I am trying to delete all footnotes/endnotes in a pdf. They all have a font size of six, while the rest of the text has a font size of twelve.

Example text:

“The Industrial Revolution marked a significant turning point in human history, ushering in mass production and urbanization.”19 (“19” would be in font size six).

Text after running code:

“The Industrial Revolution marked a significant turning point in human history, ushering in mass production and urbanization.”

This is the code I have so far, but is not working.

import fitz  # PyMuPDF

def remove_small_numbers(pdf_path, output_path):
    doc = fitz.open(pdf_path)

    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        blocks = page.get_text("dict")["blocks"]

        for b in blocks:
            if "lines" in b:
                for line in b["lines"]:
                    for span in line["spans"]:
                        if span["size"] == 6 and span["text"].strip().isdigit():
                            rect = fitz.Rect(span["bbox"])  # Get the bounding box of the span
                            page.add_rect_annot(rect)  # Add a transparent annotation to cover the text

        # Remove all annotations (which cover the small numbers)
        for annot in page.annots():
            page.delete_annot(annot)

    doc.save(output_path)
    doc.close()

# Example usage
input_pdf = "input.pdf"
output_pdf = "output.pdf"

remove_small_numbers(input_pdf, output_pdf)