protected override bool ShouldCrawlPage(PageToCrawl pageToCrawl)
{
bool allowedByRobots = true;
if (_robotsDotText != null)
{
allowedByRobots = _robotsDotText.IsUrlAllowed(pageToCrawl.Uri.AbsoluteUri, _crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
}
if (!allowedByRobots && pageToCrawl.IsRoot && _crawlContext.CrawlConfiguration.IsIgnoreRobotsDotTextIfRootDisallowedEnabled)
{
string message = string.Format("Page [{0}] [Disallowed by robots.txt file], however since IsIgnoreRobotsDotTextIfRootDisallowedEnabled is set to true the robots.txt file will be ignored for this site.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
allowedByRobots = true;
_robotsDotText = null;
}
else if (!allowedByRobots)
{
string message = string.Format("Page [{0}] not crawled, [Disallowed by robots.txt file], set IsRespectRobotsDotText=false in config file if you would like to ignore robots.txt files.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
FirePageCrawlDisallowedEventAsync(pageToCrawl, message);
FirePageCrawlDisallowedEvent(pageToCrawl, message);
return(false);
}
return(allowedByRobots && base.ShouldCrawlPage(pageToCrawl));
}
public override CrawlResult Crawl(Uri uri, CancellationTokenSource cancellationTokenSource)
{
int robotsDotTextCrawlDelayInSecs = 0;
int robotsDotTextCrawlDelayInMillisecs = 0;
//Load robots.txt
if (_crawlContext.CrawlConfiguration.IsRespectRobotsDotTextEnabled)
{
_robotsDotText = _robotsDotTextFinder.Find(uri);
if (_robotsDotText != null)
{
FireRobotsDotTextParseCompletedAsync(_robotsDotText.Robots);
FireRobotsDotTextParseCompleted(_robotsDotText.Robots);
robotsDotTextCrawlDelayInSecs = _robotsDotText.GetCrawlDelay(_crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
}
// Additional url patterns to exclude
var urlPatternsToExclude = _crawlContext.CrawlConfiguration.UrlPatternsToExclude;
if (urlPatternsToExclude != null && urlPatternsToExclude.Count > 0)
{
if (_robotsDotText == null)
{
_robotsDotText = new RobotsDotText(uri, String.Empty);
}
if (_robotsDotText.Robots is Robots.Robots)
{
foreach (var pattern in urlPatternsToExclude)
{
((Robots.Robots)_robotsDotText.Robots).AddDisallowEntry(_crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString, pattern);
}
}
}
//Use whichever value is greater between the actual crawl delay value found, the max allowed crawl delay value or the minimum crawl delay required for every domain
if (robotsDotTextCrawlDelayInSecs > 0 && robotsDotTextCrawlDelayInMillisecs > _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds)
{
if (robotsDotTextCrawlDelayInSecs > _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds)
{
_logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] is above the value set in the config value MaxRobotsDotTextCrawlDelay, will use MaxRobotsDotTextCrawlDelay value instead.", uri, _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds);
robotsDotTextCrawlDelayInSecs = _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds;
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
_logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] will be respected.", uri, robotsDotTextCrawlDelayInSecs);
_domainRateLimiter.AddDomain(uri, robotsDotTextCrawlDelayInMillisecs);
}
PageCrawlStarting += (s, e) => _domainRateLimiter.RateLimit(e.PageToCrawl.Uri);
return(base.Crawl(uri, cancellationTokenSource));
}
public void Find_RobotsExists_UriIsRootDomainNoSlash_ReturnsRobotsDotText()
{
Uri _rootUri = new Uri("http://a.com");
Uri expectedRobotsUri = new Uri("http://a.com/robots.txt");
_fakePageRequester.Setup(f => f.MakeRequest(It.Is <Uri>(u => u == expectedRobotsUri))).Returns(_goodPageResult);
IRobotsDotText result = _uut.Find(_rootUri);
_fakePageRequester.Verify(f => f.MakeRequest(It.Is <Uri>(u => u == expectedRobotsUri)), Times.Exactly(1));
Assert.IsNotNull(result);
}
public async Task Find_RobotsExists_UriIsNotRootDomain_ReturnsRobotsDotText()
{
Uri _rootUri = new Uri("http://a.com/a/b/b.html");
Uri expectedRobotsUri = new Uri("http://a.com/robots.txt");
_fakePageRequester.Setup(f => f.MakeRequestAsync(It.Is <Uri>(u => u == expectedRobotsUri))).Returns(Task.FromResult(_goodPageResult));
IRobotsDotText result = await _uut.FindAsync(_rootUri);
_fakePageRequester.Verify(f => f.MakeRequestAsync(It.Is <Uri>(u => u == expectedRobotsUri)), Times.Exactly(1));
