Spaces:
Sleeping
Sleeping
| import PyPDF2 | |
| from docx import Document | |
| def extract_text_from_pdf(file_path): | |
| """ | |
| Estrae il testo da un file PDF. | |
| Args: | |
| file_path: Percorso del file PDF | |
| Returns: | |
| str: Testo estratto dal PDF | |
| """ | |
| with open(file_path, 'rb') as f: | |
| reader = PyPDF2.PdfReader(f) | |
| text = "" | |
| for page in reader.pages: | |
| text += page.extract_text() | |
| return text | |
| def extract_text_from_docx(file_path): | |
| """ | |
| Estrae il testo da un file DOCX. | |
| Args: | |
| file_path: Percorso del file DOCX | |
| Returns: | |
| str: Testo estratto dal documento Word | |
| """ | |
| doc = Document(file_path) | |
| text = "" | |
| for para in doc.paragraphs: | |
| text += para.text + "\n" | |
| return text |