(pdf_path, start_page, end_page, tag=True)
| 234 | return title |
| 235 | |
| 236 | def get_text_of_pages(pdf_path, start_page, end_page, tag=True): |
| 237 | pdf_reader = PyPDF2.PdfReader(pdf_path) |
| 238 | text = "" |
| 239 | for page_num in range(start_page-1, end_page): |
| 240 | page = pdf_reader.pages[page_num] |
| 241 | page_text = page.extract_text() |
| 242 | if tag: |
| 243 | text += f"<start_index_{page_num+1}>\n{page_text}\n<end_index_{page_num+1}>\n" |
| 244 | else: |
| 245 | text += page_text |
| 246 | return text |
| 247 | |
| 248 | def get_first_start_page_from_text(text): |
| 249 | start_page = -1 |
nothing calls this directly
no outgoing calls
no test coverage detected