Updated version of rlskoeser, Export people data for Shakespeare & co lending card holders (fields needed for Finding Aid enhancement and image import into Figgy)

mep_cardholders.py

# use env to set django settings module
# env DJANGO_SETTINGS_MODULE=mep.settings python mep_cardholders.py

import csv
import codecs


import django
from django.db import models
import progressbar

django.setup()

from mep.accounts.partial_date import DatePrecision
from mep.people.models import Person
from mep.accounts.models import Borrow, Event


cardholders = Person.objects.filter(account__card__isnull=False)

fields = ['name', 'sort name', 'person/organization', 'viaf', 'dates', 'images']

image_files = []



with open('/tmp/sylviabeach-cardholders.csv', 'w') as csvfile:
    # write utf-8 byte order mark at the beginning of the file
    csvfile.write(codecs.BOM_UTF8.decode())
    csvwriter = csv.writer(csvfile)
    csvwriter.writerow(fields)
    for person in progressbar.progressbar(cardholders):
        dates = ''
        account = person.account_set.filter(card__isnull=False).first()
        # find any event with footnotes for this account and order by
        # start date
        # footnote could be on event, borrow, or purchase
        events = Event.objects.filter(account=account) \
                      .filter(models.Q(event_footnotes__isnull=False) |
                              models.Q(borrow__footnotes__isnull=False) |
                              models.Q(purchase__footnotes__isnull=False)) \
                      .exclude(models.Q(event_footnotes__location='') &
                              models.Q(borrow__footnotes__location='') &
                              models.Q(purchase__footnotes__location='')) \
                      .order_by('start_date')
        # split on newline, drop first (label "Images:")
        card_images = account.card.notes.split()[1:]
        entity = 'organization' if person.is_organization else 'person'
        if events:
            # get earliest date and latest date, combine them if they aren't the same date
            dates = events.first().start_date or events.first().end_date
            end_date = events.last().end_date or events.last().start_date

            if end_date and end_date != dates:
                dates = '%s/%s' % (dates, end_date)

        card_images = ['%s.jp2' % img if not img.endswith('.jp2')
                       and img[-1].isnumeric() else img for img in card_images]
        # a number of image paths have an extra slash in the url; remove it
        card_images = [img.replace('//c/', '/c/').replace('.jpg', '.jp2')
                       for img in card_images]
        # add to list of all card images
        image_files.extend(card_images)
        csvwriter.writerow([person.name, person.sort_name, entity,
                            person.viaf.uri if person.viaf else '',
                            dates, ';'.join([str(img) for img in card_images])])


with open('/tmp/sylviabeach-card-images.txt', 'w') as cardimgfile:
    if len(image_files) != len(set(image_files)):
        print('Warning: duplicate images (unique count off by %d)' % \
              (len(image_files) - len(set(image_files)), ))
    cardimgfile.write('\n'.join(image_files))