emory-libraries/eulfedora

#!/usr/bin/env python

import base64
import hashlib
from eulfedora.server import Repository
from eulfedora.models import DigitalObject
from lxml import etree


def archive_decode():
    repo = Repository('https://libfedqa1.library.emory.edu:8443/fedora',
        username='fedoraAdmin', password='fedoraAdmin')
    # response = repo.api.export('readux:p7g45', context='archive',
    response = repo.api.export('readux:p7kcf', context='archive',
        stream=True)
    print response
    xmlarchive = etree.fromstring(response.content)
    print xmlarchive

    img_ds = xmlarchive.xpath('//foxml:datastreamVersion[@ID="source-image.0"]',
            namespaces={'foxml': DigitalObject.FOXML_NS})[0]
    digest = img_ds.xpath('foxml:contentDigest',
            namespaces={'foxml': DigitalObject.FOXML_NS})[0]
    print 'Datastream %s size %s, %s %s' % \
        (img_ds.get('ID'), img_ds.get('SIZE'),
            digest.get('TYPE'), digest.get('DIGEST'))

    binary_content = img_ds.xpath('foxml:binaryContent',
            namespaces={'foxml': DigitalObject.FOXML_NS})[0]
    decoded_content = base64.b64decode(binary_content.text)
    size = len(decoded_content)
    m = hashlib.md5()
    m.update(decoded_content)
    md5 = m.hexdigest()
    print 'decoded content size %s, MD5 %s' % \
        (size, md5)


if __name__ == '__main__':
    archive_decode()