static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample1.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
// Create new stream. You can use MemoryStream or any other System.IO.Stream inheritor.
FileStream stream = new FileStream(@".\page" + i + ".txt", FileMode.Create);
// Save text from page to the file stream
extractor.SavePageTextToStream(i, stream);
// Close stream
stream.Dispose();
}
// Cleanup
extractor.Dispose();
// Open first output file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\page1.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
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";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
// Get dimensions of the first document page
RectangleF rectangle = extractor.GetPageRectangle(0);
// Get text from the 1/3 of the page
rectangle.Width = rectangle.Width / 3f;
Response.Clear();
Response.ContentType = "text/html";
extractor.SetExtractionArea(rectangle);
Response.Write("<pre>");
// Save extracted text to output stream
extractor.SavePageTextToStream(0, Response.OutputStream);
Response.Write("</pre>");
Response.End();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample1.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
string outputText = "";
for (int i = 0; i < pageCount; i++)
{
// create new file stream
FileStream fStream = new FileStream("page" + i.ToString() + ".txt", FileMode.Create);
// save text from page #i to the file stream
extractor.SavePageTextToStream(i, fStream);
// close stream
fStream.Close();
}
// Open first output file in default associated application
System.Diagnostics.Process.Start("page1.txt");
}
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";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
// read width of the very first page (zero index)
float pageWidth = extractor.GetPageRect_Width(0);
float pageHeight = extractor.GetPageRect_Height(0);
// now we are extracting content assuming we have 3 columns
// equally distributed on pages
// first calculate the width of the one column by dividing page width by number of columns (3)
float columnWidth = pageWidth / 3f;
Response.Clear();
Response.ContentType = "text/html";
// iterate through 3 columns
for (int i = 0; i < 3; i++)
{
// set the extraction area to the #i column
extractor.SetExtractionArea(i * columnWidth, 0, columnWidth, pageHeight);
// Save extracted text to output stream
extractor.SavePageTextToStream(0, Response.OutputStream);
}
Response.End();
}
