XHTML Web Scraper to generate xml and bind to search box using Asp.Net 4.5.1 and C# and Telerik Ajax

I need a site scraping admin form that will enable the indexing of site form information and files. The resource needs to create an XML file stored in App_Data that is bound to Telerik search box. The search box located on a master page or form or user control to implement multi part word contains search terms. Eg the big house can be found with ‘th ig se’. The admin configuration panel should configure to a domain and list site folders using a checkbox so folders can be selected for indexing. Existing code is supplied and the HTML agility pack is also available for reference that uses regular expressions and excludes common words. The search results page should list like Google with a hyperlinked Title, URL and Description sorted by date descending. Results display in the parent page in the content section of the page. This includes PDF files.