Default.aspx.cs
using System; using Bytescout.PDFExtractor; namespace ExtractTextByColumns { public partial class _Default : System.Web.UI.Page { protected void Page_Load(object sender, EventArgs e) { String inputFile = Server.MapPath(@".\bin\columns.pdf"); // Create Bytescout.PDFExtractor.TextExtractor instance TextExtractor extractor = new TextExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Extract text by columns (useful if PDF document is designed in column layout like a newspaper) extractor.ExtractColumnByColumn = true; // Load sample PDF document extractor.LoadDocumentFromFile(inputFile); Response.Clear(); Response.ContentType = "text/html"; Response.Write("<pre>"); // Save extracted text to output stream extractor.SaveTextToStream(Response.OutputStream); Response.Write("</pre>"); Response.End(); } } }
Web.config
<?xml version="1.0"?> <configuration> <appSettings/> <connectionStrings/> <system.web> <!-- Set compilation debug="true" to insert debugging symbols into the compiled page. Because this affects performance, set this value to true only during development. --> <compilation debug="true" /> <!-- The <authentication> section enables configuration of the security authentication mode used by ASP.NET to identify an incoming user. --> <authentication mode="Windows" /> <!-- The <customErrors> section enables configuration of what to do if/when an unhandled error occurs during the execution of a request. Specifically, it enables developers to configure html error pages to be displayed in place of a error stack trace. <customErrors mode="RemoteOnly" defaultRedirect="GenericErrorPage.htm"> <error statusCode="403" redirect="NoAccess.htm" /> <error statusCode="404" redirect="FileNotFound.htm" /> </customErrors> --> </system.web> </configuration>
Click here to get your Free Trial version of the SDK
also available as: