C# PDF 解析器：PDF編輯與文字擷取工具

using IronPdf;

// Parse PDF from URL
var pdfFromUrl = PdfDocument.FromUrl("https://example.com/document.pdf");
string urlPdfText = pdfFromUrl.ExtractAllText();

// Parse password-protected PDFs
var protectedPdf = PdfDocument.FromFile("protected.pdf", "password123");
string protectedText = protectedPdf.ExtractAllText();

// Extract text from specific page range
var largePdf = PdfDocument.FromFile("large-document.pdf");
for (int i = 5; i < 10; i++)
{
    string pageText = largePdf.ExtractTextFromPage(i);
    Console.WriteLine($"Page {i + 1}: {pageText.Substring(0, 100)}...");
}

Imports IronPdf

' Parse PDF from URL
Dim pdfFromUrl = PdfDocument.FromUrl("https://example.com/document.pdf")
Dim urlPdfText As String = pdfFromUrl.ExtractAllText()

' Parse password-protected PDFs
Dim protectedPdf = PdfDocument.FromFile("protected.pdf", "password123")
Dim protectedText As String = protectedPdf.ExtractAllText()

' Extract text from specific page range
Dim largePdf = PdfDocument.FromFile("large-document.pdf")
For i As Integer = 5 To 9
    Dim pageText As String = largePdf.ExtractTextFromPage(i)
    Console.WriteLine($"Page {i + 1}: {pageText.Substring(0, 100)}...")
Next

using IronPdf;
using System.Text.RegularExpressions;

// Parse scanned PDFs with OCR (requires IronOcr)
var scannedPdf = PdfDocument.FromFile("scanned-document.pdf");
string ocrText = scannedPdf.ExtractAllText();

// Parse PDFs with forms
var formPdf = PdfDocument.FromFile("form.pdf");
string formText = formPdf.ExtractAllText();

// Extract and filter specific content
string invoiceText = pdf.ExtractAllText();
var invoiceNumber = Regex.Match(invoiceText, @"Invoice #: (\d+)").Groups[1].Value;
var totalAmount = Regex.Match(invoiceText, @"Total: \$([0-9,]+\.\d{2})").Groups[1].Value;

Imports IronPdf
Imports System.Text.RegularExpressions

' Parse scanned PDFs with OCR (requires IronOcr)
Dim scannedPdf = PdfDocument.FromFile("scanned-document.pdf")
Dim ocrText As String = scannedPdf.ExtractAllText()

' Parse PDFs with forms
Dim formPdf = PdfDocument.FromFile("form.pdf")
Dim formText As String = formPdf.ExtractAllText()

' Extract and filter specific content
Dim invoiceText As String = pdf.ExtractAllText()
Dim invoiceNumber = Regex.Match(invoiceText, "Invoice #: (\d+)").Groups(1).Value
Dim totalAmount = Regex.Match(invoiceText, "Total: \$([0-9,]+\.\d{2})").Groups(1).Value

// ASP.NET Core example
public IActionResult ParseUploadedPdf(IFormFile pdfFile)
{
    using var stream = pdfFile.OpenReadStream();
    var pdf = PdfDocument.FromStream(stream);

    var extractedText = pdf.ExtractAllText();

    // Process or store the extracted text
    return Json(new { 
        success = true, 
        textLength = extractedText.Length,
        preview = extractedText.Substring(0, Math.Min(500, extractedText.Length))
    });
}

// Console application example
static void BatchParsePdfs(string folderPath)
{
    var pdfFiles = Directory.GetFiles(folderPath, "*.pdf");

    foreach (var file in pdfFiles)
    {
        var pdf = PdfDocument.FromFile(file);
        var text = pdf.ExtractAllText();

        // Save extracted text
        var textFile = Path.ChangeExtension(file, ".txt");
        File.WriteAllText(textFile, text);

        Console.WriteLine($"Parsed: {Path.GetFileName(file)} - {text.Length} characters");
    }
}

Imports Microsoft.AspNetCore.Mvc
Imports System.IO

' ASP.NET Core example
Public Function ParseUploadedPdf(pdfFile As IFormFile) As IActionResult
    Using stream = pdfFile.OpenReadStream()
        Dim pdf = PdfDocument.FromStream(stream)

        Dim extractedText = pdf.ExtractAllText()

        ' Process or store the extracted text
        Return Json(New With {
            .success = True,
            .textLength = extractedText.Length,
            .preview = extractedText.Substring(0, Math.Min(500, extractedText.Length))
        })
    End Using
End Function

' Console application example
Private Shared Sub BatchParsePdfs(folderPath As String)
    Dim pdfFiles = Directory.GetFiles(folderPath, "*.pdf")

    For Each file In pdfFiles
        Dim pdf = PdfDocument.FromFile(file)
        Dim text = pdf.ExtractAllText()

        ' Save extracted text
        Dim textFile = Path.ChangeExtension(file, ".txt")
        File.WriteAllText(textFile, text)

        Console.WriteLine($"Parsed: {Path.GetFileName(file)} - {text.Length} characters")
    Next
End Sub