PDF データ抽出 .NET：完全開発者ガイド

Install-Package IronPDF

'INSTANT VB TODO TASK: The following line uses invalid syntax:
'Install-Package IronPDF

using IronPdf;
// Load any PDF document
var pdf = PdfDocument.FromFile("document.pdf");
// Extract all text with one line
string allText = pdf.ExtractAllText();
Console.WriteLine(allText);

Imports IronPdf

' Load any PDF document
Dim pdf = PdfDocument.FromFile("document.pdf")
' Extract all text with one line
Dim allText As String = pdf.ExtractAllText()
Console.WriteLine(allText)

using IronPdf;
using System;
using System.Text.RegularExpressions;
// Load any PDF document
var pdf = PdfDocument.FromFile("AnnualReport2024.pdf");
// Extract from selected pages
int[] pagesToExtract = { 0, 2, 4 }; // Pages 1, 3, and 5
foreach (var pageIndex in pagesToExtract)
{
    string pageText = pdf.ExtractTextFromPage(pageIndex);
    // Split on 2 or more spaces (tables often flatten into space-separated values)
    var tokens = Regex.Split(pageText, @"\s{2,}");
    foreach (string token in tokens)
    {
        // Match totals, invoice headers, and invoice rows
        if (token.Contains("Invoice") || token.Contains("Total") || token.StartsWith("INV-"))
        {
            Console.WriteLine($"Important: {token.Trim()}");
        }
    }
}

Imports IronPdf
Imports System
Imports System.Text.RegularExpressions

' Load any PDF document
Dim pdf = PdfDocument.FromFile("AnnualReport2024.pdf")
' Extract from selected pages
Dim pagesToExtract As Integer() = {0, 2, 4} ' Pages 1, 3, and 5
For Each pageIndex In pagesToExtract
    Dim pageText As String = pdf.ExtractTextFromPage(pageIndex)
    ' Split on 2 or more spaces (tables often flatten into space-separated values)
    Dim tokens = Regex.Split(pageText, "\s{2,}")
    For Each token As String In tokens
        ' Match totals, invoice headers, and invoice rows
        If token.Contains("Invoice") OrElse token.Contains("Total") OrElse token.StartsWith("INV-") Then
            Console.WriteLine($"Important: {token.Trim()}")
        End If
    Next
Next

using IronPdf;
using System;
using System.Text;
using System.Text.RegularExpressions;
var pdf = PdfDocument.FromFile("example.pdf");
string rawText = pdf.ExtractAllText();
// Split into lines for processing
string[] lines = rawText.Split('\n');
var csvBuilder = new StringBuilder();
foreach (string line in lines)
{
    if (string.IsNullOrWhiteSpace(line) || line.Contains("Page"))
        continue;
    string[] rawCells = Regex.Split(line.Trim(), @"\s+");
    string[] cells;
    // If the line starts with "Product", combine first two tokens as product name
    if (rawCells[0].StartsWith("Product") && rawCells.Length >= 5)
    {
        cells = new string[rawCells.Length - 1];
        cells[0] = rawCells[0] + " " + rawCells[1]; // Combine Product + letter
        Array.Copy(rawCells, 2, cells, 1, rawCells.Length - 2);
    }
    else
    {
        cells = rawCells;
    }
    // Keep header or table rows
    bool isTableOrHeader = cells.Length >= 2
                           && (cells[0].StartsWith("Item") || cells[0].StartsWith("Product")
                               || Regex.IsMatch(cells[0], @"^INV-\d+"));
    if (isTableOrHeader)
    {
        Console.WriteLine($"Row: {string.Join("|", cells)}");
        string csvRow = string.Join(",", cells).Trim();
        csvBuilder.AppendLine(csvRow);
    }
}
// Save as CSV for Excel import
File.WriteAllText("extracted_table.csv", csvBuilder.ToString());
Console.WriteLine("Table data exported to CSV");

Imports IronPdf
Imports System
Imports System.Text
Imports System.Text.RegularExpressions

Dim pdf = PdfDocument.FromFile("example.pdf")
Dim rawText As String = pdf.ExtractAllText()
' Split into lines for processing
Dim lines As String() = rawText.Split(ControlChars.Lf)
Dim csvBuilder As New StringBuilder()

For Each line As String In lines
    If String.IsNullOrWhiteSpace(line) OrElse line.Contains("Page") Then
        Continue For
    End If

    Dim rawCells As String() = Regex.Split(line.Trim(), "\s+")
    Dim cells As String()

    ' If the line starts with "Product", combine first two tokens as product name
    If rawCells(0).StartsWith("Product") AndAlso rawCells.Length >= 5 Then
        cells = New String(rawCells.Length - 2) {}
        cells(0) = rawCells(0) & " " & rawCells(1) ' Combine Product + letter
        Array.Copy(rawCells, 2, cells, 1, rawCells.Length - 2)
    Else
        cells = rawCells
    End If

    ' Keep header or table rows
    Dim isTableOrHeader As Boolean = cells.Length >= 2 AndAlso (cells(0).StartsWith("Item") OrElse cells(0).StartsWith("Product") OrElse Regex.IsMatch(cells(0), "^INV-\d+"))

    If isTableOrHeader Then
        Console.WriteLine($"Row: {String.Join("|", cells)}")
        Dim csvRow As String = String.Join(",", cells).Trim()
        csvBuilder.AppendLine(csvRow)
    End If
Next

' Save as CSV for Excel import
File.WriteAllText("extracted_table.csv", csvBuilder.ToString())
Console.WriteLine("Table data exported to CSV")

using IronPdf;
using System.Drawing;
using System.Linq;
var pdf = PdfDocument.FromFile("form_document.pdf");
// Extract form field data
var form = pdf.Form;
foreach (var field in form) // Removed '.Fields' as 'FormFieldCollection' is enumerable
{
    Console.WriteLine($"{field.Name}: {field.Value}");
    // Update form values if needed
    if (field.Name == "customer_name")
    {
        field.Value = "Updated Value";
    }
}
// Save modified form
pdf.SaveAs("updated_form.pdf");

Imports IronPdf
Imports System.Drawing
Imports System.Linq

Dim pdf = PdfDocument.FromFile("form_document.pdf")
' Extract form field data
Dim form = pdf.Form
For Each field In form ' Removed '.Fields' as 'FormFieldCollection' is enumerable
    Console.WriteLine($"{field.Name}: {field.Value}")
    ' Update form values if needed
    If field.Name = "customer_name" Then
        field.Value = "Updated Value"
    End If
Next
' Save modified form
pdf.SaveAs("updated_form.pdf")