06d4652807
git-svn-id: svn://svn.cy55.de/Zope3/src/cybertools/trunk@1626 fd906abe-77d9-0310-91a1-e0d9ade77398
42 lines
1.3 KiB
Python
42 lines
1.3 KiB
Python
#
|
|
# Copyright (c) 2007 Helmut Merz helmutm@cy55.de
|
|
#
|
|
# This program is free software; you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation; either version 2 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with this program; if not, write to the Free Software
|
|
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
#
|
|
|
|
"""
|
|
Searchable text support for Portable Document Format (PDF) files.
|
|
|
|
This uses the pdftotext command from xpdf to perform the extraction.
|
|
|
|
Based on code provided by zc.index and TextIndexNG3.
|
|
|
|
$Id$
|
|
"""
|
|
|
|
import os, sys
|
|
|
|
from cybertools.text import base
|
|
|
|
|
|
class PdfTransform(base.BaseFileTransform):
|
|
|
|
extension = ".pdf"
|
|
|
|
def extract(self, directory, filename):
|
|
if not self.checkAvailable('pdftotext', 'pdftotext is not available'):
|
|
return u''
|
|
data = self.execute('pdftotext -enc UTF-8 "%s" -' % filename)
|
|
return data.decode('UTF-8')
|