def extract_and_ocr(filename, region):
application_id = os.environ['ABBYY_APPLICATION_ID']
password = os.environ['ABBYY_PASSWORD']
ocr_engine = CloudOCR(application_id=application_id, password=password)
image = Image.open(filename)
region_data = image.crop(region)
stream = StringIO()
region_data.save(stream, 'JPEG')
stream.seek(0)
post_file = {'temp.jpg': stream}
result = ocr_engine.process_and_download(post_file,exportFormat='txt')
return result['txt'].read()
def extract_and_ocr(filename, region):
application_id = os.environ['ABBYY_APPLICATION_ID']
password = os.environ['ABBYY_PASSWORD']
ocr_engine = CloudOCR(application_id=application_id, password=password)
image = Image.open(filename)
region_data = image.crop(region)
stream = StringIO()
region_data.save(stream, 'JPEG')
stream.seek(0)
post_file = {'temp.jpg': stream}
result = ocr_engine.process_and_download(post_file, exportFormat='txt')
return result['txt'].read()
def mrz_scan(source_file, APPID, PWD):
if (os.path.isfile(source_file) == False):
raise Exception("file error.")
ocr_engine = CloudOCR(APPID, PWD)
input_file = open(source_file, 'rb')
post_file = {input_file.name: input_file}
# print("Waiting...")
time.sleep(0.0001)
result = ocr_engine.process_and_download(post_file,
exportFormat='txt',
language='English')
mrz_code = ""
f = result['txt'].read().decode("utf-8")
for d in f.splitlines()[-3:]:
if '<' in d:
# remove space for error scan
mrz_code += re.sub(' ', '', d)[:44]
mrz_code += '\n'
print("ourcode :", mrz_code)
return mrz_code
'Contains a password for accessing password-protected images in PDF format.'
)
parser.add_argument('--inputFilename', help='', required=True)
args = parser.parse_args()
if 'ABBYY_APPLICATION_ID' in os.environ.keys():
application_id = os.environ['ABBYY_APPLICATION_ID']
else:
application_id = args.application_id
if 'ABBYY_PASSWORD' in os.environ.keys():
password = os.environ['ABBYY_PASSWORD']
else:
password = args.password
ocr_engine = CloudOCR(application_id, password)
api_parameters = ['language', 'textType', 'exportFormat', 'pdfPassword']
parameters = dict(
filter(lambda x: x[0] in api_parameters and x[1] is not None,
args._get_kwargs()))
input_file = open(args.inputFilename, 'rb')
post_file = {input_file.name: input_file}
result = ocr_engine.process_and_download(post_file, **parameters)
for format, content in result.iteritems():
output_filename = '{name}.{extension}'.format(name='.'.join(
input_file.name.split('.')[:-1]),
extension=format)
with open(output_filename, 'wb') as output_file:
output_file.write(content.read())
parser.add_argument('--language', help='Specifies recognition language of the document.')
parser.add_argument('--textType', help='Specifies the type of the text on a page.')
parser.add_argument('--exportFormat', help='Specifies the export format.')
parser.add_argument('--pdfPassword', help='Contains a password for accessing password-protected images in PDF format.')
parser.add_argument('--inputFilename', help='', required=True)
args = parser.parse_args()
if 'ABBYY_APPLICATION_ID' in list(os.environ.keys()):
application_id = os.environ['ABBYY_APPLICATION_ID']
else:
application_id = args.application_id
if 'ABBYY_PASSWORD' in list(os.environ.keys()):
password = os.environ['ABBYY_PASSWORD']
else:
password = args.password
ocr_engine = CloudOCR(application_id, password)
api_parameters = ['language', 'textType', 'exportFormat', 'pdfPassword']
parameters = dict([x for x in args._get_kwargs() if x[0] in api_parameters and x[1] is not None])
input_file = open(args.inputFilename, 'rb')
post_file = {input_file.name: input_file}
result = ocr_engine.process_and_download(post_file, **parameters)
for format, content in result.items():
output_filename = '{name}.{extension}'.format(name='.'.join(input_file.name.split('.')[:-1]), extension=format)
with open(output_filename, 'wb') as output_file:
output_file.write(content.read())
output_file.close()
from ABBYY import CloudOCR
from io import BytesIO
import os
import dropbox
import argparse
parser = argparse.ArgumentParser(
description="runs ocr on the given files and uploads it to dropbox")
parser.add_argument('file', type=argparse.FileType('r'), nargs='+')
parser.add_argument('--output', required=True)
args = parser.parse_args()
dropbox = dropbox.Dropbox(os.environ['dropbox_token'])
ocr = CloudOCR(application_id=os.environ['abbyy_app_id'],
password=os.environ['abbyy_app_secret'])
def ocrImages(files, exportFormat="pdfSearchable"):
task = None
for file in files:
if task is None:
task = ocr.submitImage(file={file.name: file})
else:
task = ocr.submitImage(file={file.name: file}, taskId=task['id'])
task = ocr.processDocument(taskId=task['id'], exportFormat=exportFormat)
result = ocr.wait_for_task(task)
print("%s credits were used." % result['credits'])
download = ocr.session.get(result['resultUrl'])
return download
