haystack index for django-filer PDFs

search_indexes.py

# coding: utf-8
from __future__ import unicode_literals
import os
from pdfminer.pdfdocument import PDFEncryptionError

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
from haystack import indexes

from filer.models import File


class PDFIndex(indexes.SearchIndex, indexes.Indexable):
    text = indexes.CharField(document=True)
    title = indexes.CharField()
    url = indexes.CharField()
    counter = 0
    # target = indexes.CharField()

    def get_model(self):
        return File

    def index_queryset(self, using=None):
        """Used when the entire index for model is updated."""
        return self.get_model().objects.filter(file__endswith='.pdf', )
        # original_filename__contains="Geschäftsbericht")

    def get_updated_field(self):
        return "modified_at"

    def prepare_text(self, object):
        self.counter += 1
        print "--- %s ---------------------" % self.counter
        print object
        print object.url
        text = convert_pdf_to_txt(object.path)
        document = "%s %s %s" % (self.prepare_title(object), self.prepare_url(object), text)
        print "--- ok -----"
        # print document
        return document

    def prepare_title(self, object):
        title = object.file.name
        # print title
        return title

    def prepare_url(self, object):
        url = object.url
        # print url
        return url


def convert_pdf_to_txt(path):
    if not os.path.isfile(path):
        print "file not existing: %s" % path
        return ''
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()

    try:
        pages = PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,
                                  caching=caching, check_extractable=True)
        for page in pages:
            interpreter.process_page(page)
    except UnicodeDecodeError:
        print "ENCRYPTED PDF DETECTED (probably, but no unknown encryption)!"
        return ''
    except PDFEncryptionError:
        print "UNKNOWN ENCRYPTION DETECTED"
        return ''

    text = retstr.getvalue()
    text = unicode(text, 'utf-8')

    fp.close()
    device.close()
    retstr.close()
    return text