/// <summary>
/// Make an http web request to the url and download its content based on the param func decision
/// </summary>
public virtual async Task <CrawledPage> MakeRequestAsync(Uri uri, Func <CrawledPage, CrawlDecision> shouldDownloadContent)
{
if (uri == null)
{
throw new ArgumentNullException(nameof(uri));
}
var crawledPage = new CrawledPage(uri);
HttpRequestMessage request = null;
HttpResponseMessage httpResponseMessage = null;
try
{
request = BuildRequestObject(uri);
crawledPage.RequestStarted = DateTime.Now;
httpResponseMessage = await _httpClient.SendAsync(request);
}
catch (Exception e)
{
_logger.LogDebug($"Error occurred requesting url [{uri.AbsoluteUri}]", e);
}
finally
{
try
{
crawledPage.HttpRequestMessage = request;
crawledPage.RequestCompleted = DateTime.Now;
if (httpResponseMessage != null)
{
crawledPage.HttpWebResponse = new HttpWebResponseWrapper(httpResponseMessage, _cookieContainer);
var shouldDownloadContentDecision = shouldDownloadContent(crawledPage);
if (shouldDownloadContentDecision.Allow)
{
crawledPage.DownloadContentStarted = DateTime.Now;
crawledPage.Content = await _extractor.GetContentAsync(httpResponseMessage);
crawledPage.DownloadContentCompleted = DateTime.Now;
}
else
{
_logger.LogDebug($"Links on page [{crawledPage.Uri.AbsoluteUri}] not crawled, [{shouldDownloadContentDecision.Reason}]");
}
httpResponseMessage.EnsureSuccessStatusCode();
httpResponseMessage.Dispose();//Should already be closed by _extractor but just being safe
}
}
catch (HttpRequestException e)
{
crawledPage.HttpRequestException = e;
_logger.LogDebug($"Error occurred finalizing requesting url [{uri.AbsoluteUri}]", e);
}
catch (Exception e)
{
_logger.LogDebug($"Error occurred finalizing requesting url [{uri.AbsoluteUri}]", e);
}
}
return(crawledPage);
}
public virtual CrawledPage MakeRequest(Uri uri, Func <CrawledPage, CrawlDecision> shouldDownloadContent)
{
if (uri == null)
{
throw new ArgumentNullException("uri");
}
CrawledPage crawledPage = new CrawledPage(uri);
HttpResponseMessage response = null;
try
{
crawledPage.RequestStarted = DateTime.Now;
HttpRequestMessage request = BuildRequestObject(uri);
response = _client.SendAsync(request).Result;
}
catch (TaskCanceledException e)
{
Error(crawledPage, e);
}
catch (Exception e)
{
Error(crawledPage, e);
}
try
{
crawledPage.RequestCompleted = DateTime.Now;
crawledPage.StatusCode = response.StatusCode;
if (response != null)
{
CrawlDecision shouldDownloadContentDecision = shouldDownloadContent(crawledPage);
if (shouldDownloadContentDecision.Allow)
{
crawledPage.DownloadContentStarted = DateTime.Now;
crawledPage.Content = _webContentExtractor.GetContentAsync(response).Result;
crawledPage.DownloadContentCompleted = DateTime.Now;
}
else
{
_logger.LogWarning("Links on page [{0}] not crawled, [{1}]", crawledPage.Uri.AbsoluteUri, shouldDownloadContentDecision.Reason);
}
response.Dispose();
}
}
catch (Exception e)
{
Error(crawledPage, e);
}
return(crawledPage);
}
/// <summary>
/// Make an http web request to the url and download its content based on the param func decision
/// </summary>
public virtual async Task <CrawledPage> MakeRequestAsync(Uri uri, Func <CrawledPage, CrawlDecision> shouldDownloadContent)
{
if (uri == null)
{
throw new ArgumentNullException(nameof(uri));
}
if (_httpClient == null)
{
_httpClientHandler = BuildHttpClientHandler(uri);
_httpClient = BuildHttpClient(_httpClientHandler);
}
var crawledPage = new CrawledPage(uri);
HttpResponseMessage response = null;
try
{
crawledPage.RequestStarted = DateTime.Now;
using (var requestMessage = BuildHttpRequestMessage(uri))
{
response = await _httpClient.SendAsync(requestMessage, CancellationToken.None).ConfigureAwait(false);
}
