/// <summary>
/// Determines whether the specified crawl request is disallowed.
/// </summary>
/// <param name = "crawlRequest">The crawl request.</param>
/// <param name = "arachnodeDAO">The arachnode DAO.</param>
/// <returns>
/// <c>true</c> if the specified crawl request is disallowed; otherwise, <c>false</c>.
/// </returns>
public override bool IsDisallowed(CrawlRequest <TArachnodeDAO> crawlRequest, IArachnodeDAO arachnodeDAO)
{
//ANODET: When you add the multi-server caching, the robots.txt file will need to be sent to all other CachePeers.
//if we're not being called by the Engine prior to assigning to a Crawl...
if (crawlRequest.Crawl != null)
{
string robotsDotTextAbsoluteUri = crawlRequest.Discovery.Uri.Scheme + Uri.SchemeDelimiter + crawlRequest.Discovery.Uri.Host + "/robots.txt";
crawlRequest.OutputIsDisallowedReason = OutputIsDisallowedReason;
if (!UserDefinedFunctions.IsDisallowedForAbsoluteUri(robotsDotTextAbsoluteUri, false, false))
{
if (crawlRequest.Politeness.DisallowedPaths == null || (crawlRequest.Politeness.DisallowedPaths != null && DateTime.Now.Subtract(crawlRequest.Politeness.DisallowedPathsSince) > TimeSpan.FromDays(1)))
{
CrawlRequest <TArachnodeDAO> robotsDotTextRequest = new CrawlRequest <TArachnodeDAO>(crawlRequest, crawlRequest.Crawl.Crawler.Cache.GetDiscovery(robotsDotTextAbsoluteUri, arachnodeDAO), 1, 1, (short)UriClassificationType.Host, (short)UriClassificationType.Host, double.MaxValue, RenderType.None, RenderType.None);
robotsDotTextRequest.Discovery.DiscoveryState = DiscoveryState.Undiscovered;
robotsDotTextRequest.Politeness = crawlRequest.Politeness;
Crawl <TArachnodeDAO> crawl = new Crawl <TArachnodeDAO>(crawlRequest.Crawl.Crawler.ApplicationSettings, crawlRequest.Crawl.Crawler.WebSettings, crawlRequest.Crawl.Crawler, crawlRequest.Crawl.Crawler.ActionManager, crawlRequest.Crawl.Crawler.ConsoleManager, crawlRequest.Crawl.Crawler.CookieManager, crawlRequest.Crawl.Crawler.CrawlRequestManager, crawlRequest.Crawl.Crawler.DataTypeManager, crawlRequest.Crawl.Crawler.DiscoveryManager, crawlRequest.Crawl.Crawler.EncodingManager, crawlRequest.Crawl.Crawler.HtmlManager, crawlRequest.Crawl.Crawler.PolitenessManager, crawlRequest.Crawl.Crawler.ProxyManager, crawlRequest.Crawl.Crawler.RuleManager, false);
robotsDotTextRequest.Crawl = crawl;
crawl.ProcessCrawlRequest(robotsDotTextRequest, false, false);
crawlRequest.Politeness.DisallowedPathsSince = DateTime.Now;
//The DataManager will not download the byte stream is ApplicationSettings.AssignFileAndImageDicoveries is set to false. This is by design.
if (robotsDotTextRequest.Data != null && robotsDotTextRequest.Data.Length == 0 && robotsDotTextRequest.WebClient.WebException == null)
{
robotsDotTextRequest.Data = robotsDotTextRequest.WebClient.DownloadHttpData(crawlRequest.Discovery.Uri.AbsoluteUri, robotsDotTextRequest.WebClient.HttpWebResponse.ContentEncoding.ToLowerInvariant() == "gzip", robotsDotTextRequest.WebClient.HttpWebResponse.ContentEncoding.ToLowerInvariant() == "deflate", crawlRequest.Crawl.Crawler.CookieContainer);
}
SiteCrawler.Value.RobotsDotText robotsDotText = _robotsDotTextManager.ParseRobotsDotTextSource(new Uri(crawlRequest.Discovery.Uri.Scheme + Uri.SchemeDelimiter + crawlRequest.Discovery.Uri.Host), robotsDotTextRequest.Data);
crawlRequest.Politeness.CrawlDelayInMilliseconds = robotsDotText.CrawlDelay * 1000;
crawlRequest.Politeness.DisallowedPaths = robotsDotText.DisallowedPaths;
}
if (crawlRequest.Politeness != null)
{
if (crawlRequest.Politeness.DisallowedPaths != null)
{
foreach (string disallowedPath in crawlRequest.Politeness.DisallowedPaths)
{
if (HttpUtility.UrlDecode(crawlRequest.Discovery.Uri.AbsoluteUri).StartsWith(HttpUtility.UrlDecode(disallowedPath)))
{
crawlRequest.IsDisallowedReason = "Prohibited by robots.txt.";
return(true);
}
}
}
}
}
}
return(false);
}
/// <summary>
/// Determines whether the specified a disallowed is disallowed.
