阿里云python通用文字OCR识别接口

概述

这里使用阿里云的OCR接口来使用文件中的文字，以下是代码示例，可以复制粘贴到文件使用。

阿里云的OCR接口有很多OCR类型的识别，包括通用识别、证件照等。

OCR识别类型：https://duguang.aliyun.com/

通用文字识别示例

"""
OCR 管理后台：https://ocr.console.aliyun.com/overview
OCR OpenAPI文档：https://api.aliyun.com/api-tools/sdk/ocr-api?language=python-tea
依赖: pip install alibabacloud_ocr_api20210707==2.0.1 alibabacloud_darabonba_stream
"""

import os
import sys

from typing import List

from alibabacloud_ocr_api20210707.client import Client as ocr_api20210707Client
from alibabacloud_tea_openapi import models as open_api_models
from alibabacloud_ocr_api20210707 import models as ocr_api_20210707_models
from alibabacloud_tea_util import models as util_models
from alibabacloud_tea_util.client import Client as UtilClient


class AliyunOCR:
    def __init__(self, access_key_id: str, access_key_secret: str):
        config = open_api_models.Config(
            # 必填，您的 AccessKey ID,
            access_key_id=access_key_id,
            # 必填，您的 AccessKey Secret,
            access_key_secret=access_key_secret
        )
        # Endpoint 请参考 https://api.aliyun.com/product/ocr-api
        config.endpoint = f'ocr-api.cn-hangzhou.aliyuncs.com'
        self.client: ocr_api20210707Client = ocr_api20210707Client(config)

    def get(self, type: str = 'General', file_url: str = None, file_stream=None, **kwargs):
        """
        参数:
            type (str): 识别类型，General Advanced
            file_url (str): 文件URL
            file_stream (str): 文件bytes流
        注意:
            file_url 与 file_stream 二选一
        """
        recognize_all_text_request = ocr_api_20210707_models.RecognizeAllTextRequest(
            type=type,
            body=file_stream,
            url=file_url,
            **kwargs
        )
        runtime = util_models.RuntimeOptions()
        try:
            return self.client.recognize_all_text_with_options(recognize_all_text_request, runtime)
        except Exception as error:
            # 如有需要，请打印 error
            print(error.message)

    def get_content_by_general(self, *args, **kwargs):
        """通用文字识别"""
        result = self.get(type='General', *args, **kwargs)
        content = result.body.data.content
        return content


class AutoOCR(AliyunOCR):
    """django自动导入key"""
    def __init__(self):
        from django.conf import settings
        super().__init__(
            settings.ALIBABA_CLOUD_ACCESS_KEY_ID,
            settings.ALIBABA_CLOUD_ACCESS_KEY_SECRET
        )


if __name__ == '__main__':
    # 加载Django环境
    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "conf.settings")
    import django
    django.setup()

    ocr = AutoOCR()
    file_url = 'https://www.example.com/123.pdf'  # 这里替换为真实测试的pdf文件路径
    result = ocr.get_content_by_general(file_url=file_url)
    print(result)