วิธีสกัดข้อความจากไฟล์ ZIP/RAR ด้วย GroupDocs.Parser ใน .NET

dotnet add package GroupDocs.Parser

using GroupDocs.Parser;
using GroupDocs.Parser.Data;
using System.Collections.Generic;
using System.IO;

// Path to the archive you want to scan
string archivePath = "./SampleDocs/InvoicesArchive.zip";

using (Parser parser = new Parser(archivePath))
{
    // Retrieve every file (or nested archive) inside the container
    IEnumerable<ContainerItem> attachments = parser.GetContainer();

    if (attachments == null)
    {
        Console.WriteLine("Archive is empty or could not be read.");
        return;
    }

    // Hand off the collection to a helper that extracts text/metadata
    ExtractDataFromAttachments(attachments);
}

/// <summary>
/// Recursively extracts metadata and plain‑text from each item in an archive.
/// </summary>
static void ExtractDataFromAttachments(IEnumerable<ContainerItem> attachments)
{
    foreach (ContainerItem item in attachments)
    {
        // Print a quick line with file name and size (optional)
        Console.WriteLine($"File: {item.FilePath} | Size: {item.Metadata.Size} bytes");

        try
        {
            // Each ContainerItem can open its own Parser instance
            using (Parser itemParser = item.OpenParser())
            {
                if (itemParser == null)
                {
                    // The item is not a supported document – skip it
                    continue;
                }

                // Detect nested archives by extension (case‑insensitive)
                bool isArchive = item.FilePath.EndsWith(".zip", StringComparison.OrdinalIgnoreCase) ||
                                 item.FilePath.EndsWith(".rar", StringComparison.OrdinalIgnoreCase);

                if (isArchive)
                {
                    // Recursively process the inner archive
                    IEnumerable<ContainerItem>? nested = itemParser.GetContainer();
                    if (nested != null)
                    {
                        ExtractDataFromAttachments(nested);
                    }
                }
                else
                {
                    // Regular document – extract its raw text
                    using (TextReader reader = itemParser.GetText())
                    {
                        string text = reader.ReadToEnd();
                        Console.WriteLine($"Extracted {text.Length} characters from {item.FilePath}");
                        // Here you could store `text` in a database, index it, etc.
                    }
                }
            }
        }
        catch (UnsupportedDocumentFormatException)
        {
            // The file type is not supported by GroupDocs.Parser – ignore gracefully
            Console.WriteLine($"Skipping unsupported format: {item.FilePath}");
        }
    }
}

using GroupDocs.Parser;
using GroupDocs.Parser.Data;
using System;
using System.Collections.Generic;
using System.IO;

class ArchiveTextExtractor
{
    static void Main(string[] args)
    {
        string archivePath = args.Length > 0 ? args[0] : "./SampleDocs/InvoicesArchive.zip";
        using (Parser parser = new Parser(archivePath))
        {
            IEnumerable<ContainerItem> attachments = parser.GetContainer();
            if (attachments == null)
            {
                Console.WriteLine("No items found in the archive.");
                return;
            }
            ExtractDataFromAttachments(attachments);
        }
    }

    static void ExtractDataFromAttachments(IEnumerable<ContainerItem> attachments)
    {
        foreach (ContainerItem item in attachments)
        {
            Console.WriteLine($"File: {item.FilePath} | Size: {item.Metadata.Size} bytes");
            try
            {
                using (Parser itemParser = item.OpenParser())
                {
                    if (itemParser == null) continue;

                    bool isArchive = item.FilePath.EndsWith(".zip", StringComparison.OrdinalIgnoreCase) ||
                                     item.FilePath.EndsWith(".rar", StringComparison.OrdinalIgnoreCase);

                    if (isArchive)
                    {
                        var nested = itemParser.GetContainer();
                        if (nested != null) ExtractDataFromAttachments(nested);
                    }
                    else
                    {
                        using (TextReader reader = itemParser.GetText())
                        {
                            string text = reader.ReadToEnd();
                            Console.WriteLine($"Extracted {text.Length} chars from {item.FilePath}");
                        }
                    }
                }
            }
            catch (UnsupportedDocumentFormatException)
            {
                Console.WriteLine($"Unsupported format: {item.FilePath}");
            }
        }
    }
}

dotnet run -- ./Data/LegalDocs.zip