OCR documents from local file system using google vision

google_doc_ocr.py

#!/usr/bin/env python
import argparse


def detect_text(path):
    """Detects text in the file."""
    from google.cloud import vision
    import io
    client = vision.ImageAnnotatorClient()

    # [START vision_python_migration_text_detection]
    with io.open(path, 'rb') as image_file:
        content = image_file.read()

    image = vision.Image(content=content)

    response = client.text_detection(image=image)
    texts = response.text_annotations
    complete_text = texts[0]
    print(complete_text.description)

    if response.error.message:
        raise Exception(
            '{}\nFor more info on error messages, check: '
            'https://cloud.google.com/apis/design/errors'.format(
                response.error.message))


def run_local(args):
    if args.command == 'text':
        detect_text(args.path)


if __name__ == '__main__':
    parser = argparse.ArgumentParser(
        description=__doc__,
        formatter_class=argparse.RawDescriptionHelpFormatter)
    subparsers = parser.add_subparsers(dest='command')

    detect_text_parser = subparsers.add_parser(
        'text', help=detect_text.__doc__)
    detect_text_parser.add_argument('path')

    args = parser.parse_args()
    run_local(args)