我正在尝试从互联网下载大量文件（图片）。我正在努力处理异步/并行，因为
a) 我不能说是否有文件。我刚刚收到一百万个链接，其中要么是一张图片（300kb 到 3MB），要么是 404 页面不存在。因此，为了避免下载 0 字节文件，我询问同一页面两次，一次是 404，另一次是图片。另一种方法是下载所有 0 字节文件，然后删除数百万个文件 - 这会让 Windows 10 一直停留在这个任务上，直到我重新启动。
b) 当（非常慢）下载正在进行时，每当我查看任何“成功下载的文件”时，它都是用 0 字节创建的，并且不包含图片。我需要更改什么才能在下载下一个文件之前真正下载该文件？
我该如何解决这两个问题？有没有更好的方法来下载数千或数百万个文件（不可能在服务器上压缩/创建 .zip）
//loopResult = Parallel.ForEach(_downloadLinkList, new ParallelOptions { MaxDegreeOfParallelism = 10 }, DownloadFilesParallel);
private async void DownloadFilesParallel(string path)
{
string downloadToDirectory = "";
string x = ""; //in case x fails, i get 404 from webserver and therefore no download is needed
System.Threading.Interlocked.Increment(ref downloadCount);
OnNewListEntry(downloadCount.ToString() + " / " + linkCount.ToString() + " heruntergeladen"); //tell my gui to update
try
{
using(WebClient webClient = new WebClient())
{
downloadToDirectory = Path.Combine(savePathLocalComputer, Path.GetFileName(path)); //path on local computer
webClient.Credentials = CredentialCache.DefaultNetworkCredentials;
x = await webClient.DownloadStringTaskAsync(new Uri(path)); //if this throws an exception, ignore this link
Directory.CreateDirectory(Path.GetDirectoryName(downloadToDirectory)); //if request is successfull, create -if needed- the folder on local pc
await webClient.DownloadFileTaskAsync(new Uri(path), @downloadToDirectory); //should download the file, release 1 parallel task to get the next file. instead there is a 0-byte file and the next one will be downloaded
}
}
catch(WebException wex)
{
}
catch(Exception ex)
{
System.Diagnostics.Debug.WriteLine(ex.Message);
}
finally
{
}
}
//picture is sfw, link is nsfw
这是使用的示例HttpClient https://learn.microsoft.com/en-us/dotnet/api/system.net.http.httpclient?view=netframework-4.8具有最大并发下载限制。
private static readonly HttpClient client = new HttpClient();
private async Task DownloadAndSaveFileAsync(string path, SemaphoreSlim semaphore, IProgress<int> status)
{
try
{
status?.Report(semaphore.CurrentCount);
using (HttpResponseMessage response = await client.GetAsync(path, HttpCompletionOption.ResponseHeadersRead).ConfigureAwait(false))
{
if (response.IsSuccessStatusCode) // ignoring if not success
{
string filePath = Path.Combine(savePathLocalComputer, Path.GetFileName(path));
string dir = Path.GetDirectoryName(filePath);
if (!Directory.Exists(dir)) Directory.CreateDirectory(dir);
using (Stream responseStream = await response.Content.ReadAsStreamAsync().ConfigureAwait(false))
using (FileStream fileStream = File.Create(filePath))
{
await responseStream.CopyToAsync(fileStream).ConfigureAwait(false);
}
}
}
}
finally
{
semaphore.Release();
}
}
并发数
client.BaseAddress = "http://somesite";
int downloadCount = 0;
List<string> pathList = new List<string>();
// fill the list here
List<Task> tasks = new List<Task>();
int maxConcurrentTasks = Environment.ProcessorCount * 2; // 16 for me
IProgress<int> status = new Progress<int>(availableTasks =>
{
downloadCount++;
OnNewListEntry(downloadCount + " / " + pathList.Count + " heruntergeladen\r\nRunning " + (maxConcurrentTasks - availableTasks) + " downloads.");
});
using (SemaphoreSlim semaphore = new SemaphoreSlim(maxConcurrentTasks))
{
foreach (string path in pathList)
{
await semaphore.WaitAsync();
tasks.Add(DownloadAndSaveFileAsync(path, semaphore, status));
}
try
{
await Task.WhenAll(tasks);
}
catch (Exception ex)
{
// handle the Exception here
}
}
Progress这里只是在 UI 线程上执行回调。因此Interlocked内部不需要，更新 UI 是安全的。
如果是.NET Framework（在.NET Core中没有效果但不需要）为了使其更快，您可以将此行添加到应用程序启动代码中
ServicePointManager.DefaultConnectionLimit = 10;