var statusCode = Convert.ToInt32(response.StatusCode);
if (statusCode < 200 || statusCode > 399)
{
throw new HttpRequestException($"Server response was unsuccessful, returned [http {statusCode}]");
}
}
catch (HttpRequestException hre)
{
crawledPage.HttpRequestException = hre;
Log.Debug("Error occurred requesting url [{0}] {@Exception}", uri.AbsoluteUri, hre);
}
catch (TaskCanceledException ex)
{
crawledPage.HttpRequestException = new HttpRequestException("Request timeout occurred", ex);//https://stackoverflow.com/questions/10547895/how-can-i-tell-when-httpclient-has-timed-out
Log.Debug("Error occurred requesting url [{0}] {@Exception}", uri.AbsoluteUri, crawledPage.HttpRequestException);
}
catch (Exception e)
{
crawledPage.HttpRequestException = new HttpRequestException("Unknown error occurred", e);
Log.Debug("Error occurred requesting url [{0}] {@Exception}", uri.AbsoluteUri, crawledPage.HttpRequestException);
}
finally
{
crawledPage.HttpRequestMessage = response?.RequestMessage;
crawledPage.RequestCompleted = DateTime.Now;
crawledPage.HttpResponseMessage = response;
crawledPage.HttpClientHandler = _httpClientHandler;
try
{
if (response != null)
{
var shouldDownloadContentDecision = shouldDownloadContent(crawledPage);
if (shouldDownloadContentDecision.Allow)
{
crawledPage.DownloadContentStarted = DateTime.Now;
crawledPage.Content = await _contentExtractor.GetContentAsync(response).ConfigureAwait(false);
if (_config.IsFollowMetaRedirectsEnabled)
{
crawledPage.MetaRedirectURL = _contentExtractor.GetMetaRedirectUrl(crawledPage);
}
crawledPage.DownloadContentCompleted = DateTime.Now;
}
else
{
Log.Debug("Links on page [{0}] not crawled, [{1}]", crawledPage.Uri.AbsoluteUri, shouldDownloadContentDecision.Reason);
}
}
}
catch (Exception e)
{
Log.Debug("Error occurred finalizing requesting url [{0}] {@Exception}", uri.AbsoluteUri, e);
}
}
return(crawledPage);
}
/// <summary>
/// Make an http web request to the url and download its content based on the param func decision
/// </summary>
public virtual async Task <CrawledPage> MakeRequestAsync(Uri uri, Func <CrawledPage, CrawlDecision> shouldDownloadContent)
{
if (uri == null)
{
throw new ArgumentNullException(nameof(uri));
}
if (_httpClient == null)
{
_httpClientHandler = BuildHttpClientHandler(uri);
_httpClient = BuildHttpClient(_httpClientHandler);
}
var crawledPage = new CrawledPage(uri);
HttpResponseMessage response = null;
try
{
crawledPage.RequestStarted = DateTime.Now;
using (var requestMessage = BuildHttpRequestMessage(uri))
{
response = await _httpClient.SendAsync(requestMessage, CancellationToken.None).ConfigureAwait(false);
}
}
catch (HttpRequestException hre)
{
crawledPage.HttpRequestException = hre;
Log.Logger.Debug("Error occurred requesting url [{0}] {@Exception}", uri.AbsoluteUri, hre);
}
catch (Exception e)
{
Log.Logger.Debug("Error occurred requesting url [{0}] {@Exception}", uri.AbsoluteUri, e);
}
finally
{
crawledPage.HttpRequestMessage = response?.RequestMessage;
crawledPage.RequestCompleted = DateTime.Now;
crawledPage.HttpResponseMessage = response;
try
{
if (response != null)
{
var shouldDownloadContentDecision = shouldDownloadContent(crawledPage);
if (shouldDownloadContentDecision.Allow)
{
crawledPage.DownloadContentStarted = DateTime.Now;
crawledPage.Content = await _contentExtractor.GetContentAsync(response).ConfigureAwait(false);
crawledPage.DownloadContentCompleted = DateTime.Now;
}
else
{
Log.Logger.Debug("Links on page [{0}] not crawled, [{1}]", crawledPage.Uri.AbsoluteUri, shouldDownloadContentDecision.Reason);
}
}
}
catch (Exception e)
{
Log.Logger.Debug("Error occurred finalizing requesting url [{0}] {@Exception}", uri.AbsoluteUri, e);
}
}
return(crawledPage);
}
