Spaces:
Paused
Paused
Update file_conversion.py
Browse files- file_conversion.py +0 -14
file_conversion.py
CHANGED
|
@@ -17,50 +17,36 @@ TEMP_DIR = "/.tempfiles"
|
|
| 17 |
def remove_file(path: str):
|
| 18 |
if os.path.exists(path):
|
| 19 |
os.unlink(path)
|
| 20 |
-
logger.info(f"Removed temporary file: {path}")
|
| 21 |
|
| 22 |
@router.post("/convert/pdf_to_docx")
|
| 23 |
async def convert_pdf_to_docx(background_tasks: BackgroundTasks, file: UploadFile = File(...)):
|
| 24 |
if not file.filename.endswith('.pdf'):
|
| 25 |
raise HTTPException(status_code=400, detail="File must be a PDF")
|
| 26 |
|
| 27 |
-
# Ensure the temp directory exists
|
| 28 |
os.makedirs(TEMP_DIR, exist_ok=True)
|
| 29 |
-
|
| 30 |
pdf_temp_path = os.path.join(TEMP_DIR, f"temp_{file.filename}")
|
| 31 |
docx_temp_path = pdf_temp_path.replace('.pdf', '.docx')
|
| 32 |
|
| 33 |
try:
|
| 34 |
-
# Save the uploaded file
|
| 35 |
with open(pdf_temp_path, "wb") as pdf_file:
|
| 36 |
shutil.copyfileobj(file.file, pdf_file)
|
| 37 |
-
|
| 38 |
-
logger.info(f"Starting conversion of {pdf_temp_path}")
|
| 39 |
|
| 40 |
-
# Convert PDF to DOCX
|
| 41 |
cv = Converter(pdf_temp_path)
|
| 42 |
cv.convert(docx_temp_path)
|
| 43 |
cv.close()
|
| 44 |
|
| 45 |
-
logger.info(f"Conversion completed. Output file: {docx_temp_path}")
|
| 46 |
-
|
| 47 |
-
# Check if the file exists
|
| 48 |
if not os.path.exists(docx_temp_path):
|
| 49 |
raise FileNotFoundError(f"Converted file not found: {docx_temp_path}")
|
| 50 |
|
| 51 |
-
# Schedule file removal after response is sent
|
| 52 |
background_tasks.add_task(remove_file, pdf_temp_path)
|
| 53 |
background_tasks.add_task(remove_file, docx_temp_path)
|
| 54 |
|
| 55 |
-
# Return the DOCX file
|
| 56 |
return FileResponse(
|
| 57 |
docx_temp_path,
|
| 58 |
media_type='application/vnd.openxmlformats-officedocument.wordprocessingml.document',
|
| 59 |
filename=file.filename.replace('.pdf', '.docx')
|
| 60 |
)
|
| 61 |
except Exception as e:
|
| 62 |
-
logger.error(f"Conversion failed: {str(e)}")
|
| 63 |
-
# Clean up files in case of an error
|
| 64 |
remove_file(pdf_temp_path)
|
| 65 |
remove_file(docx_temp_path)
|
| 66 |
raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")
|
|
|
|
| 17 |
def remove_file(path: str):
|
| 18 |
if os.path.exists(path):
|
| 19 |
os.unlink(path)
|
|
|
|
| 20 |
|
| 21 |
@router.post("/convert/pdf_to_docx")
|
| 22 |
async def convert_pdf_to_docx(background_tasks: BackgroundTasks, file: UploadFile = File(...)):
|
| 23 |
if not file.filename.endswith('.pdf'):
|
| 24 |
raise HTTPException(status_code=400, detail="File must be a PDF")
|
| 25 |
|
|
|
|
| 26 |
os.makedirs(TEMP_DIR, exist_ok=True)
|
|
|
|
| 27 |
pdf_temp_path = os.path.join(TEMP_DIR, f"temp_{file.filename}")
|
| 28 |
docx_temp_path = pdf_temp_path.replace('.pdf', '.docx')
|
| 29 |
|
| 30 |
try:
|
|
|
|
| 31 |
with open(pdf_temp_path, "wb") as pdf_file:
|
| 32 |
shutil.copyfileobj(file.file, pdf_file)
|
|
|
|
|
|
|
| 33 |
|
|
|
|
| 34 |
cv = Converter(pdf_temp_path)
|
| 35 |
cv.convert(docx_temp_path)
|
| 36 |
cv.close()
|
| 37 |
|
|
|
|
|
|
|
|
|
|
| 38 |
if not os.path.exists(docx_temp_path):
|
| 39 |
raise FileNotFoundError(f"Converted file not found: {docx_temp_path}")
|
| 40 |
|
|
|
|
| 41 |
background_tasks.add_task(remove_file, pdf_temp_path)
|
| 42 |
background_tasks.add_task(remove_file, docx_temp_path)
|
| 43 |
|
|
|
|
| 44 |
return FileResponse(
|
| 45 |
docx_temp_path,
|
| 46 |
media_type='application/vnd.openxmlformats-officedocument.wordprocessingml.document',
|
| 47 |
filename=file.filename.replace('.pdf', '.docx')
|
| 48 |
)
|
| 49 |
except Exception as e:
|
|
|
|
|
|
|
| 50 |
remove_file(pdf_temp_path)
|
| 51 |
remove_file(docx_temp_path)
|
| 52 |
raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")
|