Assert.IsNotNull(result);
}
/// <summary>
/// Try to find and load site robots.txt
/// </summary>
/// <param name="uri"></param>
protected bool TryLoadRobotsTxt(Uri uri)
{
int robotsDotTextCrawlDelayInSecs = 0;
long robotsDotTextCrawlDelayInMillisecs = 0;
// Load robots.txt
if (CrawlContext.CrawlConfiguration.IsRespectRobotsDotTextEnabled)
{
RobotsDotText = RobotsDotTextFinder.Find(uri);
if (RobotsDotText != null)
{
Logger.InfoFormat("Robots.txt was found!");
FireRobotsDotTextParseCompletedAsync(RobotsDotText.Robots);
FireRobotsDotTextParseCompleted(RobotsDotText.Robots);
robotsDotTextCrawlDelayInSecs = RobotsDotText.GetCrawlDelay(CrawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
robotsDotTextCrawlDelayInMillisecs = TimeConverter.SecondsToMilliseconds(robotsDotTextCrawlDelayInSecs);
}
else
{
Logger.InfoFormat("Robots.txt was NOT found!");
}
}
// Use whichever value is greater between the actual crawl delay value found,
// the max allowed crawl delay value or the minimum crawl delay required for every domain
if (robotsDotTextCrawlDelayInSecs > 0 &&
robotsDotTextCrawlDelayInMillisecs > CrawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds)
{
if (robotsDotTextCrawlDelayInSecs > CrawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds)
{
Logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] is above the value set " +
"in the config value MaxRobotsDotTextCrawlDelay, will use MaxRobotsDotTextCrawlDelay value instead.",
uri,
CrawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds);
robotsDotTextCrawlDelayInSecs = CrawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds;
robotsDotTextCrawlDelayInMillisecs = TimeConverter.SecondsToMilliseconds(robotsDotTextCrawlDelayInSecs);
}
Logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] will be respected.",
uri,
robotsDotTextCrawlDelayInSecs);
DomainRateLimiter.AddDomain(uri, robotsDotTextCrawlDelayInMillisecs);
}
return(RobotsDotText != null);
}
/// <summary>
///
/// </summary>
/// <param name="pageToCrawl"></param>
/// <returns></returns>
protected override bool ShouldCrawlPage(PageToCrawl pageToCrawl)
{
bool allowedByRobots = true;
if (_robotsDotText != null)
{
allowedByRobots = _robotsDotText.IsUrlAllowed(pageToCrawl.Uri.AbsoluteUri, _crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
}
//https://github.com/sjdirect/abot/issues/96 Handle scenario where the root is allowed but all the paths below are disallowed like "disallow: /*"
var allPathsBelowRootAllowedByRobots = false;
if (_robotsDotText != null && pageToCrawl.IsRoot && allowedByRobots)
{
var anyPathOffRoot = pageToCrawl.Uri.AbsoluteUri.EndsWith("/") ? pageToCrawl.Uri.AbsoluteUri + "aaaaa": pageToCrawl.Uri.AbsoluteUri + "/aaaaa";
allPathsBelowRootAllowedByRobots = _robotsDotText.IsUrlAllowed(anyPathOffRoot, _crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
}
if (_crawlContext.CrawlConfiguration.IsIgnoreRobotsDotTextIfRootDisallowedEnabled && pageToCrawl.IsRoot)
{
if (!allowedByRobots)
{
string message = string.Format("Page [{0}] [Disallowed by robots.txt file], however since IsIgnoreRobotsDotTextIfRootDisallowedEnabled is set to true the robots.txt file will be ignored for this site.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
allowedByRobots = true;
_robotsDotText = null;
}
else if (!allPathsBelowRootAllowedByRobots)
{
string message = string.Format("All Pages below [{0}] [Disallowed by robots.txt file], however since IsIgnoreRobotsDotTextIfRootDisallowedEnabled is set to true the robots.txt file will be ignored for this site.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
allowedByRobots = true;
_robotsDotText = null;
}
}
else if (!allowedByRobots)
{
string message = string.Format("Page [{0}] not crawled, [Disallowed by robots.txt file], set IsRespectRobotsDotText=false in config file if you would like to ignore robots.txt files.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
FirePageCrawlDisallowedEventAsync(pageToCrawl, message);
FirePageCrawlDisallowedEvent(pageToCrawl, message);
return(false);
}
return(allowedByRobots && base.ShouldCrawlPage(pageToCrawl));
}
public override CrawlResult Crawl(Uri uri, CancellationTokenSource cancellationTokenSource)
{
int robotsDotTextCrawlDelayInSecs = 0;
int robotsDotTextCrawlDelayInMillisecs = 0;
