/**************************************************************************/ private MacroscopeLink AddSitemapTextOutlink( string AbsoluteUrl, MacroscopeConstants.InOutLinkType LinkType, Boolean Follow ) { MacroscopeLink OutLink = null; if (!MacroscopePreferencesManager.GetCheckExternalLinks()) { MacroscopeAllowedHosts AllowedHosts = this.DocCollection.GetAllowedHosts(); if (AllowedHosts != null) { if (!AllowedHosts.IsAllowedFromUrl(Url: AbsoluteUrl)) { return(OutLink); } } } OutLink = new MacroscopeLink( SourceUrl: this.GetUrl(), TargetUrl: AbsoluteUrl, LinkType: LinkType, Follow: Follow ); this.Outlinks.Add(OutLink); return(OutLink); }
/**************************************************************************/ private MacroscopeLink AddSitemapXmlOutlink( string AbsoluteUrl, MacroscopeConstants.InOutLinkType LinkType, Boolean Follow ) { MacroscopeLink OutLink = null; Boolean Proceed = true; if (!MacroscopePreferencesManager.GetCheckExternalLinks()) { MacroscopeAllowedHosts AllowedHosts = this.DocCollection.GetAllowedHosts(); if (AllowedHosts != null) { if (!AllowedHosts.IsAllowedFromUrl(Url: AbsoluteUrl)) { Proceed = false; } } } switch (LinkType) { case MacroscopeConstants.InOutLinkType.SITEMAPXML: if (!MacroscopePreferencesManager.GetFetchXml()) { Proceed = false; } break; } if (Proceed) { OutLink = new MacroscopeLink( SourceUrl: this.GetUrl(), TargetUrl: AbsoluteUrl, LinkType: LinkType, Follow: Follow ); this.Outlinks.Add(OutLink); } return(OutLink); }
/**************************************************************************/ public void SetPrefsFormControlFields() { { // Configure Display Options this.checkBoxPauseDisplayDuringScan.Checked = MacroscopePreferencesManager.GetPauseDisplayDuringScan(); this.checkBoxShowProgressDialogues.Checked = MacroscopePreferencesManager.GetShowProgressDialogues(); } { //Configure Form Fields /** Spidering Control ---------------------------------------------- **/ this.numericUpDownDepth.Minimum = -1; this.numericUpDownDepth.Maximum = 10000; this.numericUpDownPageLimit.Minimum = -1; this.numericUpDownPageLimit.Maximum = 10000; this.numericUpDownCrawlDelay.Minimum = 0; this.numericUpDownCrawlDelay.Maximum = 60; this.numericUpDownMaxRetries.Minimum = 0; this.numericUpDownMaxRetries.Maximum = 10; } { /** WebProxy Options ----------------------------------------------- **/ this.comboBoxProxyType.SelectedIndex = (int)MacroscopePreferencesManager.GetProxyType(); /** Server Certificate Options --------------------------------------- **/ this.checkBoxServerCertificateValidation.Checked = MacroscopePreferencesManager.GetServerCertificateValidation(); /** Spidering Control ---------------------------------------------- **/ this.numericUpDownMaxThreads.Value = MacroscopePreferencesManager.GetMaxThreads(); this.numericUpDownDepth.Value = MacroscopePreferencesManager.GetDepth(); this.numericUpDownPageLimit.Value = MacroscopePreferencesManager.GetPageLimit(); this.numericUpDownCrawlDelay.Value = MacroscopePreferencesManager.GetCrawlDelay(); this.numericUpDownRequestTimeout.Value = (Decimal)MacroscopePreferencesManager.GetRequestTimeout(); this.numericUpDownMaxRetries.Value = (Decimal)MacroscopePreferencesManager.GetMaxRetries(); this.checkBoxCrawlStrictUrlCheck.Checked = MacroscopePreferencesManager.GetCrawlStrictUrlCheck(); this.checkBoxCheckExternalLinks.Checked = MacroscopePreferencesManager.GetCheckExternalLinks(); this.checkBoxFetchExternalLinks.Checked = MacroscopePreferencesManager.GetFetchExternalLinks(); this.checkBoxFollowRobotsProtocol.Checked = MacroscopePreferencesManager.GetFollowRobotsProtocol(); this.checkBoxFollowSitemapLinks.Checked = MacroscopePreferencesManager.GetFollowSitemapLinks(); this.checkBoxProbeHumansText.Checked = MacroscopePreferencesManager.GetProbeHumansText(); this.checkBoxCheckRedirects.Checked = MacroscopePreferencesManager.GetCheckRedirects(); this.checkBoxFollowRedirects.Checked = MacroscopePreferencesManager.GetFollowRedirects(); this.checkBoxFollowNoFollow.Checked = MacroscopePreferencesManager.GetFollowNoFollow(); this.checkBoxIgnoreQueries.Checked = MacroscopePreferencesManager.GetIgnoreQueries(); this.checkBoxIgnoreHashFragments.Checked = MacroscopePreferencesManager.GetIgnoreHashFragments(); this.checkBoxFollowCanonicalLinks.Checked = MacroscopePreferencesManager.GetFollowCanonicalLinks(); this.checkBoxFollowAlternateLinks.Checked = MacroscopePreferencesManager.GetFollowAlternateLinks(); this.checkBoxFollowHrefLangLinks.Checked = MacroscopePreferencesManager.GetFollowHrefLangLinks(); this.checkBoxDowncaseLinks.Checked = MacroscopePreferencesManager.GetDowncaseLinks(); this.checkBoxFetchStylesheets.Checked = MacroscopePreferencesManager.GetFetchStylesheets(); this.checkBoxFetchJavascripts.Checked = MacroscopePreferencesManager.GetFetchJavascripts(); this.checkBoxFetchImages.Checked = MacroscopePreferencesManager.GetFetchImages(); this.checkBoxFetchAudio.Checked = MacroscopePreferencesManager.GetFetchAudio(); this.checkBoxFetchVideo.Checked = MacroscopePreferencesManager.GetFetchVideo(); this.checkBoxFetchXml.Checked = MacroscopePreferencesManager.GetFetchXml(); this.checkBoxFetchBinaries.Checked = MacroscopePreferencesManager.GetFetchBinaries(); this.checkBoxScanSitesInList.Checked = MacroscopePreferencesManager.GetScanSitesInList(); this.checkBoxProbeParentFolderUrls.Checked = MacroscopePreferencesManager.GetProbeParentFolderUrls(); this.checkBoxProbeHead404sWithGet.Checked = MacroscopePreferencesManager.GetProbeHead404sWithGet(); /** Analysis Options ----------------------------------------------- **/ this.checkBoxResolveAddresses.Checked = MacroscopePreferencesManager.GetResolveAddresses(); this.checkBoxCheckHreflangs.Checked = MacroscopePreferencesManager.GetCheckHreflangs(); this.checkBoxDetectLanguage.Checked = MacroscopePreferencesManager.GetDetectLanguage(); this.checkBoxProcessStylesheets.Checked = MacroscopePreferencesManager.GetProcessStylesheets(); this.checkBoxProcessJavascripts.Checked = MacroscopePreferencesManager.GetProcessJavascripts(); this.checkBoxProcessImages.Checked = MacroscopePreferencesManager.GetProcessImages(); this.checkBoxProcessPdfs.Checked = MacroscopePreferencesManager.GetProcessPdfs(); this.checkBoxProcessAudio.Checked = MacroscopePreferencesManager.GetProcessAudio(); this.checkBoxProcessVideo.Checked = MacroscopePreferencesManager.GetProcessVideo(); this.checkBoxProcessXml.Checked = MacroscopePreferencesManager.GetProcessXml(); this.checkBoxProcessBinaries.Checked = MacroscopePreferencesManager.GetProcessBinaries(); this.numericUpDownRedirectChainsMaxHops.Value = MacroscopePreferencesManager.GetRedirectChainsMaxHops(); this.checkBoxWarnAboutInsecureLinks.Checked = MacroscopePreferencesManager.GetWarnAboutInsecureLinks(); this.checkBoxEnableTextIndexing.Checked = MacroscopePreferencesManager.GetEnableTextIndexing(); this.checkBoxCaseSensitiveTextIndexing.Checked = MacroscopePreferencesManager.GetCaseSensitiveTextIndexing(); this.checkBoxDisregardHtml5ElementNav.Checked = MacroscopePreferencesManager.GetDisregardHtml5ElementNav(); this.checkBoxDisregardHtml5ElementHeader.Checked = MacroscopePreferencesManager.GetDisregardHtml5ElementHeader(); this.checkBoxDisregardHtml5ElementFooter.Checked = MacroscopePreferencesManager.GetDisregardHtml5ElementFooter(); this.checkBoxDetectQrCodeInImage.Checked = MacroscopePreferencesManager.GetDetectQrCodeInImage(); /** SEO Options ---------------------------------------------------- **/ this.numericUpDownTitleMinLen.Value = MacroscopePreferencesManager.GetTitleMinLen(); this.numericUpDownTitleMaxLen.Value = MacroscopePreferencesManager.GetTitleMaxLen(); this.numericUpDownTitleMinWords.Value = MacroscopePreferencesManager.GetTitleMinWords(); this.numericUpDownTitleMaxWords.Value = MacroscopePreferencesManager.GetTitleMaxWords(); this.numericUpDownTitleMaxPixelWidth.Value = MacroscopePreferencesManager.GetTitleMaxPixelWidth(); this.numericUpDownDescriptionMinLen.Value = MacroscopePreferencesManager.GetDescriptionMinLen(); this.numericUpDownDescriptionMaxLen.Value = MacroscopePreferencesManager.GetDescriptionMaxLen(); this.numericUpDownDescriptionMinWords.Value = MacroscopePreferencesManager.GetDescriptionMinWords(); this.numericUpDownDescriptionMaxWords.Value = MacroscopePreferencesManager.GetDescriptionMaxWords(); this.numericUpDownMaxHeadingDepth.Value = MacroscopePreferencesManager.GetMaxHeadingDepth(); this.checkBoxAnalyzeKeywordsInText.Checked = MacroscopePreferencesManager.GetAnalyzeKeywordsInText(); this.checkBoxAnalyzeTextReadability.Checked = MacroscopePreferencesManager.GetAnalyzeTextReadability(); this.comboBoxAnalyzeTextReadabilityEnglishAlgorithm.SelectedIndex = (int)MacroscopePreferencesManager.GetAnalyzeTextReadabilityEnglishAlgorithm(); this.checkBoxEnableLevenshteinDeduplication.Checked = MacroscopePreferencesManager.GetEnableLevenshteinDeduplication(); this.comboBoxLevenshteinAnalysisLevel.SelectedIndex = (int)MacroscopePreferencesManager.GetLevenshteinAnalysisLevel(); this.numericUpDownMaxLevenshteinSizeDifference.Value = MacroscopePreferencesManager.GetMaxLevenshteinSizeDifference(); this.numericUpDownMaxLevenshteinDistance.Value = MacroscopePreferencesManager.GetMaxLevenshteinDistance(); this.checkBoxAnalyzeClickPaths.Checked = MacroscopePreferencesManager.GetAnalyzeClickPaths(); // TODO: Finish implementing click path analysis: #if DEBUG this.groupBoxPageNavigationAnalysis.Visible = true; #else this.groupBoxPageNavigationAnalysis.Visible = false; #endif /** Custom Filter Options ------------------------------------------ **/ this.checkBoxCustomFiltersEnable.Checked = MacroscopePreferencesManager.GetCustomFiltersEnable(); this.numericUpDownCustomFiltersMaxItems.Value = MacroscopePreferencesManager.GetCustomFiltersMaxItems(); this.checkBoxCustomFiltersApplyToHtml.Checked = MacroscopePreferencesManager.GetCustomFiltersApplyToHtml(); this.checkBoxCustomFiltersApplyToCss.Checked = MacroscopePreferencesManager.GetCustomFiltersApplyToCss(); this.checkBoxCustomFiltersApplyToJavascripts.Checked = MacroscopePreferencesManager.GetCustomFiltersApplyToJavascripts(); this.checkBoxCustomFiltersApplyToText.Checked = MacroscopePreferencesManager.GetCustomFiltersApplyToText(); this.checkBoxCustomFiltersApplyToXml.Checked = MacroscopePreferencesManager.GetCustomFiltersApplyToXml(); /** Extractor Options ---------------------------------------------- **/ this.checkBoxDataExtractorsEnable.Checked = MacroscopePreferencesManager.GetDataExtractorsEnable(); this.checkBoxDataExtractorsCleanWhiteSpace.Checked = MacroscopePreferencesManager.GetDataExtractorsCleanWhiteSpace(); this.numericUpDownDataExtractorsMaxItemsCssSelectors.Value = MacroscopePreferencesManager.GetDataExtractorsMaxItemsCssSelectors(); this.numericUpDownDataExtractorsMaxItemsRegexes.Value = MacroscopePreferencesManager.GetDataExtractorsMaxItemsRegexes(); this.numericUpDownDataExtractorsMaxItemsXpaths.Value = MacroscopePreferencesManager.GetDataExtractorsMaxItemsXpaths(); this.checkBoxDataExtractorsApplyToHtml.Checked = MacroscopePreferencesManager.GetDataExtractorsApplyToHtml(); this.checkBoxDataExtractorsApplyToCss.Checked = MacroscopePreferencesManager.GetDataExtractorsApplyToCss(); this.checkBoxDataExtractorsApplyToJavascripts.Checked = MacroscopePreferencesManager.GetDataExtractorsApplyToJavascripts(); this.checkBoxDataExtractorsApplyToText.Checked = MacroscopePreferencesManager.GetDataExtractorsApplyToText(); this.checkBoxDataExtractorsApplyToPdf.Checked = MacroscopePreferencesManager.GetDataExtractorsApplyToPdf(); this.checkBoxDataExtractorsApplyToXml.Checked = MacroscopePreferencesManager.GetDataExtractorsApplyToXml(); /** Export Options ------------------------------------------------- **/ this.checkBoxSitemapIncludeLinkedPdfs.Checked = MacroscopePreferencesManager.GetSitemapIncludeLinkedPdfs(); /** Ignore Errors Settings ----------------------------------------- **/ this.checkBoxIgnoreErrors410.Checked = MacroscopePreferencesManager.GetIgnoreErrors410(); this.checkBoxIgnoreErrors451.Checked = MacroscopePreferencesManager.GetIgnoreErrors451(); } }
/**************************************************************************/ private async Task <MacroscopeConstants.FetchStatus> Fetch(string Url, string RedirectedFromUrl = null) { MacroscopeDocument msDoc = null; MacroscopeConstants.FetchStatus FetchStatus = MacroscopeConstants.FetchStatus.VOID; bool BlockedByRobotsRule; if (MacroscopePreferencesManager.GetPageLimit() > -1) { int PagesFound = this.JobMaster.GetPagesFound(); int PageLimit = MacroscopePreferencesManager.GetPageLimit(); if (PagesFound >= PageLimit) { this.DebugMsg(string.Format("PAGE LIMIT REACHED: {0} :: {1}", PageLimit, PagesFound)); return(FetchStatus); } } if (this.DocCollection.ContainsDocument(Url: Url)) { msDoc = this.DocCollection.GetDocumentByUrl(Url: Url); if (msDoc.GetAuthenticationRealm() != null) { if (msDoc.GetAuthenticationType() == MacroscopeConstants.AuthenticationType.BASIC) { MacroscopeCredential Credential; Credential = this.JobMaster.GetCredentialsHttp().GetCredential( msDoc.GetHostAndPort(), msDoc.GetAuthenticationRealm() ); if (Credential != null) { msDoc = this.DocCollection.CreateDocument( Credential: Credential, Url: Url ); } } } } else { msDoc = this.DocCollection.CreateDocument(Url: Url); } if (!string.IsNullOrEmpty(RedirectedFromUrl)) { msDoc.SetUrlRedirectFrom(Url: RedirectedFromUrl); } msDoc.SetFetchStatus(MacroscopeConstants.FetchStatus.OK); if (!MacroscopeDnsTools.CheckValidHostname(Url: Url)) { this.DebugMsg(string.Format("Fetch :: CheckValidHostname: {0}", "NOT OK")); msDoc.SetStatusCode(HttpStatusCode.BadGateway); FetchStatus = MacroscopeConstants.FetchStatus.NETWORK_ERROR; msDoc.SetFetchStatus(FetchStatus); } if (await this.JobMaster.GetRobots().CheckRobotRule(Url: Url)) { msDoc.SetAllowedByRobots(true); } else { msDoc.SetAllowedByRobots(false); } BlockedByRobotsRule = await this.JobMaster.GetRobots().ApplyRobotRule(Url: Url); if (!BlockedByRobotsRule) { this.DebugMsg(string.Format("Disallowed by robots.txt: {0}", Url)); this.JobMaster.AddToBlockedByRobots(Url); FetchStatus = MacroscopeConstants.FetchStatus.ROBOTS_DISALLOWED; msDoc.SetFetchStatus(FetchStatus); JobHistory.VisitedHistoryItem(Url: msDoc.GetUrl()); } else { this.JobMaster.RemoveFromBlockedByRobots(Url); } if (this.AllowedHosts.IsExternalUrl(Url: Url)) { this.DebugMsg(string.Format("IsExternalUrl: {0}", Url)); msDoc.SetIsExternal(State: true); } if (this.DocCollection.ContainsDocument(Url: Url)) { if (!this.DocCollection.GetDocumentByUrl(Url: Url).GetIsDirty()) { FetchStatus = MacroscopeConstants.FetchStatus.ALREADY_SEEN; return(FetchStatus); } } if (MacroscopePreferencesManager.GetDepth() >= 0) { int Depth = MacroscopeHttpUrlUtils.FindUrlDepth(Url: Url); if (Depth > MacroscopePreferencesManager.GetDepth()) { this.DebugMsg(string.Format("URL Too Deep: {0}", Depth)); FetchStatus = MacroscopeConstants.FetchStatus.SKIPPED; return(FetchStatus); } } /** ------------------------------------------------------------------ **/ if (!await msDoc.Execute()) { this.DebugMsg(string.Format("EXECUTE FAILED: {0}", Url)); FetchStatus = MacroscopeConstants.FetchStatus.ERROR; } /** ------------------------------------------------------------------ **/ /** ------------------------------------------------------------------ **/ { if (msDoc.GetStatusCode() == HttpStatusCode.Unauthorized) { if (msDoc.GetAuthenticationType() == MacroscopeConstants.AuthenticationType.BASIC) { MacroscopeCredentialsHttp CredentialsHttp = this.JobMaster.GetCredentialsHttp(); CredentialsHttp.EnqueueCredentialRequest( Domain: msDoc.GetHostAndPort(), Realm: msDoc.GetAuthenticationRealm(), Url: msDoc.GetUrl() ); this.JobMaster.AddUrlQueueItem(Url: msDoc.GetUrl()); } } if (msDoc.GetIsRedirect()) { this.DebugMsg(string.Format("REDIRECTION DETECTED GetUrl: {0}", msDoc.GetUrl())); this.DebugMsg(string.Format("REDIRECTION DETECTED From: {0}", msDoc.GetUrlRedirectFrom())); if (MacroscopePreferencesManager.GetCheckRedirects()) { string Hostname = msDoc.GetHostAndPort(); string HostnameFrom = MacroscopeAllowedHosts.ParseHostnameFromUrl(msDoc.GetUrlRedirectFrom()); string UrlRedirectTo = msDoc.GetUrlRedirectTo(); string HostnameTo = MacroscopeAllowedHosts.ParseHostnameFromUrl(UrlRedirectTo); this.DebugMsg(string.Format("REDIRECTION DETECTED UrlRedirectTo: {0}", UrlRedirectTo)); this.DebugMsg(string.Format("REDIRECTION DETECTED HostnameTo: {0}", HostnameTo)); if (MacroscopePreferencesManager.GetFollowRedirects()) { if (MacroscopePreferencesManager.GetCheckExternalLinks()) { this.AllowedHosts.AddFromUrl(Url: UrlRedirectTo); } else { if (this.AllowedHosts.IsInternalUrl(Url: UrlRedirectTo)) { this.AllowedHosts.AddFromUrl(Url: UrlRedirectTo); } } } } this.JobMaster.AddUrlQueueItem(Url: msDoc.GetUrlRedirectTo()); } else { this.ProcessHrefLangLanguages(msDoc); // Process Languages from HrefLang this.JobMaster.ProcessOutlinks(msDoc: msDoc); // Process Outlinks from document } FetchStatus = MacroscopeConstants.FetchStatus.SUCCESS; } /** ------------------------------------------------------------------ **/ if (DocCollection.ContainsDocument(msDoc: msDoc)) { JobHistory.VisitedHistoryItem(Url: Url); } else { this.DebugMsg(string.Format("OOPS: {0}", Url)); } /** ------------------------------------------------------------------ **/ return(FetchStatus); }