| from io import BytesIO | |
| from docx import Document as DocxDocument | |
| from pptx import Presentation | |
| def extract_text_from_docx(content_bytes: bytes) -> str: | |
| doc = DocxDocument(BytesIO(content_bytes)) | |
| paragraphs = [p.text for p in doc.paragraphs if p.text.strip()] | |
| return "\n".join(paragraphs) | |
| def extract_text_from_pptx(content_bytes: bytes) -> str: | |
| prs = Presentation(BytesIO(content_bytes)) | |
| texts = [] | |
| for slide in prs.slides: | |
| for shape in slide.shapes: | |
| if hasattr(shape, "text") and shape.text.strip(): | |
| texts.append(shape.text) | |
| return "\n".join(texts) | |