{"type":"doc","content":[{"type":"paragraph","content":[{"text":"In this article you will find:","type":"text","marks":[{"type":"strong"}]}]},{"type":"extension","attrs":{"layout":"default","extensionType":"com.atlassian.confluence.macro.core","extensionKey":"toc","parameters":{"macroParams":{},"macroMetadata":{"macroId":{"value":"fbeb5361-1984-4f83-8d3a-6aa1f197d0eb"},"schemaVersion":{"value":"1"},"title":"Table of Contents"}}}},{"type":"heading","attrs":{"level":2},"content":[{"text":"Goal","type":"text"}]},{"type":"paragraph","content":[{"text":"This article provides information on how to export Sitefinity’s page content in Hawksearch V4L.","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Prerequisite","type":"text"}]},{"type":"panel","attrs":{"panelType":"info"},"content":[{"type":"paragraph","content":[{"text":"Installed Connector - ","type":"text"},{"type":"inlineCard","attrs":{"url":"https://bridgeline.atlassian.net/wiki/spaces/CON/pages/3468472522"}}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Building a Custom Exporter","type":"text"}]},{"type":"paragraph","content":[{"text":"You can extend the default implementation of the DataLoader class using the IoCKernel in Global.asax on the Bootstrapper_Bootstrapped method.","type":"text"}]},{"type":"paragraph"},{"type":"codeBlock","content":[{"text":"using Hawksearch.SDK;\nusing Hawksearch.SDK.Export;\nusing SitefinityWebApp.Hawksearch;\nusing System;\nusing Telerik.Sitefinity.Abstractions;\n\nnamespace SitefinityWebApp\n{\n public class Global : System.Web.HttpApplication\n {\n protected void Application_Start(object sender, EventArgs e)\n {\n Bootstrapper.Bootstrapped += this.Bootstrapper_Bootstrapped;\n }\n\n private void Bootstrapper_Bootstrapped(object sender, EventArgs e)\n {\n IocKernel.Kernel.Rebind().To();\n }\n }\n}","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Export Page Content","type":"text"}]},{"type":"paragraph","content":[{"text":"By default, the content of the page is not indexed. To export the content of the page, you need to extend the default DataLoader class and add the logic below, which is responsible for exporting the page content and striping the html from it.","type":"text"}]},{"type":"orderedList","attrs":{"order":1},"content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Add the logic for exporting page content to your custom exporter class.","type":"text"}]}]}]},{"type":"codeBlock","content":[{"text":"using System.Collections.Generic;\nusing System.Globalization;\nusing Hawksearch.Export;\nusing Telerik.Sitefinity.Model;\nusing Telerik.Sitefinity.Pages.Model;\nusing Telerik.Sitefinity.Web.ResourceCombining;\n\nnamespace SitefinityWebApp.Search\n{\n public class CustomDataLoader : DataLoader\n {\n protected override IEnumerable GetFieldValue(IDataItem item, string fieldName, CultureInfo culture = null)\n {\n if (item.GetType() == typeof(PageNode) && fieldName == \"Page\")\n {\n var pnItem = (PageNode)item;\n\n InMemoryPageRender renderer = new InMemoryPageRender();\n var memPage = renderer.RenderPage(pnItem, false, true);\n var result = new List();\n var cleanHtml = this.StripHTML(memPage).Replace(\"\\n\", string.Empty).Trim();\n cleanHtml = cleanHtml.Replace(\"\\\"\", \"\\\"\\\"\");\n cleanHtml = \"\\\"\" + cleanHtml + \"\\\"\";\n\n result.Add(cleanHtml);\n\n return result;\n }\n\n if (item.GetType() == typeof(PageNode) && fieldName == \"Description\")\n {\n var pnItem = (PageNode)item;\n var pageData = pnItem.GetPageData();\n var result = new List();\n\n if (pageData != null)\n {\n var final = this.StripHTML(pageData.Description.ToString()).Replace(\"\\n\", string.Empty).Trim();\n final = final.Replace(\"\\\"\", \"\\\"\\\"\");\n\n if (!string.IsNullOrWhiteSpace(final))\n {\n result.Add(final);\n }\n }\n else\n {\n result.Add(string.Empty);\n }\n\n\n return result;\n }\n\n return base.GetFieldValue(item, fieldName, culture);\n }\n\n private string StripHTML(string source)\n {\n try\n {\n string result;\n\n // Remove HTML Development formatting\n // Replace line breaks with space\n // because browsers inserts space\n result = source.Replace(\"\\r\", \" \");\n // Replace line breaks with space\n // because browsers inserts space\n result = result.Replace(\"\\n\", \" \");\n // Remove step-formatting\n result = result.Replace(\"\\t\", string.Empty);\n // Remove repeating spaces because browsers ignore them\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"( )+\", \" \");\n\n // Remove the header (prepare first by clearing attributes)\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*head([^>])*>\", \"\",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"(<( )*(/)( )*head( )*>)\", \"\",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"().*()\", string.Empty,\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // remove all scripts (prepare first by clearing attributes)\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*script([^>])*>\", \"\",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n //result = System.Text.RegularExpressions.Regex.Replace(result,\n // @\"()])*()\",\n // string.Empty,\n // System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"()\", string.Empty,\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // remove all styles (prepare first by clearing attributes)\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*style([^>])*>\", \"\",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"()\", string.Empty,\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // insert tabs in spaces of tags\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*td([^>])*>\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // insert line breaks in places of
and

tags\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*br( )*>\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*li( )*>\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // insert line paragraphs (double line breaks) in place\n // if

and tags\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*div([^>])*>\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*tr([^>])*>\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<( )*p([^>])*>\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // Remove remaining tags like , links, images,\n // comments etc - anything that's enclosed inside < >\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<[^>]*>\", string.Empty,\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // replace special characters:\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\" \", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"•\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"‹\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"›\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"™\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"⁄\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"<\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\">\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"©\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"®\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n // Remove all others. More can be added, see\n // http://hotwired.lycos.com/webmonkey/reference/special_characters/\n result = System.Text.RegularExpressions.Regex.Replace(result,\n @\"&(.{2,6});\", string.Empty,\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // for testing\n //System.Text.RegularExpressions.Regex.Replace(result,\n // this.txtRegex.Text,string.Empty,\n // System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n\n // make line breaking consistent\n result = result.Replace(\"\\n\", \" \");\n\n // Remove extra line breaks and tabs:\n // replace over 2 breaks with 2 and over 4 tabs with 4.\n // Prepare first to remove any whitespaces in between\n // the escaped characters and remove redundant tabs in between line breaks\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"(\\r)( )+(\\r)\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"(\\t)( )+(\\t)\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"(\\t)( )+(\\r)\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"(\\r)( )+(\\t)\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n // Remove redundant tabs\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"(\\r)(\\t)+(\\r)\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n // Remove multiple tabs following a line break with just one tab\n result = System.Text.RegularExpressions.Regex.Replace(result,\n \"(\\r)(\\t)+\", \" \",\n System.Text.RegularExpressions.RegexOptions.IgnoreCase);\n // Initial replacement target string for line breaks\n string breaks = \"\\r\\r\";\n // Initial replacement target string for tabs\n string tabs = \"\\t\\t\\t\\t\\t\";\n for (int index = 0; index < result.Length; index++)\n {\n result = result.Replace(breaks, \" \");\n result = result.Replace(tabs, \" \");\n }\n\n // That's it.\n return result;\n }\n catch\n {\n return source;\n }\n }\n }\n}","type":"text"}]},{"type":"paragraph"}],"version":1}

Browser not supported