이미지 텍스트를 읽고 추출하는 최고의 Python OCR API

pip를 통해 Python용 Aspose.OCR Cloud SDK 설치

 pip install aspose-ocr-cloud

Aspose.OCR Python Cloud SDK 제품 페이지에서 SDK를 직접 다운로드할 수 있습니다.

Python 앱 내부 이미지에 OCR 수행

import asposeocrcloud

# create an instance of the OCR client
client = asposeocrcloud.OcrApi(api_key='your_api_key', app_sid='your_app_sid')

# read the image file
with open('image.jpg', 'rb') as image_file:
    image_data = image_file.read()

# call the OCR API to extract text from the image
result = client.post_ocr(image_data=image_data, language='eng', use_default_dictionaries=True)

# print the extracted text
print(result.text)

Python API를 통해 PDF 파일에서 텍스트를 추출하는 방법

import asposeocrcloud
from asposeocrcloud.apis.ocr_api import OcrApi
from asposeocrcloud.configuration import Configuration

configuration = Configuration(api_key='your_api_key', app_sid='your_app_sid')
api = OcrApi(asposeocrcloud.ApiClient(configuration))

# Upload the PDF file to the Aspose cloud storage

with open('your_pdf_file.pdf', 'rb') as file:
    api.upload_file(path='your_pdf_file.pdf', file=file)

# Perform the OCR recognition on the uploaded PDF file
result = api.post_recognize_ocr_from_url_or_content(file_path='your_pdf_file.pdf')

# Story the recognized text

recognized_text = result['text']
print(recognized_text)

Python API를 사용하여 텍스트를 음성으로 변환하는 방법

 import os
from asposeocrcloud import OcrApi, OcrClient, SpeechApi

client_id = os.environ['CLIENT_ID']
client_secret = os.environ['CLIENT_SECRET']
ocr_api = OcrApi(OcrClient(client_id, client_secret))
speech_api = SpeechApi(OcrClient(client_id, client_secret))

# Upload the image containing the text
filename = 'image.png'
with open(filename, 'rb') as file:
    response = ocr_api.post_recognize_from_content(file.read(), language='English', use_default_dictionaries=True)

# Extract the recognized text

text = ''
for result in response.parts:
    for line in result.lines:
        for word in line.words:
            text += word.text + ' '

# Convert the text to speech
response = speech_api.post_recognize_from_text(text, language='en-US', voice_name='Ben')

# Save the speech file to disk

with open('output.wav', 'wb') as file:
    file.write(response.content)