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(@".\bin\sample2.pdf");
// Create Bytescout.PDF2HTML.HTMLExtractor instance
HTMLExtractor extractor = new HTMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Set HTML with CSS extraction mode
extractor.ExtractionMode = HTMLExtractionMode.HTMLWithCSS;
// Embed images into HTML file
extractor.SaveImages = ImageHandling.Embed;
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
Response.Clear();
Response.ContentType = "text/html";
// Save extracted text to output stream
extractor.SaveHtmlToStream(Response.OutputStream);
Response.End();
extractor.Dispose();
}
static void Main(string[] args)
{
// Create Bytescout.PDF2HTML.HTMLExtractor instance
HTMLExtractor extractor = new HTMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Set plain HTML extraction mode
extractor.ExtractionMode = HTMLExtractionMode.PlainHTML;
// Load sample PDF document
extractor.LoadDocumentFromFile("sample2.pdf");
// Convert 2-nd page to HTML and save it to file
extractor.SaveHtmlPageToFile(1, "output.html");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.html");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDF2HTML.HTMLExtractor instance
HTMLExtractor extractor = new HTMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Set HTML with CSS extraction mode
extractor.ExtractionMode = HTMLExtractionMode.HTMLWithCSS;
// Input file Url
var inputUrl = @"https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf";
// Get Input Stream
var inpStream = GetStreamFromUrl(inputUrl);
// Load sample PDF document
extractor.LoadDocumentFromStream(inpStream);
// Convert 1-st page to HTML and save it to file
extractor.SaveHtmlPageToFile(0, "output.html");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.html");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
protected void Page_Load(object sender, EventArgs e)
{
// This test PDF file is automatically copied to the output build directory.
String inputFile = Server.MapPath("bin\\sample2.pdf");
// Prepare output file path
String outputFolder = Server.MapPath("~/output/");
String outputFile = Path.Combine(outputFolder, "result.html");
// Create Bytescout.PDF2HTML.HTMLExtractor instance
HTMLExtractor extractor = new HTMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Set HTML with CSS extraction mode
extractor.ExtractionMode = HTMLExtractionMode.HTMLWithCSS;
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
// Save extracted text to output file. Document images will be created in a subfolder.
extractor.SaveHtmlToFile(outputFile);
// The converter knows nothing about server's home directory, so it places images to a subfolder
// named "<filename>.images" near to the output file and generates image paths relative to the output folder.
// We need to change those paths relative to server home directory.
string[] lines = File.ReadAllLines(outputFile);
StringBuilder builder = new StringBuilder();
foreach (string line in lines)
{
// replace image source paths
builder.AppendLine(line.Replace("sample2.pdf.images", "output/sample2.pdf.images"));
}
// Write the modified content to Response:
Response.Clear();
Response.ContentType = "text/html";
Response.Write(builder.ToString());
Response.End();
extractor.Dispose();
}