int maxRobotsDotTextCrawlDelayInSeconds = _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds;
int maxRobotsDotTextCrawlDelayInMilliSecs = maxRobotsDotTextCrawlDelayInSeconds * 1000;
//Load robots.txt
if (_crawlContext.CrawlConfiguration.IsRespectRobotsDotTextEnabled)
{
_robotsDotText = _robotsDotTextFinder.Find(uri);
if (_robotsDotText != null)
{
robotsDotTextCrawlDelayInSecs = _robotsDotText.GetCrawlDelay(_crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
}
//Use whichever value is greater between the actual crawl delay value found, the max allowed crawl delay value or the minimum crawl delay required for every domain
if (robotsDotTextCrawlDelayInSecs > 0 && robotsDotTextCrawlDelayInMillisecs > _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds)
{
if (robotsDotTextCrawlDelayInSecs > maxRobotsDotTextCrawlDelayInSeconds)
{
_logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] is above the value set in the config value MaxRobotsDotTextCrawlDelay, will use MaxRobotsDotTextCrawlDelay value instead.", uri, robotsDotTextCrawlDelayInSecs);
robotsDotTextCrawlDelayInSecs = maxRobotsDotTextCrawlDelayInSeconds;
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
_logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] will be respected.", uri, robotsDotTextCrawlDelayInSecs);
_domainRateLimiter.AddDomain(uri, robotsDotTextCrawlDelayInMillisecs);
}
if (robotsDotTextCrawlDelayInSecs > 0 || _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds > 0)
{
PageCrawlStarting += (s, e) => _domainRateLimiter.RateLimit(e.PageToCrawl.Uri);
}
return(base.Crawl(uri, cancellationTokenSource));
}
public override CrawlResult Crawl(Uri uri, CancellationTokenSource cancellationTokenSource)
{
var robotsDotTextCrawlDelayInSecs = 0;
var robotsDotTextCrawlDelayInMillisecs = 0;
//Load robots.txt
if (_crawlContext.CrawlConfiguration.IsRespectRobotsDotTextEnabled)
{
_robotsDotText = _robotsDotTextFinder.Find(uri);
if (_robotsDotText != null)
{
robotsDotTextCrawlDelayInSecs = _robotsDotText.GetCrawlDelay(_crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
}
//Use whichever value is greater between the actual crawl delay value found, the max allowed crawl delay value or the minimum crawl delay required for every domain
if (robotsDotTextCrawlDelayInSecs > 0 && robotsDotTextCrawlDelayInMillisecs > _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds)
{
if (robotsDotTextCrawlDelayInSecs > _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds)
{
_logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] is above the value set in the config value MaxRobotsDotTextCrawlDelay, will use MaxRobotsDotTextCrawlDelay value instead.", uri, _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds);
robotsDotTextCrawlDelayInSecs = _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds;
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
_logger.WarnFormat("[{0}] robot.txt file directive [Crawl-delay: {1}] will be respected.", uri, robotsDotTextCrawlDelayInSecs);
_domainRateLimiter.AddDomain(uri, robotsDotTextCrawlDelayInMillisecs);
}
//if (robotsDotTextCrawlDelayInSecs > 0 || _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds > 0)
// PageCrawlStarting += (s, e) => _domainRateLimiter.RateLimit(e.PageToCrawl.Uri);
if (robotsDotTextCrawlDelayInSecs > 0 || _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds > 0)
PageCrawlCompleted += (s, e) => _domainRateLimiter.RateLimit((WebProxy)e.CrawledPage.HttpWebRequest.Proxy, e.CrawledPage.Uri);
return base.Crawl(uri, cancellationTokenSource);
}
public override async Task <CrawlResult> CrawlAsync(Uri uri, CancellationTokenSource cancellationTokenSource)
{
var robotsDotTextCrawlDelayInSecs = 0;
var robotsDotTextCrawlDelayInMillisecs = 0;
//Load robots.txt
if (_crawlContext.CrawlConfiguration.IsRespectRobotsDotTextEnabled)
{
_robotsDotText = await _robotsDotTextFinder.FindAsync(uri);
if (_robotsDotText != null)
{
FireRobotsDotTextParseCompletedAsync(_robotsDotText.Robots);
FireRobotsDotTextParseCompleted(_robotsDotText.Robots);
robotsDotTextCrawlDelayInSecs = _robotsDotText.GetCrawlDelay(_crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
}
//Use whichever value is greater between the actual crawl delay value found, the max allowed crawl delay value or the minimum crawl delay required for every domain
