() : base()
    {
        cookies = new CookieContainer();
    }

    protected override WebRequest GetWebRequest( Uri address )
    {
        WebRequest request = base.GetWebRequest( address );

        if( request is HttpWebRequest )
        {
            string cookie = cookies[address];
            if( cookie != null )
                ( (HttpWebRequest) request ).Headers.Set( "cookie", cookie );
        }

        return request;
    }

    protected override WebResponse GetWebResponse( WebRequest request, IAsyncResult result )
    {
        WebResponse response = base.GetWebResponse( request, result );

        string[] cookies = response.Headers.GetValues( "Set-Cookie" );
        if( cookies != null && cookies.Length > 0 )
        {
            string cookie = "";
            foreach( string c in cookies )
                cookie += c;

            this.cookies[response.ResponseUri] = cookie;
        }

        return response;
    }

    protected override WebResponse GetWebResponse( WebRequest request )
    {
        WebResponse response = base.GetWebResponse( request );

        string[] cookies = response.Headers.GetValues( "Set-Cookie" );
        if( cookies != null && cookies.Length > 0 )
        {
            string cookie = "";
            foreach( string c in cookies )
                cookie += c;

            this.cookies[response.ResponseUri] = cookie;
        }

        return response;
    }
}

有了stackoverflow问题+这个github代码我明白它与这两个问题有关,因为当文件大于50mb时谷歌发送确认页面。因此,在实现github代码之后,现在我可以使用我的webClient下载大文件。

答案 1 :(得分:2)

您必须等待webClient.DownloadFileAsync进程

否则,当文件仍在下载时,您的执行将归结为dispose命令

示例:

public class DownloadManager
{
    public void DownloadFile(string sourceUrl, string targetFolder)
    {
        WebClient downloader = new WebClient();
            // fake as if you are a browser making the request.
        downloader.Headers.Add("User-Agent", "Mozilla/4.0 (compatible; MSIE 8.0)");
        downloader.DownloadFileCompleted += new AsyncCompletedEventHandler(Downloader_DownloadFileCompleted);

        downloader.DownloadFileAsync(new Uri(sourceUrl), targetFolder);

    }

    private void Downloader_DownloadFileCompleted(object sender, AsyncCompletedEventArgs e)
    {
            // display completion status.
        if (e.Error != null)
            Console.WriteLine(e.Error.Message);
        else
            Console.WriteLine("Download Completed!!!");
    }
}