Google Vision API

visionapi.py

import argparse
import base64
import json
import sys
import requests

KEY = '<<your API key here>>'

# Usage:
# python visionapi.py -i input_file -o output_json_file

def main(input_filename, output_filename):
    """Translates the input file into a json output file.

    Args:
        input_file: a file object, containing lines of input to convert.
        output_filename: the name of the file to output the json to.
    """
    request_list = []

    with open(input_filename, 'rb') as image_file:
        content_json_obj = {
            'content': base64.b64encode(image_file.read())
        }

    feature_json_obj = []
    feature, max_results = [4, 10]
    feature_json_obj.append({
        'type': get_detection_type(feature),
        'maxResults': int(max_results),
    })

    request_list.append({
        'features': feature_json_obj,
        'image': content_json_obj,
    })

    response = requests.post(url='https://vision.googleapis.com/v1/images:annotate?key=' + KEY,
        data=json.dumps({'requests': request_list}),
        headers={'Content-Type': 'application/json'})
    with open(output_filename, 'w') as output_file:
        output_file.write(response.text)


DETECTION_TYPES = [
    'TYPE_UNSPECIFIED',
    'FACE_DETECTION',
    'LANDMARK_DETECTION',
    'LOGO_DETECTION',
    'LABEL_DETECTION',
    'TEXT_DETECTION',
    'SAFE_SEARCH_DETECTION',
]


def get_detection_type(detect_num):
    """Return the Vision API symbol corresponding to the given number."""
    detect_num = int(detect_num)
    if 0 < detect_num < len(DETECTION_TYPES):
        return DETECTION_TYPES[detect_num]
    else:
        return DETECTION_TYPES[0]

if __name__ == '__main__':
    main(sys.argv[2], sys.argv[4])

That CLI is pretty... not right. Why even bother with dash args when you're pulling directly from args list. =^.^=