Create file_conversion.py

file_conversion.py

@@ -0,0 +1,46 @@
+from fastapi import APIRouter, UploadFile, File, HTTPException
+from fastapi.responses import FileResponse
+from pdf2docx import Converter
+import os
+import tempfile
+
+router = APIRouter()
+
+# Define the temp directory
+TEMP_DIR = "/.tempfiles"
+
+@router.post("/convert/pdf_to_docx")
+async def convert_pdf_to_docx(file: UploadFile = File(...)):
+    if not file.filename.endswith('.pdf'):
+        raise HTTPException(status_code=400, detail="File must be a PDF")
+
+    # Ensure the temp directory exists
+    os.makedirs(TEMP_DIR, exist_ok=True)
+
+    pdf_temp_path = os.path.join(TEMP_DIR, f"temp_{file.filename}")
+    docx_temp_path = pdf_temp_path.replace('.pdf', '.docx')
+
+    try:
+        # Save the uploaded file
+        with open(pdf_temp_path, "wb") as pdf_file:
+            pdf_file.write(await file.read())
+
+        # Convert PDF to DOCX
+        cv = Converter(pdf_temp_path)
+        cv.convert(docx_temp_path)
+        cv.close()
+
+        # Return the DOCX file
+        return FileResponse(
+            docx_temp_path,
+            media_type='application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+            filename=file.filename.replace('.pdf', '.docx')
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")
+    finally:
+        # Clean up temporary files
+        if os.path.exists(pdf_temp_path):
+            os.unlink(pdf_temp_path)
+        if os.path.exists(docx_temp_path):
+            os.unlink(docx_temp_path)