protected void Page_Load(object sender, EventArgs e)
{
// This test file will be copied to the project directory on the pre-build event (see the project properties).
String inputFile = Server.MapPath("columns.pdf");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// set to extract text column by column
extractor.ExtractColumnByColumn = true;
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
Response.Clear();
Response.ContentType = "text/html";
// Save extracted text to output stream
extractor.SaveTextToStream(Response.OutputStream);
Response.End();
}
/*
* IF YOU SEE TEMPORARY FOLDER ACCESS ERRORS:
*
* Temporary folder access is required for web application when you use ByteScout SDK in it.
* If you are getting errors related to the access to temporary folder like "Access to the path 'C:\Windows\TEMP\... is denied" then you need to add permission for this temporary folder to make ByteScout SDK working on that machine and IIS configuration because ByteScout SDK requires access to temp folder to cache some of its data for more efficient work.
*
* SOLUTION:
*
* If your IIS Application Pool has "Load User Profile" option enabled the IIS provides access to user's temp folder. Check user's temporary folder
*
* If you are running Web Application under an impersonated account or IIS_IUSRS group, IIS may redirect all requests into separate temp folder like "c:\temp\".
*
* In this case
* - check the User or User Group your web application is running under
* - then add permissions for this User or User Group to read and write into that temp folder (c:\temp or c:\windows\temp\ folder)
* - restart your web application and try again
*
*/
protected void Page_Load(object sender, EventArgs e)
{
String inputFile = Server.MapPath(@".\bin\sample1.pdf");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
Response.Clear();
Response.ContentType = "text/html";
Response.Write("<pre>");
// Write extracted text to output stream
extractor.SaveTextToStream(Response.OutputStream);
Response.Write("</pre>");
Response.End();
}
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();
}
protected void Page_Load(object sender, EventArgs e)
{
// Directory containing test files
String inputFolder = Server.MapPath(@".\bin");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
Response.Clear();
Response.ContentType = "text/html";
// Get PDF files
string[] pdfFiles = Directory.GetFiles(inputFolder, "*.pdf");
foreach (string file in pdfFiles)
{
// Load document
extractor.LoadDocumentFromFile(file);
// Save extracted text to output stream
extractor.SaveTextToStream(Response.OutputStream);
// Reset the extractor before load another file
extractor.Reset();
}
Response.End();
}
