Estimated time calculator for Getty Re indexing

estimated-time-for-getty-reindex.py

# Put this file on scripts folder and run using following command
# sudo DJANGO_SETTINGS_MODULE=theplatform.settings  /root/python-env/bin/python estimated-time-for-getty-reindex.py  /home/ubuntu/source-72-combine-getty-assetgroups.checkpoint

import sys
import datetime


def print_progress(filename):
    with open(filename, 'r') as f:
        content = f.read()
        (dur, checkpoint_info) = eval(content)
        (_, _, checkpoint_id, num_err, num_suc) = checkpoint_info

    from theplatform.newscred.models import Source, Image
    GETTY_SOURCE = Source.objects.get(name='Getty Images')
    remn = Image.objects.filter(source=GETTY_SOURCE, id__lt=checkpoint_id).count()
    rdur = dur*remn/(num_err+num_suc)
    print "Estimated remaining time to complete: %s" % rdur


def main():
    print_progress(sys.argv[1])


if __name__ == '__main__':
    main()

The back pop is completed. Content of the checkpoint after completion is

[datetime.timedelta(20, 7796, 861578), ('theplatform.newscred.models.image', 'Image', 4063647L, 10, 34294634)]