O maj laćho Python OCR API te ginaves thaj te lel pes o teksto e imaʒenqo

Te astarel pes o Aspose.OCR Cloud SDK vaś o Python

O rekomenduime drom te instalis Aspose.OCR Cloud SDK vash Python si te hasnis o pip. Mangav tumen te hasnin o śerutno komando vaś jekh śukar instalàcia.

 pip install aspose-ocr-cloud

Image Recognition by Python Apps

Aspose.OCR Cloud SDK vaś o Python del śajsaripen e softveresqe kerde te keren OCR operacia te resen o prinźaripen e image-esqo and-e lenqe Python aplikacie. O API si but lokho te hasnil pes thaj o pindžaripe e imagengo šaj te kerel pes katar savi platforma savi si la internetosko akceso. Tu śaj te hasnis o OCR REST API te alosares thaj te bićhales e patretura vaś o prinʒaripen, te les e rezultàturǎ thaj te garaves len anθ-e sa e formaturǎ save si suportime e lilǎqe numaj jekh parne rigaqe kodosqe. O egzamplo so avel sikavel sar te kerel pes OCR operacia pe slike kotar o Python kodo.

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)

Xramosar o tèksto katar e PDF-esqe lila prekal o Python API

Portable Document Format (PDF) si jekh katar e maj popularno formatura e biznis dokumenturenqi ki lumia thaj si formato e dokumenturenqo kerdo katar o Adobe ko 1992 berś te prezentisarel dokumentură. Aspose.OCR Cloud SDK vaś o Python inklistil jekh but zurali funkcia vaś te lel pes o tèksto katar e PDF-esqe lila and-e Python-esqe aplikacie. Te areses i buti ano lokho drom trubul te thoves o PDF lil ko Aspose cloud storage thaj te keres o OCR pindžaripe ko uploadimo PDF lil. O egzàmplo so avel sikavel sar e softveresqe kerde śaj te len avri o tèksto katar jekh PDF-esqo lil labǎrindoj o Python-esqo kodo.

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)

Konvertisar o tèksto anθ-i vorba prekal o Python API

Aspose.OCR Cloud SDK vaś o Python del śajsaripen e softveresqe kerde te paruven o tèksto katar o lil bi te instalisaren varesavo softèro katar aver rig. Ko utiliziribe e API-esko, e programerura śaj te paruven e pinʒaripnasqe rezultatură anθ-o jekh naturalo manuśikano glaso savo śaj te avel baśaldo anθ-o fundo vaj te avel tele ćhudino. O angluno uźitori trubul te bićhalel o lil ko Aspose OCR Cloud server thaj te lel teksto kotar leste thaj palo odova te paruvel o teksto ki vorba kotar o Aspose OCR Cloud Text-to-Speech API. Palal i laćhi konverzia śaj te garaves o lil e lavǎqo anθ-o disko.

 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)