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_filepat         


        

Answer 1

In 2019, for ones who are interested in a faster way, it's possible to use:

from PyPDF2 import PdfFileReader

def printPageNumberFrom(filename):
    with open(filename, "rb") as f:
       pdf = PdfFileReader(f)
       bookmarks = pdf.getOutlines()
       for b in bookmarks:
           print(pdf.getDestinationPageNumber(b) + 1) #page count starts from 0 

Answer 2

Manage bookmarks recursively with vjayky and Giulio D suggestion

PyPDF2 >= v1.25

from PyPDF2 import PdfFileReader

def printBookmarksPageNumbers(pdf):
    def review_and_print_bookmarks(bookmarks, lvl=0):
        for b in bookmarks:
            if type(b) == list:
                review_and_print_bookmarks(b, lvl + 4)
                continue
            pg_num = pdf.getDestinationPageNumber(b) + 1 #page count starts from 0
            print("%s%s: Page %s" %(" "*lvl, b.title, pg_num))
    review_and_print_bookmarks(pdf.getOutlines())

with open('document.pdf', "rb") as f:
    pdf = PdfFileReader(f)
    printBookmarksPageNumbers(pdf)

PyPDF2 < v1.25

from PyPDF2 import PdfFileReader

def printBookmarksPageNumbers(pdf):
    # Map page ids to page numbers
    pg_id_to_num = {}
    for pg_num in range(0, pdf.getNumPages()):
        pg_id_to_num[pdf.getPage(pg_num).indirectRef.idnum] = pg_num

    def review_and_print_bookmarks(bookmarks, lvl=0):
        for b in bookmarks:
            if type(b) == list:
                review_and_print_bookmarks(b, lvl + 4)
                continue
            pg_num = pg_id_to_num[b.page.idnum] + 1 #page count starts from 0 
            print("%s%s: Page %s" %(" "*lvl, b.title, pg_num))
    review_and_print_bookmarks(pdf.getOutlines())

with open('document.pdf', "rb") as f:
    pdf = PdfFileReader(f)
    printBookmarksPageNumbers(pdf)

Answer 3

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))

Answer 4

I'm not sure but according to the docs for pyPdf.Destination at http://pybrary.net/pyPdf/pythondoc-pyPdf.pdf.html#pyPdf.pdf.Destination.page-attribute the page number for the bookmark is just Destination.page .