/// </summary>
/// <param name = "aDisallowed">A disallowed.</param>
/// <param name = "uri">The URI.</param>
/// <returns>
/// <c>true</c> if the specified a disallowed is disallowed; otherwise, <c>false</c>.
/// </returns>
protected bool IsDisallowed(ADisallowed <TArachnodeDAO> aDisallowed, Uri uri)
{
bool isDisallowed = false;
aDisallowed.OutputIsDisallowedReason = OutputIsDisallowedReason;
#region Disallowed by AbsoluteUri.
if (UserDefinedFunctions.IsDisallowedForAbsoluteUri(uri.AbsoluteUri, true, false))
{
isDisallowed = true;
}
if (_negateIsDisallowedForAbsoluteUri)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by AbsoluteUri.";
return(true);
}
#endregion
#region Disallowed by Domain.
if (UserDefinedFunctions.IsDisallowedForDomain(uri.AbsoluteUri, false, false))
{
isDisallowed = true;
}
if (_negateIsDisallowedForDomain)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by Domain.";
return(true);
}
#endregion
#region Disallowed by Extension.
if (UserDefinedFunctions.IsDisallowedForExtension(uri.AbsoluteUri, false, false))
{
isDisallowed = true;
}
if (_negateIsDisallowedForExtension)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by Extension.";
return(true);
}
#endregion
#region Disallowed by FileExtension.
if (UserDefinedFunctions.IsDisallowedForFileExtension(uri.AbsoluteUri, false, false))
{
isDisallowed = true;
}
if (_negateIsDisallowedForFileExtension)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by FileExtension.";
return(true);
}
#endregion
#region Disallowed by Host.
if (UserDefinedFunctions.IsDisallowedForHost(uri.AbsoluteUri, false, false))
{
isDisallowed = true;
}
if (_negateIsDisallowedForHost)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by Host.";
return(true);
}
#endregion
#region Disallowed by Scheme.
if (UserDefinedFunctions.IsDisallowedForScheme(uri.AbsoluteUri, false, false))
{
isDisallowed = true;
}
if (_negateIsDisallowedForScheme)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by Scheme.";
return(true);
}
#endregion
#region Disallowed by repeating AbsoluteUri.
if (_detectRepeatingAbsoluteUrisRegex.IsMatch(uri.AbsoluteUri))
{
isDisallowed = true;
}
if (_negateIsDisallowedForRepeatingAbsoluteUri)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by repeating AbsoluteUri.";
return(true);
}
#endregion
#region Disallowed by maximum directory depth.
if (uri.AbsoluteUri.Replace("/", string.Empty).Length < uri.AbsoluteUri.Length - (_maximumDirectoryDepth + 2))
{
isDisallowed = true;
}
if (_negateIsDisallowedForMaximumDirectoryDepth)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by maximum directory depth.";
return(true);
}
#endregion
#region Disallowed by named anchor.
//if (_disallowNamedAnchors && _detectAbsoluteUrisWithNamedAnchorRegex.IsMatch(discovery.Uri.AbsoluteUri))
if (_disallowNamedAnchors && !string.IsNullOrEmpty(uri.Fragment))
{
isDisallowed = true;
}
if (_negateIsDisallowedForNamedAnchor)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by named anchor.";
return(true);
}
#endregion
#region Disallowed by query string.
//if (_disallowQueryStrings && _detectAbsoluteUrisWithQueryStringRegex.IsMatch(discovery.Uri.AbsoluteUri))
if (_disallowQueryStrings && !string.IsNullOrEmpty(uri.Query))
{
isDisallowed = true;
}
if (_negateIsDisallowedForQueryString)
{
isDisallowed = !isDisallowed;
}
if (isDisallowed)
{
aDisallowed.IsDisallowedReason = "Disallowed by query string.";
return(true);
}
#endregion
return(false);
}
