|
import os |
|
import glob |
|
import comtypes.client |
|
import docx |
|
from fastapi import FastAPI, File, UploadFile |
|
from pydantic import BaseModel |
|
from starlette.responses import FileResponse |
|
import zipfile |
|
import io |
|
|
|
app = FastAPI() |
|
|
|
UPLOAD_FOLDER = 'uploads/' |
|
if not os.path.exists(UPLOAD_FOLDER): |
|
os.makedirs(UPLOAD_FOLDER) |
|
|
|
@app.post('/convert') |
|
async def convert_pdfs(pdf_files: list[UploadFile] = File(...)): |
|
if not pdf_files: |
|
return {"detail": "No selected file"} |
|
|
|
for pdf_file in pdf_files: |
|
filename = pdf_file.filename |
|
with open(os.path.join(UPLOAD_FOLDER, filename), "wb") as f: |
|
f.write(await pdf_file.read()) |
|
|
|
path_pdf = UPLOAD_FOLDER |
|
path_docx = UPLOAD_FOLDER |
|
|
|
word = comtypes.client.CreateObject('Word.Application') |
|
word.visible = 0 |
|
|
|
for i, doc in enumerate(glob.iglob(path_pdf + '*.pdf')): |
|
filename = doc.split('\\')[-1] |
|
in_file = os.path.abspath(doc) |
|
wdoc = word.Documents.Open(in_file) |
|
out_file = os.path.abspath(path_docx + filename[:-4] + '.docx') |
|
wdoc.SaveAs2(out_file, FileFormat=16) |
|
wdoc.Close() |
|
|
|
word.Quit() |
|
|
|
memory_file = io.BytesIO() |
|
with zipfile.ZipFile(memory_file, 'w', zipfile.ZIP_DEFLATED) as zf: |
|
for root, _, filenames in os.walk(UPLOAD_FOLDER): |
|
for filename in filenames: |
|
if filename.endswith('.docx'): |
|
filepath = os.path.join(root, filename) |
|
zf.write(filepath, filename) |
|
|
|
memory_file.seek(0) |
|
return FileResponse(memory_file, filename='converted_docx.zip', media_type='application/zip') |
|
|
|
if __name__ == '__main__': |
|
import uvicorn |
|
uvicorn.run(app, host='0.0.0.0', port=7860) |
|
|
