feat: initial commit — markitdown converter

2026-05-28 11:53:52 +00:00
commit 8b0e93bf69
5 changed files with 707 additions and 0 deletions
@@ -0,0 +1,70 @@
+from fastapi import FastAPI, UploadFile, File, Request
+from fastapi.responses import HTMLResponse, JSONResponse, PlainTextResponse
+from fastapi.templating import Jinja2Templates
+from fastapi.staticfiles import StaticFiles
+from markitdown import MarkItDown
+from markitdown._stream_info import StreamInfo
+import io, os, mimetypes
+
+app = FastAPI(title="MarkItDown Converter")
+templates = Jinja2Templates(directory="templates")
+
+# markitdown supports: PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML,
+# images (with OCR via LLM), audio, ZIP, EPUB, YouTube URLs, Wikipedia, etc.
+ALLOWED_EXTENSIONS = {
+    ".pdf", ".docx", ".doc", ".pptx", ".ppt", ".xlsx", ".xls",
+    ".html", ".htm", ".csv", ".json", ".xml", ".epub",
+    ".txt", ".md", ".rst", ".zip", ".msg",
+    ".png", ".jpg", ".jpeg", ".gif", ".webp", ".bmp",
+    ".mp3", ".wav", ".m4a",
+}
+
+MAX_SIZE_MB = 50
+
+
+@app.get("/", response_class=HTMLResponse)
+async def index(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+
+@app.post("/convert")
+async def convert(file: UploadFile = File(...)):
+    # Validate extension
+    _, ext = os.path.splitext(file.filename or "")
+    ext = ext.lower()
+    if ext not in ALLOWED_EXTENSIONS:
+        return JSONResponse(
+            {"error": f"Unsupported file type: '{ext}'. Supported: {', '.join(sorted(ALLOWED_EXTENSIONS))}"},
+            status_code=400
+        )
+
+    # Read into memory
+    data = await file.read()
+    size_mb = len(data) / (1024 * 1024)
+    if size_mb > MAX_SIZE_MB:
+        return JSONResponse(
+            {"error": f"File too large ({size_mb:.1f} MB). Max: {MAX_SIZE_MB} MB"},
+            status_code=413
+        )
+
+    try:
+        md = MarkItDown()
+        stream = io.BytesIO(data)
+        mime = mimetypes.types_map.get(ext, "application/octet-stream")
+        result = md.convert_stream(
+            stream,
+            stream_info=StreamInfo(
+                mimetype=mime,
+                extension=ext,
+                filename=file.filename,
+            )
+        )
+        markdown_text = result.text_content or ""
+        return JSONResponse({
+            "markdown": markdown_text,
+            "filename": file.filename,
+            "size_kb": round(len(data) / 1024, 1),
+            "chars": len(markdown_text),
+        })
+    except Exception as e:
+        return JSONResponse({"error": f"Conversion failed: {str(e)}"}, status_code=500)