PyPDF Merge and Write issue

I am getting an unexpected error when using this. The first section is from a script that I found online, and I am trying to use it to pull a particular section identified in the PDF's outline. Everything works fine, except right at output.write(outputfile1) it says:

PdfReadError: multiple definitions in dictionary.

Anybody else run into this? Please forgive all the unnecessary prints at the end. :)

import pyPdf
import glob

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开发者_如何学Python 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

for fileName in glob.glob("*.pdf"):
    output = pyPdf.PdfFileWriter()
    print fileName
    pdf = Darrell(open(fileName, '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)

    for p,t in sorted([(v,k) for k,v in pdf.getDestinationPageNumbers().iteritems()]):
        if t == "CATEGORY 1":
            startpg = p+1
            print p+1,'is the first page of Category 1.'
            if t == "CATEGORY 2":
                endpg = p+1
                print p+1,'is the last page of Category 1.'
    print startpg, endpg
    pagenums = range(startpg,endpg)
    print pagenums
    for i in pagenums:
        output.addPage(pdf.getPage(i))
    fileName2 = "%sCategory1_data.pdf" % (str(fileName[:-13]))
    print "%s has %s pages." % (fileName2,output.getNumPages())
    outputfile1 = file(r"%s" % (fileName2), 'wb')
    output.write(outputfile1)
    outputfile1.close()

I know it might be too late for you, but for anyone else who will stumble here to look for the answer: I had the same problem today, setting:

export_reader = PdfFileReader(filename, strict=False)

If you are just merging, then use:

merger = PdfFileMerger(strict=False)

This way, you will get only a warning, rather than an exception.