python - How to get bookmark's page number

Question

from typing import List
from PyPDF2 import PdfFileReader
from PyPDF2.generic import Destination


def get_outlines(pdf_filepath: str) -> List[Destination]:
    """Get the bookmarks of a PDF file."""
    with open(pdf_filepath, "rb") as fp:
        pdf_file_reader = PdfFileReader(fp)
        outlines = pdf_file_reader.getOutlines()
    return outlines


print(get_outlines("PDF-export-example.pdf"))

pyPdf.pdf.Destination has many properties, but I can't find any referring page number of that bookmark. How can I get the page number of the bookmarks?

---

For example outlines[1].page.idnum returns a number which is approximately 3 times bigger than referenced page number in PDF document, which I assume references some object smaller then page, as running .page.idnum on whole PDF document outline returns array of numbers which is not even linearly correlated with "real" page number destinations in PDF document and it's roughly multiple by ~ 3

---

Update: This question is same as this: split a pdf based on outline although I don't understand what author did in his self answer there. Seems too complicated to me to be usable

Answer 1

As @theta pointed out "split a pdf based on outline" has the code required to extract page numbers. If you feel this is complicated I copied part of the code which maps page ids to page numbers and made it a function. Here is a working example that prints page number of bookmark o[0]:

from PyPDF2 import PdfFileReader


def _setup_page_id_to_num(pdf, pages=None, _result=None, _num_pages=None):
    if _result is None:
        _result = {}
    if pages is None:
        _num_pages = []
        pages = pdf.trailer["/Root"].getObject()["/Pages"].getObject()
    t = pages["/Type"]
    if t == "/Pages":
        for page in pages["/Kids"]:
            _result[page.idnum] = len(_num_pages)
            _setup_page_id_to_num(pdf, page.getObject(), _result, _num_pages)
    elif t == "/Page":
        _num_pages.append(1)
    return _result
# main
f = open('document.pdf','rb')
p = PdfFileReader(f)
# map page ids to page numbers
pg_id_num_map = _setup_page_id_to_num(p)
o = p.getOutlines()
pg_num = pg_id_num_map[o[0].page.idnum] + 1
print(pg_num)

probably too late for @theta but might help others :) btw my first post on stackoverflow so excuse me if I did not follow the usual format

To extend this further: If you are looking to get the exact location on the page for a bookmark this will make your job easier:

from PyPDF2 import PdfFileReader
import PyPDF2 as pyPdf

def _setup_page_id_to_num(pdf, pages=None, _result=None, _num_pages=None):
    if _result is None:
        _result = {}
    if pages is None:
        _num_pages = []
        pages = pdf.trailer["/Root"].getObject()["/Pages"].getObject()
    t = pages["/Type"]
    if t == "/Pages":
        for page in pages["/Kids"]:
            _result[page.idnum] = len(_num_pages)
            _setup_page_id_to_num(pdf, page.getObject(), _result, _num_pages)
    elif t == "/Page":
        _num_pages.append(1)
    return _result
def outlines_pg_zoom_info(outlines, pg_id_num_map, result=None):
    if result is None:
        result = dict()
    if type(outlines) == list:
        for outline in outlines:
            result = outlines_pg_zoom_info(outline, pg_id_num_map, result)
    elif type(outlines) == pyPdf.pdf.Destination:
        title = outlines['/Title']
        result[title.split()[0]] = dict(title=outlines['/Title'], top=outlines['/Top'], 
        left=outlines['/Left'], page=(pg_id_num_map[outlines.page.idnum]+1))
    return result

# main
pdf_name = 'document.pdf'
f = open(pdf_name,'rb')
pdf = PdfFileReader(f)
# map page ids to page numbers
pg_id_num_map = _setup_page_id_to_num(pdf)
outlines = pdf.getOutlines()
bookmarks_info = outlines_pg_zoom_info(outlines, pg_id_num_map)
print(bookmarks_info)

Note: My bookmarks are section numbers (ex: 1.1 Introduction) and I am mapping the bookmark info to the section number. If your bookmarks are different modify this part of the code:

    elif type(outlines) == pyPdf.pdf.Destination:
        title = outlines['/Title']
        result[title.split()[0]] = dict(title=outlines['/Title'], top=outlines['/Top'], 
        left=outlines['/Left'], page=(pg_id_num_map[outlines.page.idnum]+1))