把图片转化为文本的格式

这个识别还是很准的，可以直接调用的，下次有时间写一个调用接口的

'''
    百度图片文字识别接口封装
'''

import base64

from .httplib import HEADERS, retry_get, retry_post


class GeneralOcr(object):
    '''百度云通用文字识别'''

    __client_id = 'z9ILc5DopWA5rm4NuAou64GY'
    __client_secret = 'fAHDaKibDPPN8G80qTTZXxjcBA6yHYUs'

    def __init__(self, client_id=None, client_secret=None, access_token=None):
        self.client_id = client_id or self.__client_id
        self.client_secret = client_id or self.__client_secret
        self.access_token = access_token or self.oauth()

    @classmethod
    def oauth(cls, client_id=None, client_secret=None):
        client_id = client_id or cls.__client_id
        client_secret = client_secret or cls.__client_secret
        oauth_url = f'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={client_id}&client_secret={client_secret}'
        oauth_data = retry_get(oauth_url).json()
        return oauth_data['access_token']

    def basic_general(self, image):
        general = f"https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic?access_token={self.access_token}"
        data = {'image': base64.b64encode(image)}
        HEADERS['Content-Type'] = 'application/x-www-form-urlencoded'
        resp = retry_post(general, data=data, headers=HEADERS)
        return resp.json() if resp else ({'words_result': '请求错误'})

    # 在确定某链接是图片的情况下可设置 `certain=True`
    def basic_ocr(self, addr, sep='\n', certain=False):
        if addr.startswith('http'):
            if certain or addr.endswith('png') or addr.endswith('jpg'):
                resp = retry_get(addr)
                image = resp.content if resp else b''
            else:
                raise Exception("The link doesn't have a suffix, make sure it's a image.")
        else:
            with open(addr, 'rb') as fp:
                image = fp.read()
        _wds = self.basic_general(image).get('words_result', tuple())
        wds = ''
        for _wd in _wds:
            wds += _wd.get('words', '') + sep
        return wds

当我们写的时候引入这个类就行

            #这里的src就是图片的链接
            from renderer.utils import GeneralOcr
            ocr = GeneralOcr()
            annex_url = response.urljoin(src)
            response.string = ocr.basic_ocr(annex_url, sep='', certain=True)
			#ocr = GeneralOcr().basic_ocr('图片链接', sep='', certain=True)

这里就可以直接打印了，然后拿到自己想要的内容，这个方法内置的，可以去调用