Spaces:
Configuration error
Configuration error
| import fitz # fitz is the internal name for PyMuPDF | |
| def load_pdf(file_path): | |
| """ | |
| Opens a PDF and extracts text from every page. | |
| Input : file_path → path to the PDF file on disk | |
| Output : list of dicts, one per page, like: | |
| [ | |
| {"page_num": 1, "text": "Introduction to AI..."}, | |
| {"page_num": 2, "text": "Chapter 1 begins here..."}, | |
| ] | |
| """ | |
| doc = fitz.open(file_path) # open the PDF file | |
| pages = [] # empty list to collect results | |
| for page_num in range(len(doc)): # loop through every page | |
| page = doc[page_num] # get the current page object | |
| text = page.get_text() # extract all text from this page | |
| text = text.strip() # remove extra spaces at start and end | |
| # only keep the page if it actually has text | |
| # some PDF pages are just images or blank — we skip those | |
| if text: | |
| pages.append({ | |
| "page_num": page_num + 1, # page numbers start from 1, not 0 | |
| "text": text # the actual text content | |
| }) | |
| doc.close() # always close the file when done | |
| print(f"Loaded {len(pages)} pages from the PDF.") | |
| return pages | |