collection.py

from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from cStringIO import StringIO

import models


class Pages(object):

    def __init__(self, document):

        self.__document = document

    def __iter__(self):

        manager = PDFResourceManager()
        outfp = StringIO()
        device = TextConverter(manager, outfp, laparams=LAParams())
        interpreter = PDFPageInterpreter(manager, device)

        for num, page in enumerate(PDFPage.create_pages(self.__document)):
            if num > 314:
                interpreter.process_page(page)
                text = outfp.getvalue()
                yield models.Page(page, text)


class Document(PDFDocument):

    def __init__(self, parser):

        super(Document, self).__init__(parser)
        self.__parser = parser
        self.__pages = None

        if not self.is_extractable:
            raise PDFTextExtractionNotAllowed

    def pages(self):

        if not self.__pages:
            self.__pages = Pages(self)

        return self.__pages

    @property
    def parser(self):
        return self.__parser

main.py

import sys
from pdfminer.pdfparser import PDFParser
from collection import Document

if __name__ == '__main__':
    with open(sys.argv[1], 'rb') as fp:
        parser = PDFParser(fp)
        document = Document(parser)

        with open(sys.argv[2], 'w') as data_out:
            for page in document.pages():
                data_out.write(page.text)

models.py

class Page(object):

    def __init__(self, page, text):
        self.__page = page
        self.__text = text

    @property
    def text(self):
        return self.__text