| import os | |
| from pypdf import PdfReader | |
| def extract_text_from_pdf(pdf_path: str) -> str: | |
| reader = PdfReader(pdf_path) | |
| chunks = [] | |
| for page in reader.pages: | |
| chunks.append(page.extract_text() or "") | |
| return "\n".join(chunks).strip() | |
| def save_uploaded_pdf(src_path: str, dest_dir: str) -> str: | |
| os.makedirs(dest_dir, exist_ok=True) | |
| base = os.path.basename(src_path) | |
| dest_path = os.path.join(dest_dir, base) | |
| # перезапись ок для пилота | |
| with open(src_path, "rb") as fsrc, open(dest_path, "wb") as fdst: | |
| fdst.write(fsrc.read()) | |
| return dest_path | |