| from PyPDF2 import PdfReader | |
| # Function to extract text from PDFs (normal PDFs only) | |
| def extract_text_from_pdf(pdf_path): | |
| reader = PdfReader(pdf_path) | |
| text = "" | |
| for page in reader.pages: | |
| text += page.extract_text() | |
| return text.strip() | |
| # Main function to handle PDF text extraction | |
| def get_pdf_text(pdf_path): | |
| return extract_text_from_pdf(pdf_path) |