public static async Task <WebDirectory> ParseIndex(IHtmlDocument htmlDocument, HttpClient httpClient, WebDirectory webDirectory)
{
try
{
OpenDirectoryIndexer.Session.GDIndex = true;
if (!OpenDirectoryIndexer.Session.Parameters.ContainsKey(Constants.Parameters_Password))
{
Console.WriteLine($"{Parser} will always be indexed at a maximum rate of 1 per second, else you will run into problems and errors.");
Logger.Info($"{Parser} will always be indexed at a maximum rate of 1 per second, else you will run into problems and errors.");
Console.WriteLine("Check if password is needed (unsupported currently)...");
Logger.Info("Check if password is needed (unsupported currently)...");
OpenDirectoryIndexer.Session.Parameters[Constants.Parameters_Password] = string.Empty;
Dictionary <string, string> postValues = new Dictionary <string, string>
{
{ "password", OpenDirectoryIndexer.Session.Parameters[Constants.Parameters_Password] },
{ "page_token", string.Empty },
{ "page_index", "0" },
{ "q", "" }
};
HttpRequestMessage httpRequestMessage = new HttpRequestMessage(HttpMethod.Post, webDirectory.Uri)
{
Content = new FormUrlEncodedContent(postValues)
};
HttpResponseMessage httpResponseMessage = await httpClient.SendAsync(httpRequestMessage);
if (httpResponseMessage.IsSuccessStatusCode)
{
string responseJson = await DecodeResponse(htmlDocument, httpClient, httpResponseMessage);
BhadooIndexResponse response = BhadooIndexResponse.FromJson(responseJson);
webDirectory = await ScanAsync(htmlDocument, httpClient, webDirectory);
}
}
else
{
webDirectory = await ScanAsync(htmlDocument, httpClient, webDirectory);
}
}
catch (Exception ex)
{
Logger.Error(ex, $"Error parsing {Parser} for URL: {webDirectory.Url}");
webDirectory.Error = true;
OpenDirectoryIndexer.Session.Errors++;
if (!OpenDirectoryIndexer.Session.UrlsWithErrors.Contains(webDirectory.Url))
{
OpenDirectoryIndexer.Session.UrlsWithErrors.Add(webDirectory.Url);
}
throw;
}
return(webDirectory);
}
private static async Task <WebDirectory> ScanAsync(IHtmlDocument htmlDocument, HttpClient httpClient, WebDirectory webDirectory)
{
webDirectory.Parser = Parser;
try
{
Polly.Retry.AsyncRetryPolicy asyncRetryPolicy = Library.GetAsyncRetryPolicy((ex, waitTimeSpan, retry, pollyContext) =>
{
Logger.Warn($"Error retrieving directory listing for {webDirectory.Uri}, waiting {waitTimeSpan.TotalSeconds} seconds.. Error: {ex.Message}");
RateLimiter.AddDelay(waitTimeSpan);
}, 8);
if (!webDirectory.Url.EndsWith("/"))
{
webDirectory.Url += "/";
}
long pageIndex = 0;
string nextPageToken = string.Empty;
do
{
await asyncRetryPolicy.ExecuteAndCaptureAsync(async() =>
{
await RateLimiter.RateLimit();
Logger.Warn($"Retrieving listings for {webDirectory.Uri.PathAndQuery}, page {pageIndex + 1}{(!string.IsNullOrWhiteSpace(OpenDirectoryIndexer.Session.Parameters[Constants.Parameters_Password]) ? $" with password: {OpenDirectoryIndexer.Session.Parameters[Constants.Parameters_Password]}" : string.Empty)}");
Dictionary <string, string> postValues = new Dictionary <string, string>
{
{ "password", OpenDirectoryIndexer.Session.Parameters[Constants.Parameters_Password] },
{ "page_token", nextPageToken },
{ "page_index", pageIndex.ToString() }
};
HttpRequestMessage httpRequestMessage = new HttpRequestMessage(HttpMethod.Post, webDirectory.Uri)
{
Content = new FormUrlEncodedContent(postValues)
};
HttpResponseMessage httpResponseMessage = await httpClient.SendAsync(httpRequestMessage);
webDirectory.ParsedSuccessfully = httpResponseMessage.IsSuccessStatusCode;
httpResponseMessage.EnsureSuccessStatusCode();
try
{
string responseJson = await DecodeResponse(htmlDocument, httpClient, httpResponseMessage);
BhadooIndexResponse indexResponse = BhadooIndexResponse.FromJson(responseJson);
webDirectory.ParsedSuccessfully = indexResponse.Data.Error == null;
if (indexResponse.Data.Error?.Message == "Rate Limit Exceeded")
{
throw new Exception("Rate limit exceeded");
}
else
{
if (indexResponse.Data.Files == null)
{
throw new Exception("Directory listing retrieval error (Files null)");
}
else
{
nextPageToken = indexResponse.NextPageToken;
pageIndex = indexResponse.CurPageIndex + 1;
foreach (File file in indexResponse.Data.Files)
{
if (file.MimeType == FolderMimeType)
{
webDirectory.Subdirectories.Add(new WebDirectory(webDirectory)
{
Parser = Parser,
// Yes, string concatenation, do not use new Uri(webDirectory.Uri, file.Name), because things could end with a space...
Url = $"{webDirectory.Uri}{GetSafeName(file.Name)}/",
Name = file.Name
});
}
else
{
webDirectory.Files.Add(new WebFile
{
Url = new Uri(webDirectory.Uri, GetSafeName(file.Name)).ToString(),
FileName = file.Name,
FileSize = file.Size
});
}
}
}
}
}
catch (Exception ex)
{
throw new Exception($"Retrieving listings for {webDirectory.Uri.PathAndQuery}, page {pageIndex + 1}. Error: {ex.Message}");
}
});
} while (!string.IsNullOrWhiteSpace(nextPageToken));
}
catch (Exception ex)
{
Logger.Error(ex, $"Error retrieving directory listing for {webDirectory.Url}");
webDirectory.Error = true;
OpenDirectoryIndexer.Session.Errors++;
if (!OpenDirectoryIndexer.Session.UrlsWithErrors.Contains(webDirectory.Url))
{
OpenDirectoryIndexer.Session.UrlsWithErrors.Add(webDirectory.Url);
}
//throw;
}
return(webDirectory);
}
