fh_actors = open(outfile_actors, 'w')
writer_actors = None
for root, dirs, files in os.walk(datadir):
for f in files:
path = os.path.join(root, f)
logging.info("processing %s" % path)
data = json.load(open(path, 'r'))
data['ulan:id'] = data['ULAN']['UlanIdNo']
data['ulan:name'] = data['ULAN']['Name']
del(data['ULAN'])
if not writer_actors:
keys = data.keys()
keys.sort()
writer_actors = csv.DictWriter(fh_actors, fieldnames=keys)
writer_actors.writeheader()
data = utils.utf8ify_dict(data)
writer_actors.writerow(data)
logging.info("done");
del(data['images'])
del(data['participants'])
del(data['exhibitions'])
#
if not writer_objects:
keys = data.keys()
keys.append('primary_image')
keys.sort()
writer_objects = csv.DictWriter(fh_objects, fieldnames=keys)
writer_objects.writeheader()
try:
data = utils.utf8ify_dict(data)
writer_objects.writerow(data)
except Exception, e:
print data
raise Exception, e
#
if not writer_images:
writer_images = csv.DictWriter(fh_images, fieldnames=('object_id', 'size', 'url', 'width', 'height', 'is_primary'))
writer_images.writeheader()
for i in images:
if not type(i) == types.DictType:
continue
#
roles = data.get('roles', [])
del(data['roles'])
#
if not writer_people:
keys = data.keys()
keys.sort()
writer_people = csv.DictWriter(fh_people, fieldnames=keys)
writer_people.writeheader()
data = utils.utf8ify_dict(data)
writer_people.writerow(data)
#
if not writer_roles:
writer_roles = csv.DictWriter(fh_roles, fieldnames=('person_id', 'person_name', 'id', 'name', 'count_objects'))
writer_roles.writeheader()
for details in roles:
details['person_id'] = data['id']
details['person_name'] = data['name']
details = utils.utf8ify_dict(details)
writer_roles.writerow(details)
fh_actors = open(outfile_actors, 'w')
writer_actors = None
for root, dirs, files in os.walk(datadir):
for f in files:
path = os.path.join(root, f)
logging.info("processing %s" % path)
data = json.load(open(path, 'r'))
data['ulan:id'] = data['ULAN']['UlanIdNo']
data['ulan:name'] = data['ULAN']['Name']
del (data['ULAN'])
if not writer_actors:
keys = data.keys()
keys.sort()
writer_actors = csv.DictWriter(fh_actors, fieldnames=keys)
writer_actors.writeheader()
data = utils.utf8ify_dict(data)
writer_actors.writerow(data)
logging.info("done")
