| import os |
| import uuid |
| import requests |
| from typing import Tuple |
| import shelve |
| import tempfile |
|
|
| class DocumentManager: |
| def __init__(self, document_url: str): |
| self.document_url = document_url |
| self.DIR = os.path.join(tempfile.gettempdir(), "doc_cache") |
| os.makedirs(self.DIR, exist_ok=True) |
| cached_path = self._get_cached_path() |
| if cached_path and os.path.exists(cached_path): |
| print("Document already cached.") |
| self.file_path = cached_path |
| else: |
| self.file_path, _ = self._download_and_cache() |
| print("Document not cached.") |
|
|
| def _get_cached_path(self) -> str: |
| with shelve.open(os.path.join(self.DIR, 'cache')) as cache: |
| return cache.get(self.document_url, '') |
|
|
| def _download_and_cache(self) -> Tuple[str, str]: |
| response = requests.get(self.document_url, timeout=60) |
| response.raise_for_status() |
| filename = f"{uuid.uuid4()}.pdf" |
| file_path = os.path.join(self.DIR, filename) |
| with open(file_path, "wb") as f: |
| f.write(response.content) |
| with shelve.open(os.path.join(self.DIR, 'cache')) as cache: |
| cache[self.document_url] = file_path |
| return file_path, filename |
|
|
| def get_filepath(self) -> str: |
| return self.file_path |
