def get_gas_price(url):
subscription_key = AZURE_COMPUTERVISION_SUBSCRIPTION_KEY
endpoint = "https://eastus.api.cognitive.microsoft.com/"
computervision_client = ComputerVisionClient(endpoint, CognitiveServicesCredentials(subscription_key))
# Get an image with printed text
remote_image_printed_text_url = url
# Call API with URL and raw response (allows you to get the operation location)
recognize_printed_results = computervision_client.batch_read_file(remote_image_printed_text_url, raw=True)
# Get the operation location (URL with an ID at the end) from the response
operation_location_remote = recognize_printed_results.headers["Operation-Location"]
# Grab the ID from the URL
operation_id = operation_location_remote.split("/")[-1]
# Call the "GET" API and wait for it to retrieve the results
while True:
get_printed_text_results = computervision_client.get_read_operation_result(operation_id)
if get_printed_text_results.status not in ['NotStarted', 'Running']:
break
time.sleep(1)
# Print the detected text, line by line
numbers_list = []
strings_list = []
newdict = {}
if get_printed_text_results.status == TextOperationStatusCodes.succeeded:
for text_result in get_printed_text_results.recognition_results:
for line in text_result.lines:
new_line = line.text.replace(" ", "")
if (is_float(new_line)):
numbers_list.append(float(new_line))
elif (is_string(new_line)):
strings_list.append(new_line)
newdict[new_line] = find_area(line.bounding_box)
numbers_list = [x for x in numbers_list if (x > 0 and x < 6) or (check_three_digit((x)))]
for x in range(len(numbers_list)):
while (numbers_list[x] >= 10.0):
numbers_list[x] /= 10.0
max = 0
gas_type = ""
for x in range(len(strings_list)):
if (newdict[strings_list[x]] > max):
max = newdict[strings_list[x]]
gas_type = strings_list[x]
price = numbers_list[0] if len(numbers_list) > 0 else 0
return {gas_type: price}
# 5. Displaying the results.
local_image_path = "resources\\handwritten_text.jpg"
local_image = open(local_image_path, "rb")
text_recognition_mode = TextRecognitionMode.handwritten
num_chars_in_operation_id = 36
client_response = computervision_client.batch_read_file_in_stream(
local_image, text_recognition_mode, raw=True)
operation_location = client_response.headers["Operation-Location"]
id_location = len(operation_location) - num_chars_in_operation_id
operation_id = operation_location[id_location:]
print("\n\nRecognizing text in a local image with the batch Read API ... \n")
while True:
result = computervision_client.get_read_operation_result(operation_id)
if result.status not in ['NotStarted', 'Running']:
break
time.sleep(1)
if result.status == TextOperationStatusCodes.succeeded:
for text_result in result.recognition_results:
for line in text_result.lines:
print(line.text)
print(line.bounding_box)
print()
# END - Recognizing printed and handwritten text with the batch read API in a local image
# Recognize text with the Read API in a remote image by:
# 1. Specifying whether the text to recognize is handwritten or printed.
# 2. Calling the Computer Vision service's batch_read_file_in_stream with the:
remote_image_printed_text_url = "https://raw.githubusercontent.com/tc-nyc/Cog-Services-Demo/master/Target%20Data.PNG"
# Call API with URL and raw response (allows you to get the operation location)
recognize_printed_results = computervision_client.batch_read_file(
remote_image_printed_text_url, raw=True)
# Get the operation location (URL with an ID at the end) from the response
operation_location_remote = recognize_printed_results.headers[
"Operation-Location"]
# Grab the ID from the URL
operation_id = operation_location_remote.split("/")[-1]
# Call the "GET" API and wait for it to retrieve the results
while True:
get_printed_text_results = computervision_client.get_read_operation_result(
operation_id)
if get_printed_text_results.status not in ['NotStarted', 'Running']:
break
time.sleep(1)
myData = []
125688
# Print the detected text, line by line
if get_printed_text_results.status == TextOperationStatusCodes.succeeded:
for text_result in get_printed_text_results.recognition_results:
for line in text_result.lines:
print(line.text)
myData.append(line.text)
#finalDataset = pandas.DataFrame(line.text, columns = line.bounding_box)
print("===== Batch Read File - local =====")
# Get image of handwriting
local_image_handwritten_path = "resources\\handwritten_text.jpg"
# Open the image
local_image_handwritten = open(local_image_handwritten_path, "rb")
# Call API with image and raw response (allows you to get the operation location)
recognize_handwriting_results = computervision_client.batch_read_file_in_stream(local_image_handwritten, raw=True)
# Get the operation location (URL with ID as last appendage)
operation_location_local = recognize_handwriting_results.headers["Operation-Location"]
# Take the ID off and use to get results
operation_id_local = operation_location_local.split("/")[-1]
# Call the "GET" API and wait for the retrieval of the results
while True:
recognize_handwriting_result = computervision_client.get_read_operation_result(operation_id_local)
if recognize_handwriting_result.status not in ['NotStarted', 'Running']:
break
time.sleep(1)
# Print results, line by line
if recognize_handwriting_result.status == TextOperationStatusCodes.succeeded:
for text_result in recognize_handwriting_result.recognition_results:
for line in text_result.lines:
print(line.text)
print(line.bounding_box)
print()
'''
END - Batch Read File - local
'''
# import models
from azure.cognitiveservices.vision.computervision.models import TextOperationStatusCodes
import time
image = open(path, 'rb')
# url = "https://smhttp-ssl-39255.nexcesscdn.net/wp-content/uploads/2016/01/Handwritten-note-on-Presidential-stationery-900x616.jpg"
raw = True
custom_headers = None
numberOfCharsInOperationId = 36
# Async SDK call
rawHttpResponse = client.batch_read_file_in_stream(image, custom_headers, raw)
# Get ID from returned headers
operationLocation = rawHttpResponse.headers["Operation-Location"]
idLocation = len(operationLocation) - numberOfCharsInOperationId
operationId = operationLocation[idLocation:]
# SDK call
while True:
result = client.get_read_operation_result(operationId)
if result.status not in ['NotStarted', 'Running']:
break
time.sleep(1)
# Get data
if result.status == TextOperationStatusCodes.succeeded:
for textResult in result.recognition_results:
for line in textResult.lines:
print(line.text)
print(line.bounding_box)
'''
Call the API
'''
# Use the Batch Read File API to extract text from the cropped image
for cropped_path in cropped_images_path:
cropped_bytes = open(cropped_path, "rb")
# Call API
results = client.batch_read_file_in_stream(cropped_bytes, raw=True)
# To get the read results, we need the operation ID from operation location
operation_location = results.headers["Operation-Location"]
# Operation ID is at the end of the URL
operation_id = operation_location.split("/")[-1]
# Wait for the "get_read_operation_result()" to retrieve the results
while True:
get_printed_text_results = client.get_read_operation_result(
operation_id)
if get_printed_text_results.status not in ['NotStarted', 'Running']:
break
time.sleep(1)
'''
Print results
'''
# Print the extracted text, line by line
if get_printed_text_results.status == OperationStatusCodes.succeeded:
for text_result in get_printed_text_results.recognition_results:
for line in text_result.lines:
print("Extracted text:")
print(line.text)
print()
print('Bounding box for each line:')
print(line.bounding_box)
