Create service to populate Imdb data collection within mongo

We can use this collection as an alternative source to lookup imdb ids, which would be executed before name_to_imdb is called in the consumer.
This commit is contained in:
iPromKnight
2024-02-27 22:38:10 +00:00
parent aad59c31e4
commit 79d0ef7f4d
26 changed files with 611 additions and 0 deletions

View File

@@ -0,0 +1,8 @@
namespace Metadata.Features.DownloadImdbData;
public class DownloadImdbDataJob(IMessageBus messageBus, JobConfiguration configuration) : BaseJob
{
public override bool IsScheduelable => !configuration.DownloadImdbOnce && !string.IsNullOrEmpty(configuration.DownloadImdbCronSchedule);
public override string JobName => nameof(DownloadImdbDataJob);
public override async Task Invoke() => await messageBus.SendAsync(new GetImdbDataRequest());
}

View File

@@ -0,0 +1,3 @@
namespace Metadata.Features.DownloadImdbData;
public record GetImdbDataRequest;

View File

@@ -0,0 +1,30 @@
namespace Metadata.Features.DownloadImdbData;
public class GetImdbDataRequestHandler(IHttpClientFactory clientFactory, ILogger<GetImdbDataRequestHandler> logger)
{
private const string TitleBasicsFileName = "title.basics.tsv";
public async Task<ImportImdbDataRequest> Handle(GetImdbDataRequest _, CancellationToken cancellationToken)
{
logger.LogInformation("Downloading IMDB data");
var client = clientFactory.CreateClient("imdb-data");
var response = await client.GetAsync($"{TitleBasicsFileName}.gz", cancellationToken);
var tempFile = Path.Combine(Path.GetTempPath(), TitleBasicsFileName);
response.EnsureSuccessStatusCode();
await using var stream = await response.Content.ReadAsStreamAsync(cancellationToken);
await using var gzipStream = new GZipStream(stream, CompressionMode.Decompress);
await using var fileStream = File.Create(tempFile);
await gzipStream.CopyToAsync(fileStream, cancellationToken);
logger.LogInformation("Downloaded IMDB data to {TempFile}", tempFile);
fileStream.Close();
return new(tempFile);
}
}