feat(skills): add markitdown document converter and regensburg-stadtrat civic intelligence skills

2026-09-12 09:15:16 +02:00
parent e2944efb3e
commit 71e8909251
5 changed files with 767 additions and 0 deletions
@@ -0,0 +1,138 @@
+#!/usr/bin/env python3
+# /// script
+# dependencies = [
+#   "markitdown[all]>=0.0.1a4",
+#   "requests>=2.31.0",
+# ]
+# ///
+"""
+Universal Document to Markdown Converter
+Powered by Microsoft MarkItDown.
+
+Supports PDF, DOCX, XLSX, PPTX, HTML, CSV, TXT, JSON, XML, images, and audio.
+Can take a local file path, a remote URL, or stdin.
+"""
+
+import argparse
+import os
+import shutil
+import subprocess
+import sys
+import tempfile
+import urllib.parse
+
+def ensure_dependencies_and_run():
+    """If markitdown is not installed in the current Python env, re-exec via uv run if available."""
+    try:
+        import markitdown  # noqa: F401
+        import requests    # noqa: F401
+    except ImportError:
+        uv_path = shutil.which("uv")
+        if uv_path and os.environ.get("_MARKITDOWN_REEXEC") != "1":
+            env = os.environ.copy()
+            env["_MARKITDOWN_REEXEC"] = "1"
+            cmd = [uv_path, "run", os.path.abspath(__file__), *sys.argv[1:]]
+            try:
+                res = subprocess.run(cmd, env=env)
+                sys.exit(res.returncode)
+            except Exception as e:
+                sys.stderr.write(f"Failed to re-execute via uv: {e}\n")
+        sys.stderr.write("Error: 'markitdown[all]' or 'requests' not found. Please install with:\n")
+        sys.stderr.write("  uv pip install 'markitdown[all]' requests\n")
+        sys.exit(1)
+
+ensure_dependencies_and_run()
+
+from markitdown import MarkItDown
+import requests
+
+def download_url(url: str, output_dir: str) -> str:
+    """Download a remote URL to a temporary local file, guessing the filename from URL or headers."""
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+    }
+    resp = requests.get(url, headers=headers, stream=True, timeout=60)
+    resp.raise_for_status()
+
+    # Determine filename
+    parsed = urllib.parse.urlparse(url)
+    basename = os.path.basename(parsed.path) or "downloaded_file"
+    if not os.path.splitext(basename)[1]:
+        ct = resp.headers.get("Content-Type", "")
+        if "pdf" in ct:
+            basename += ".pdf"
+        elif "word" in ct or "docx" in ct:
+            basename += ".docx"
+        elif "sheet" in ct or "excel" in ct or "xlsx" in ct:
+            basename += ".xlsx"
+        elif "html" in ct:
+            basename += ".html"
+
+    local_path = os.path.join(output_dir, basename)
+    with open(local_path, "wb") as f:
+        for chunk in resp.iter_content(chunk_size=65536):
+            if chunk:
+                f.write(chunk)
+    return local_path
+
+def convert_file(path: str) -> str:
+    """Convert local file to Markdown text using MarkItDown."""
+    md = MarkItDown()
+    result = md.convert(path)
+    return result.text_content
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Convert documents (PDF, Office, HTML, images) to Markdown via Microsoft MarkItDown"
+    )
+    parser.add_argument("file", nargs="?", help="Local path to the document file")
+    parser.add_argument("--url", "-u", help="Remote URL of the document to download and convert")
+    parser.add_argument("--output", "-o", help="Optional output file path (defaults to stdout)")
+    parser.add_argument("--frontmatter", action="store_true", help="Add YAML frontmatter with file metadata")
+
+    args = parser.parse_args()
+
+    if not args.file and not args.url:
+        parser.print_help()
+        sys.exit(1)
+
+    temp_dir = None
+    target_file = args.file
+
+    try:
+        if args.url:
+            temp_dir = tempfile.mkdtemp(prefix="markitdown_")
+            target_file = download_url(args.url, temp_dir)
+
+        if not target_file or not os.path.exists(target_file):
+            sys.stderr.write(f"Error: File not found: {target_file}\n")
+            sys.exit(1)
+
+        content = convert_file(target_file)
+
+        if args.frontmatter:
+            meta = [
+                "---",
+                f"source_file: {os.path.basename(target_file)}",
+                f"original_url: {args.url or ''}",
+                f"size_bytes: {os.path.getsize(target_file)}",
+                "converted_by: microsoft-markitdown",
+                "---",
+                "",
+            ]
+            content = "\n".join(meta) + content
+
+        if args.output:
+            os.makedirs(os.path.dirname(os.path.abspath(args.output)), exist_ok=True)
+            with open(args.output, "w", encoding="utf-8") as f:
+                f.write(content)
+            print(f"Successfully converted to {args.output}")
+        else:
+            print(content)
+
+    finally:
+        if temp_dir and os.path.exists(temp_dir):
+            shutil.rmtree(temp_dir, ignore_errors=True)
+
+if __name__ == "__main__":
+    main()