Extract Markdown

using MuPDF.NET;
using PDF4LLM;

string mdText = PdfExtractor.ToMarkdown("document.pdf");

// Extract pages 1, 2, and 3 (zero-based: 0, 1, 2)
string mdText = PdfExtractor.ToMarkdown(
    "document.pdf",
    pages: new List<int> { 0, 1, 2 }
);

// Extract every other page
Document doc         = new Document("document.pdf");
var      everyOther  = Enumerable.Range(0, doc.PageCount)
                                 .Where(i => i % 2 == 0)
                                 .ToList();

string mdText = PdfExtractor.ToMarkdown(doc, pages: everyOther);
doc.Close();

var reader = PdfExtractor.LlamaMarkdownReader();
var chunks = reader.LoadData("document.pdf");

foreach (var chunk in chunks)
{
    int    page = (int)chunk.ExtraInfo["page"];
    string text = chunk.Text;

    Console.WriteLine($"Page {page}");
    Console.WriteLine(text);
}

ParsedDocument parsed = PdfExtractor.ParseDocument("document.pdf");

foreach (ParsedPage page in parsed.Pages)
{
    // Exclude blocks in the top and bottom 60pt margin bands
    var bodyBlocks = page.Blocks
        .Where(b => b.BoundingBox.Y0 > 60 && b.BoundingBox.Y1 < (page.Height - 60))
        .ToList();

    // Render body blocks only
}

string mdText = PdfExtractor.ToMarkdown(
    "document.pdf",
    writeImages:  true,
    imagePath:    "assets/images/",
    imageFormat:  "png"
);

![image](assets/images/document.pdf-0-1.png)

| Column A | Column B | Column C |
|----------|----------|----------|
| Value 1  | Value 2  | Value 3  |

using MuPDF.NET;
using PDF4LLM;
using System.IO;

// Ensure image output directory exists
Directory.CreateDirectory("assets/");

// Extract the first five pages with images
string mdText = PdfExtractor.ToMarkdown(
    "report.pdf",
    pages:       new List<int> { 0, 1, 2, 3, 4 },   // first five pages only
    writeImages: true,                                  // extract images to disk
    imagePath:   "assets/",                             // image output directory
    imageFormat: "png"                                  // image format
);

// Save the full output as a single Markdown file
File.WriteAllText("output/report.md", mdText, System.Text.Encoding.UTF8);

var reader = PdfExtractor.LlamaMarkdownReader();
var chunks = reader.LoadData("report.pdf");

Directory.CreateDirectory("output");

foreach (var chunk in chunks)
{
    int    pageNum  = (int)chunk.ExtraInfo["page"];
    string filePath = $"output/page-{pageNum}.md";

    File.WriteAllText(filePath, chunk.Text, System.Text.Encoding.UTF8);
}