Split pdf based on outline

Question

I would like to use pyPdf to split a PDF file based on a path, where each destination in the path links to another page in pdf.

Example circuit:

main -> points to page 1
  sect1 -> points to page 1
  sect2 -> points to page 15
  sect3 -> points to page 22

in pyPdf, it is easy to cut through every page of a document or each recipient in the outline of a document; however, I cannot figure out how to get the page number where the destination points are.

Does anyone know how to find the page reference number for each destination in the outline?

Answer 1

I understood:

    class Darrell (pyPdf.PdfFileReader):

        def getDestinationPageNumbers(self):
            def _setup_outline_page_ids(outline, _result=None):
                if _result is None:
                    _result = {}
                for obj in outline:
                    if isinstance(obj, pyPdf.pdf.Destination):
                        _result[(id(obj), obj.title)] = obj.page.idnum
                    elif isinstance(obj, list):
                        _setup_outline_page_ids(obj, _result)
                return _result

            def _setup_page_id_to_num(pages=None, _result=None, _num_pages=None):
                if _result is None:
                    _result = {}
                if pages is None:
                    _num_pages = []
                    pages = self.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(page.getObject(), _result, _num_pages)
                elif t == "/Page":
                    _num_pages.append(1)
                return _result

            outline_page_ids = _setup_outline_page_ids(self.getOutlines())
            page_id_to_page_numbers = _setup_page_id_to_num()

            result = {}
            for (_, title), page_idnum in outline_page_ids.iteritems():
                result[title] = page_id_to_page_numbers.get(page_idnum, '???')
            return result

    pdf = Darrell(open(PATH-TO-PDF, 'rb'))
    template = '%-5s  %s'
    print template % ('page', 'title')
    for p,t in sorted([(v,k) for k,v in pdf.getDestinationPageNumbers().iteritems()]):
        print template % (p+1,t)

Answer 2

Darrell pdf ( pdftoc pdftk.)

_setup_page_id_to_num, "", 1. . , , . .

"PDF Hacks" , LaTeX, .. , pdftk , python.

Answer 3

, . PdfFileReader PyPDF2.

, PyPDF2 sejda-console PDF . 1, . script .

import operator
import os
import subprocess
import sys
import time

import PyPDF2 as pyPdf

# need to have sejda-console installed
# change this to point to your installation
sejda = 'C:\\sejda-console-1.0.0.M2\\bin\\sejda-console.bat'

class Darrell(pyPdf.PdfFileReader):
    ...

if __name__ == '__main__':
    t0= time.time()

    # get the name of the file to split as a command line arg
    pdfname = sys.argv[1]

    # open up the pdf
    pdf = Darrell(open(pdfname, 'rb'))

    # build list of (pagenumbers, newFileNames)
    splitlist = [(1,'FrontMatter')] # Customize name of first section

    template = '%-5s  %s'
    print template % ('Page', 'Title')
    print '-'*72
    for t,p in sorted(pdf.getDestinationPageNumbers().iteritems(),
                      key=operator.itemgetter(1)):

        # Customize this to get it to split where you want
        if t.startswith('Chapter') or \
           t.startswith('Preface') or \
           t.startswith('References'):

            print template % (p+1, t)

            # this customizes how files are renamed
            new = t.replace('Chapter ', 'Chapter')\
                   .replace(':  ', '-')\
                   .replace(': ', '-')\
                   .replace(' ', '_')
            splitlist.append((p+1, new))

    # call sejda tools and split document
    call = sejda
    call += ' splitbypages'
    call += ' -f "%s"'%pdfname
    call += ' -o ./'
    call += ' -n '
    call += ' '.join([str(p) for p,t in splitlist[1:]])
    print '\n', call
    subprocess.call(call)
    print '\nsejda-console has completed.\n\n'

    # rename the split files
    for p,t in splitlist:
        old ='./%i_'%p + pdfname
        new = './' + t + '.pdf'
        print 'renaming "%s"\n      to "%s"...'%(old, new),

        try:
            os.remove(new)
        except OSError:
            pass

        try:
            os.rename(old, new)
            print' succeeded.\n'
        except:
            print' failed.\n'

    print '\ndone. Spliting took %.2f seconds'%(time.time() - t0)

Answer 4

@darrell, UTF-8, , .

pyPdf.pdf.Destination.title, :

• pyPdf.generic.TextStringObject
• pyPdf.generic.ByteStringObject

so the output from the function _setup_outline_page_ids()also returns two different types for the object titlethat fails with UnicodeDecodeErrorif the header header contains anything other than ASCII.

I added this code to solve the problem:

if isinstance(title, pyPdf.generic.TextStringObject):
    title = title.encode('utf-8')

whole class:

class PdfOutline(pyPdf.PdfFileReader):

    def getDestinationPageNumbers(self):

        def _setup_outline_page_ids(outline, _result=None):
            if _result is None:
                _result = {}
            for obj in outline:
                if isinstance(obj, pyPdf.pdf.Destination):
                    _result[(id(obj), obj.title)] = obj.page.idnum
                elif isinstance(obj, list):
                    _setup_outline_page_ids(obj, _result)
            return _result

        def _setup_page_id_to_num(pages=None, _result=None, _num_pages=None):
            if _result is None:
                _result = {}
            if pages is None:
                _num_pages = []
                pages = self.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(page.getObject(), _result, _num_pages)
            elif t == "/Page":
                _num_pages.append(1)
            return _result

        outline_page_ids = _setup_outline_page_ids(self.getOutlines())
        page_id_to_page_numbers = _setup_page_id_to_num()

        result = {}
        for (_, title), page_idnum in outline_page_ids.iteritems():
            if isinstance(title, pyPdf.generic.TextStringObject):
                title = title.encode('utf-8')
            result[title] = page_id_to_page_numbers.get(page_idnum, '???')
        return result