Getting Unexpected EOF with Python PDFMiner when creating a document object

Question

I'm trying to parse PDF file in a directory using PDFMiner, and I'm starting out by replicating the first script from the documentation contained here. The code (repeated below) opens the file, and creates the parser object, but gives an 'Unexpected EOF' error when trying to create the document object. Any help in understanding why this is the case would be greatly appreciated. Specifically, are there types of PDFs that cannot be parsed in this way?

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice

import os
import re

fp = open(os.getcwd() + '\\' + os.listdir(os.getcwd())[0])

parser = PDFParser(fp)
doc = PDFDocument(parser) #This is the problem, getting an "unexpected EOF" error

if not doc.is_extractable:
    raise PDFTextExtractionNotAllowed

rsrcmgr = PDFResourceManager()
device = PDFDevice(rsrcmgr)
interpreter = PDFPageInterpreter(rsrcmgr, device)

for page in PDFPage.create_pages(doc):
    interpreter.process_page(page)

This yields the following error:

%run scrape_psr.py
---------------------------------------------------------------------------
PSEOF                                     Traceback (most recent call last)
C:\Users\Rob Lantz\Anaconda\lib\site-packages\IPython\utils\py3compat.pyc in execfile(fname, glob, loc)
    195             else:
    196                 filename = fname
--> 197             exec compile(scripttext, filename, 'exec') in glob, loc
    198     else:
    199         def execfile(fname, *where):


     22 
     23 parser = PDFParser(fp)
---> 24 doc = PDFDocument(parser) #This is the problem, getting an "unexpected EOF" error
     25 
     26 if not doc.is_extractable:

C:\Users\Rob Lantz\Anaconda\lib\site-packages\pdfminer-20140328-py2.7.egg\pdfminer\pdfdocument.pyc in __init__(self, parser, password, caching, fallback)
    313             parser.fallback = True
    314             xref = PDFXRefFallback()
--> 315             xref.load(parser)
    316             self.xrefs.append(xref)
    317         for xref in self.xrefs:

C:\Users\Rob Lantz\Anaconda\lib\site-packages\pdfminer-20140328-py2.7.egg\pdfminer\pdfdocument.pyc in load(self, parser, debug)
    173             # expand ObjStm.
    174             parser.seek(pos)
--> 175             (_, obj) = parser.nextobject()
    176             if isinstance(obj, PDFStream) and obj.get('Type') is LITERAL_OBJSTM:
    177                 stream = stream_value(obj)

C:\Users\Rob Lantz\Anaconda\lib\site-packages\pdfminer-20140328-py2.7.egg\pdfminer\psparser.pyc in nextobject(self)
    555         """
    556         while not self.results:
--> 557             (pos, token) = self.nexttoken()
    558             #print (pos,token), (self.curtype, self.curstack)
    559             if isinstance(token, (int, long, float, bool, str, PSLiteral)):

C:\Users\Rob Lantz\Anaconda\lib\site-packages\pdfminer-20140328-py2.7.egg\pdfminer\psparser.pyc in nexttoken(self)
    480     def nexttoken(self):
    481         while not self._tokens:
--> 482             self.fillbuf()
    483             self.charpos = self._parse1(self.buf, self.charpos)
    484         token = self._tokens.pop(0)

C:\Users\Rob Lantz\Anaconda\lib\site-packages\pdfminer-20140328-py2.7.egg\pdfminer\psparser.pyc in fillbuf(self)
    213         self.buf = self.fp.read(self.BUFSIZ)
    214         if not self.buf:
--> 215             raise PSEOF('Unexpected EOF')
    216         self.charpos = 0
    217         return

PSEOF: Unexpected EOF

Edit: Some have suggested that the problem is with xref table, related to the question here. I'm unconvinced since that error trace does not mention "Unexpected EOF", but rather "EOF marker not found". The solution, such that it is, may be valid in that it essentially says that Python packages as they exist right now are not well suited to parsing the mess that is PDF file standards.