[PYTHON] Transcription of images with GCP's Vision API

Transcription of images with Vision API

'type': is "TEXT_DETECTION" There are two, "DOCUMENT_TEXT_DETECTION", and the latter is selected.

#coding:utf-8
import base64
import json
from requests import Request, Session
from io import BytesIO
from PIL import Image
import pandas as pd

#Throw an image opened in PIL to the Cloud Vision API
def recognize_image(pil_image):
        def pil_image_to_base64(img_path):
            pil_image = Image.open(img_path)
            buffered = BytesIO()
            pil_image.save(buffered, format="PNG")
            str_encode_file = base64.b64encode(buffered.getvalue()).decode("utf-8")
            return str_encode_file
        
        def get_fullTextAnnotation(json_data):
            text_dict = json.loads(json_data)
            try:
                text = text_dict["responses"][0]["fullTextAnnotation"]["text"]
                return text
            except:
                print(None)
                return None

        str_encode_file = pil_image_to_base64(pil_image)###Erase here at the end
        str_url = "https://vision.googleapis.com/v1/images:annotate?key="
        str_api_key = "API key"
        str_headers = {'Content-Type': 'application/json'}
        str_json_data = {
            'requests': [
                {
                    'image': {
                        'content': str_encode_file
                    },
                    'features': [
                        {
                            'type': "DOCUMENT_TEXT_DETECTION",
                            'maxResults': 10
                        }
                    ]
                }
            ]
        }

        obj_session = Session()
        obj_request = Request("POST",
                              str_url + str_api_key,
                              data=json.dumps(str_json_data),
                              headers=str_headers
                              )
        obj_prepped = obj_session.prepare_request(obj_request)
        obj_response = obj_session.send(obj_prepped,
                                        verify=True,
                                        timeout=60
                                        )

        if obj_response.status_code == 200:
            text = get_fullTextAnnotation(obj_response.text)
            
            return text

recognize_image ("image path")