Google Cloud Vision OCR Python

gcvocr.py

#!/usr/bin/env python

# Copyright 2017 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""This application demonstrates how to perform fulltext detection with the
Google Cloud Vision API.
Example Usage:
python gcvocr.py text ./resources/wakeupcat.jpg
For more information, the documentation at
https://cloud.google.com/vision/docs.
"""

import argparse
import io
import re


# [START vision_fulltext_detection]
def detect_document(path):
    """Detects document features in an image."""
    from google.cloud import vision
    client = vision.ImageAnnotatorClient()

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

    image = vision.types.Image(content=content)

    response = client.document_text_detection(image=image)

    for page in response.full_text_annotation.pages:
        for block in page.blocks:
            print('\nBlock confidence: {}\n'.format(block.confidence))

            for paragraph in block.paragraphs:
                print('Paragraph confidence: {}'.format(
                    paragraph.confidence))

                for word in paragraph.words:
                    word_text = ''.join([
                        symbol.text for symbol in word.symbols
                    ])
                    print('Word text: {} (confidence: {})'.format(
                        word_text, word.confidence))

                    for symbol in word.symbols:
                        print('\tSymbol: {} (confidence: {})'.format(
                            symbol.text, symbol.confidence))
    # [END vision_python_migration_document_text_detection]
# [END vision_fulltext_detection]