René's URL Explorer Experiment

{
  "@context": "http://schema.org",
  "@type": "Article",
  "headline": "Python MarkItDown: Convert Documents Into LLM-Ready Markdown",
  "image": {
    "@type": "ImageObject",
    "url": "https://files.realpython.com/media/MarkItDown-Convert-Anything-to-Markdown-to-Feed-to-Your-LLM_Watermarked.201792042d8c.jpg",
    "width": 1920,
    "height": 1080
  },
  "mainEntityOfPage": {
    "@type": "WebPage",
    "@id": "https://realpython.com/python-markitdown/",
    "lastReviewed": "2026-10-15",
    "author": {
      "@type": "Person",
      "name": "Leodanis Pozo Ramos",
      "image": "https://realpython.com/cdn-cgi/image/width=862,height=862,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/Perfil_final1.9f896bc212f6.jpg",
      "url": "https://realpython.com/team/lpozoramos/",
      "affiliation": {
        "@type": "Organization",
        "@id": "https://realpython.com/#organization",
        "name": "Real Python",
        "url": "https://realpython.com",
        "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
      }
    },
    "reviewedBy": [
      {
        "@type": "Person",
        "name": "Aldren Santos",
        "image": "https://realpython.com/cdn-cgi/image/width=500,height=500,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/Aldren_Santos_Real_Python.6b0861d8b841.png",
        "url": "https://realpython.com/team/asantos/",
        "affiliation": {
          "@type": "Organization",
          "@id": "https://realpython.com/#organization",
          "name": "Real Python",
          "url": "https://realpython.com",
          "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
        }
      },
      {
        "@type": "Person",
        "name": "Brenda Weleschuk",
        "image": "https://realpython.com/cdn-cgi/image/width=320,height=320,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/IMG_3324_1.50b309355fc1.jpg",
        "url": "https://realpython.com/team/bweleschuk/",
        "affiliation": {
          "@type": "Organization",
          "@id": "https://realpython.com/#organization",
          "name": "Real Python",
          "url": "https://realpython.com",
          "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
        }
      },
      {
        "@type": "Person",
        "name": "Bartosz Zaczy\u0144ski",
        "image": "https://realpython.com/cdn-cgi/image/width=1694,height=1694,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/coders_lab_2109368.259b1599fbee.jpg",
        "url": "https://realpython.com/team/bzaczynski/",
        "affiliation": {
          "@type": "Organization",
          "@id": "https://realpython.com/#organization",
          "name": "Real Python",
          "url": "https://realpython.com",
          "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
        }
      },
      {
        "@type": "Person",
        "name": "Martin Breuss",
        "image": "https://realpython.com/cdn-cgi/image/width=456,height=456,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/martin_breuss_python_square.efb2b07faf9f.jpg",
        "url": "https://realpython.com/team/mbreuss/",
        "affiliation": {
          "@type": "Organization",
          "@id": "https://realpython.com/#organization",
          "name": "Real Python",
          "url": "https://realpython.com",
          "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
        }
      },
      {
        "@type": "Person",
        "name": "Philipp Acsany",
        "image": "https://realpython.com/cdn-cgi/image/width=1920,height=1920,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/pacsany.19bcf16f5a00.jpg",
        "url": "https://realpython.com/team/pacsany/",
        "affiliation": {
          "@type": "Organization",
          "@id": "https://realpython.com/#organization",
          "name": "Real Python",
          "url": "https://realpython.com",
          "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
        }
      }
    ]
  },
  "datePublished": "2025-11-05T14:00:00+00:00",
  "dateModified": "2026-10-15T19:56:13.221765+00:00",
  "publisher": {
    "@type": "Organization",
    "@id": "https://realpython.com/#organization",
    "name": "Real Python",
    "url": "https://realpython.com",
    "logo": {
      "@type": "ImageObject",
      "url": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png",
      "width": 512,
      "height": 512
    },
    "description": "Real Python is a leading provider of online Python education and one of the largest language-specific online communities for software developers. It publishes high-quality learning resources, such as tutorials, books, and courses to an audience of millions of developers, data scientists, and machine learning engineers each month.",
    "slogan": "Become a Python Expert",
    "email": "info@realpython.com",
    "sameAs": [
      "https://github.com/realpython",
      "https://www.youtube.com/realpython",
      "https://twitter.com/realpython",
      "https://x.com/realpython",
      "https://www.linkedin.com/company/realpython-com/",
      "https://www.facebook.com/learnrealpython",
      "https://www.instagram.com/realpython",
      "https://www.tiktok.com/@realpython.com"
    ]
  },
  "author": {
    "@type": "Person",
    "name": "Leodanis Pozo Ramos",
    "image": "https://realpython.com/cdn-cgi/image/width=862,height=862,fit=crop,gravity=auto,format=auto/https://files.realpython.com/media/Perfil_final1.9f896bc212f6.jpg",
    "url": "https://realpython.com/team/lpozoramos/",
    "affiliation": {
      "@type": "Organization",
      "@id": "https://realpython.com/#organization",
      "name": "Real Python",
      "url": "https://realpython.com",
      "logo": "https://realpython.com/static/real-python-logo-square-512.157ae6bf64ed.png"
    }
  },
  "description": "Get started with Python MarkItDown to turn PDFs, Office files, images, and URLs into clean, LLM-ready Markdown in seconds.",
  "hasPart": {
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "When should you pick MarkItDown over Pandoc?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "\u003cp\u003eChoose MarkItDown when you need fast, LLM-ready Markdown from multiple input formats and prioritize structure over fidelity. Use Pandoc when you need precise formatting control or a wider range of output formats.\u003c/p\u003e"
        }
      },
      {
        "@type": "Question",
        "name": "How do you install MarkItDown with optional features?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "\u003cp\u003eYou run \u003ccode\u003epython -m pip install 'markitdown[all]'\u003c/code\u003e to include all optional features. When you only need specific format handlers, you can install a subset like \u003ccode\u003e'markitdown[pdf,pptx,docx]'\u003c/code\u003e.\u003c/p\u003e"
        }
      },
      {
        "@type": "Question",
        "name": "How do you convert a file from the CLI and save the result?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "\u003cp\u003eYou run \u003ccode\u003emarkitdown \u0026lt;path\u0026gt;\u003c/code\u003e to print Markdown, and add \u003ccode\u003e-o \u0026lt;output_file.md\u0026gt;\u003c/code\u003e to write the output to your disk. You can also pipe input or use input redirection to feed data to \u003ccode\u003emarkitdown\u003c/code\u003e.\u003c/p\u003e"
        }
      },
      {
        "@type": "Question",
        "name": "How do you convert documents from Python code?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "\u003cp\u003eTo convert documents from Python code, you create a \u003ccode\u003eMarkItDown\u003c/code\u003e instance and call its \u003ccode\u003e.convert()\u003c/code\u003e method with a path or URL. Then, you access the \u003ccode\u003e.markdown\u003c/code\u003e attribute for the conversion result.\u003c/p\u003e"
        }
      },
      {
        "@type": "Question",
        "name": "Can you integrate MarkItDown with LLMs for images and OCR?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "\u003cp\u003eYes, you can use Azure Document Intelligence to perform OCR on image formats such as PDF, JPEG, PNG, BMP, and TIFF. Alternatively, you can use a custom prompt and an OCR-capable LLM.\u003c/p\u003e"
        }
      }
    ]
  }
}