if (robotsDotTextCrawlDelayInSecs > 0 && robotsDotTextCrawlDelayInMillisecs > _crawlContext.CrawlConfiguration.MinCrawlDelayPerDomainMilliSeconds)
{
if (robotsDotTextCrawlDelayInSecs > _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds)
{
_logger.LogWarning($"[{uri}] robot.txt file directive [Crawl-delay: {_crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds}] is above the value set in the config value MaxRobotsDotTextCrawlDelay, will use MaxRobotsDotTextCrawlDelay value instead.");
robotsDotTextCrawlDelayInSecs = _crawlContext.CrawlConfiguration.MaxRobotsDotTextCrawlDelayInSeconds;
robotsDotTextCrawlDelayInMillisecs = robotsDotTextCrawlDelayInSecs * 1000;
}
_logger.LogWarning($"[{uri}] robot.txt file directive [Crawl-delay: {robotsDotTextCrawlDelayInSecs}] will be respected.");
_domainRateLimiter.AddDomain(uri, robotsDotTextCrawlDelayInMillisecs);
}
PageCrawlStarting += (s, e) => _domainRateLimiter.RateLimit(e.PageToCrawl.Uri);
return(await base.CrawlAsync(uri, cancellationTokenSource));
}
protected override bool ShouldCrawlPage(PageToCrawl pageToCrawl)
{
bool allowedByRobots = true;
if (_robotsDotText != null)
allowedByRobots = _robotsDotText.IsUrlAllowed(pageToCrawl.Uri.AbsoluteUri, _crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
if (!allowedByRobots && pageToCrawl.IsRoot && _crawlContext.CrawlConfiguration.IsIgnoreRobotsDotTextIfRootDisallowedEnabled)
{
string message = string.Format("Page [{0}] [Disallowed by robots.txt file], however since IsIgnoreRobotsDotTextIfRootDisallowedEnabled is set to true the robots.txt file will be ignored for this site.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
allowedByRobots = true;
_robotsDotText = null;
}
else if (!allowedByRobots)
{
string message = string.Format("Page [{0}] not crawled, [Disallowed by robots.txt file], set IsRespectRobotsDotText=false in config file if you would like to ignore robots.txt files.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
FirePageCrawlDisallowedEventAsync(pageToCrawl, message);
FirePageCrawlDisallowedEvent(pageToCrawl, message);
return false;
}
return allowedByRobots && base.ShouldCrawlPage(pageToCrawl);
}
protected override bool ShouldCrawlPage(PageToCrawl pageToCrawl)
{
bool allowedByRobots = true;
if (_robotsDotText != null)
allowedByRobots = _robotsDotText.IsUrlAllowed(pageToCrawl.Uri.AbsoluteUri, _crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
//https://github.com/sjdirect/abot/issues/96 Handle scenario where the root is allowed but all the paths below are disallowed like "disallow: /*"
var allPathsBelowRootAllowedByRobots = false;
if (_robotsDotText != null && pageToCrawl.IsRoot && allowedByRobots)
{
var anyPathOffRoot = pageToCrawl.Uri.AbsoluteUri.EndsWith("/") ? pageToCrawl.Uri.AbsoluteUri + "aaaaa": pageToCrawl.Uri.AbsoluteUri + "/aaaaa";
allPathsBelowRootAllowedByRobots = _robotsDotText.IsUrlAllowed(anyPathOffRoot, _crawlContext.CrawlConfiguration.RobotsDotTextUserAgentString);
}
if (_crawlContext.CrawlConfiguration.IsIgnoreRobotsDotTextIfRootDisallowedEnabled && pageToCrawl.IsRoot)
{
if (!allowedByRobots)
{
string message = string.Format("Page [{0}] [Disallowed by robots.txt file], however since IsIgnoreRobotsDotTextIfRootDisallowedEnabled is set to true the robots.txt file will be ignored for this site.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
allowedByRobots = true;
_robotsDotText = null;
}
else if (!allPathsBelowRootAllowedByRobots)
{
string message = string.Format("All Pages below [{0}] [Disallowed by robots.txt file], however since IsIgnoreRobotsDotTextIfRootDisallowedEnabled is set to true the robots.txt file will be ignored for this site.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
allowedByRobots = true;
_robotsDotText = null;
}
}
else if (!allowedByRobots)
{
string message = string.Format("Page [{0}] not crawled, [Disallowed by robots.txt file], set IsRespectRobotsDotText=false in config file if you would like to ignore robots.txt files.", pageToCrawl.Uri.AbsoluteUri);
_logger.DebugFormat(message);
FirePageCrawlDisallowedEventAsync(pageToCrawl, message);
FirePageCrawlDisallowedEvent(pageToCrawl, message);
return false;
}
return allowedByRobots && base.ShouldCrawlPage(pageToCrawl);
}
