pdftitle.py

###
# Copyright (c) 2017, Brandon Roberts <brandon@bxroberts.org>
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
#   * Redistributions of source code must retain the above copyright notice,
#     this list of conditions, and the following disclaimer.
#   * Redistributions in binary form must reproduce the above copyright notice,
#     this list of conditions, and the following disclaimer in the
#     documentation and/or other materials provided with the distribution.
#   * Neither the name of the author of this software nor the name of
#     contributors to this software may be used to endorse or promote products
#     derived from this software without specific prior written consent.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
###

import PyPDF2
import io


def pdf2information(content):
    """
    Take a PDF page's content (data) and extract a title & info from
    the PDF metadata if it exists. Many PDFs omit this information
    so maybe a fallback could be extracting the first N chars
    from the document or to look for bookmarks or related metadata.
    Returns a dict with pages, title keys.
    """
    # we'll collect our information about the document here
    info = {
        "pages": '',
        "title": ''
    }

    try:
        o = io.BytesIO(content)
        reader = PyPDF2.PdfFileReader(o)
    except Exception, e:
        print "PDF parse error: {}".format(e)
        return ' '.join(response)

    try:
        title = reader.getDocumentInfo().title
    except Exception, e:
        print "error getting pdf documentinfo/title: {}".format(e)
    else:
        if title:
            info["title"] = title

    try:
        pages = reader.getNumPages()
    except Exception, e:
        print "PDF getNumPages error: {}".format(e)
    else:
        if pages == 1:
            info["pages"] = '{} page'.format(pages)
        elif pages > 1:
            info["pages"] = '{} pages'.format(pages)

    # will return blank string if nothing worked above
    return info