Parse annotations from a pdf

Question

I want a python function that takes a pdf and returns a list of the text of the note annotations in the document. I have looked at python-poppler (https://code.launchpad.net

Answer 1

The author @JorjMcKie of PyMuPDF wrote a snippet for me and I modified a bit:

import fitz  # to import the PyMuPDF library
# from pprint import pprint


def _parse_highlight(annot: fitz.Annot, wordlist: list) -> str:
    points = annot.vertices
    quad_count = int(len(points) / 4)
    sentences = ['' for i in range(quad_count)]
    for i in range(quad_count):
        r = fitz.Quad(points[i * 4: i * 4 + 4]).rect
        words = [w for w in wordlist if fitz.Rect(w[:4]).intersects(r)]
        sentences[i] = ' '.join(w[4] for w in words)
    sentence = ' '.join(sentences)
    return sentence


def main() -> dict:
    doc = fitz.open('path/to/your/file')
    page = doc[0]

    wordlist = page.getText("words")  # list of words on page
    wordlist.sort(key=lambda w: (w[3], w[0]))  # ascending y, then x

    highlights = {}
    annot = page.firstAnnot
    i = 0
    while annot:
        if annot.type[0] == 8:
            highlights[i] = _parse_highlight(annot, wordlist)
            i += 1
            print('> ' + highlights[i] + '\n')
        annot = annot.next

    # pprint(highlights)
    return highlights


if __name__ == "__main__":
    main()

• https://github.com/pymupdf/PyMuPDF
• Is it posible to extract highlighted text? #318 https://github.com/pymupdf/PyMuPDF/issues/318#issuecomment-657102559

Though there are still some small typos in the results:

> system upsets,

> expansion of smart grid monitoring devices that generally provide nodal voltages and power injections at fine spatial resolution,

> hurricanes to indi- vidual lightning strikes),