/// <summary>
/// Process page by
/// - skipping if already visited/processed
/// - skipping if invalid (i.e. leaves main domain)
/// - archive contents
/// - recursively process links
/// </summary>
/// <param name="uri"></param>
/// <returns></returns>
public async Task ProcessPage(Uri uri)
{
var pageUri = UriTracker.TrackUri(UriMapper.MapUri(uri));
if (pageUri == null)
{
Logger.LogDebug($"skipped uri: {uri}");
// uri is invalid, already visited or in progress
return;
}
// Fetch page
var pageContent = await PageLoader.DownloadPage(pageUri);
// parallell: Ensure page is saved
var saveCompletion = PageArchive.SavePage(pageUri, pageContent);
// paralell: Process links
var crawlCompletion = ProcessLinks(pageUri, pageContent);
// wait for all parallell
await Task.WhenAll(saveCompletion, crawlCompletion);
}
public Task ProcessPage(string link)
{
return(ProcessPage(UriMapper.MapLink(link)));
}
