วิธีการสกัดเนื้อหาเพื่อค้นหาและ indexing โดยใช้ Aspose.Words

using System;
using Aspose.Words;

class Program
{
    static void Main()
    {
        // Load the Word document
        string filePath = "DocumentToIndex.docx";
        Document doc = new Document(filePath);

        Console.WriteLine("Document loaded successfully.");
    }
}

using System;
using Aspose.Words;

class Program
{
    static void Main()
    {
        Document doc = new Document("DocumentToIndex.docx");

        // Extract text from the document
        string text = doc.GetText();
        Console.WriteLine("Extracted Text:");
        Console.WriteLine(text);
    }
}

using System;
using Aspose.Words;

class Program
{
    static void Main()
    {
        Document doc = new Document("DocumentToIndex.docx");

        // Extract headings
        foreach (Paragraph para in doc.GetChildNodes(NodeType.Paragraph, true))
        {
            if (para.ParagraphFormat.StyleIdentifier == StyleIdentifier.Heading1 ||
                para.ParagraphFormat.StyleIdentifier == StyleIdentifier.Heading2)
            {
                Console.WriteLine($"Heading: {para.GetText().Trim()}");
            }
        }

        // Extract metadata
        Console.WriteLine("Title: " + doc.BuiltInDocumentProperties.Title);
        Console.WriteLine("Author: " + doc.BuiltInDocumentProperties.Author);
    }
}

using System;
using Aspose.Words;

class Program
{
    static void Main()
    {
        Document doc = new Document("DocumentToIndex.docx");

        // Extract tables from the document
        foreach (Table table in doc.GetChildNodes(NodeType.Table, true))
        {
            foreach (Row row in table.Rows)
            {
                foreach (Cell cell in row.Cells)
                {
                    Console.Write(cell.GetText().Trim() + "\t");
                }
                Console.WriteLine();
            }
        }
    }
}