| from PyPDF2 import PdfReader | |
| from io import BytesIO | |
| import logging | |
| logger = logging.getLogger(__name__) | |
| def parse_pdf(file_content): | |
| try: | |
| reader = PdfReader(BytesIO(file_content)) | |
| text = "" | |
| for page in reader.pages: | |
| extracted = page.extract_text() | |
| if extracted: | |
| text += extracted | |
| return text | |
| except Exception as e: | |
| logger.error(f"PDF parse error: {e}") | |
| return "" | |
| def parse_text(file_content): | |
| try: | |
| return file_content.decode("utf-8") | |
| except UnicodeDecodeError: | |
| try: | |
| return file_content.decode("latin1") | |
| except Exception as e: | |
| logger.error(f"Text parse error: {e}") | |
| return "" | |