百度智能云-人工智能-通用文字识别OCR

# encoding:utf-8

import requests
import base64
import json

'''
通用文字识别
'''

request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic"
# 二进制方式打开图片文件
#f = open('/home/cnliutz/微21.jpg', 'rb') 要识别的图片放这里。
f = open('/home/cnliutz/微信图片_20200724140210.jpg', 'rb')
img = base64.b64encode(f.read())

params = {"image":img}
access_token = '24.d4c2ebf5af97dd3dde655eabf3a22e2f.2592000.1598160343.282335-215715one.seven'  #生成的签名 利用百度智能云-文字识别-技术文档里的方法产生。
request_url = request_url + "?access_token=" + access_token
headers = {'content-type': 'application/x-www-form-urlencoded'}
response = requests.post(request_url, data=params, headers=headers)
if response:
    print (response.json())
results=response.json()
with open('shibiejieguo.txt',"w",encoding="utf-8") as f:
    for i in results['words_result']:
        f.write(i["words"]+"\n")

注意修改access_token内容，否则无法使用呢
参考网址：https://cloud.baidu.com/doc/OCR/s/dk3iqnq51
【只要10分钟 快速掌握文字识别】 教程
参考网址：https://ai.baidu.com/forum/topic/show/867951

#文字识别另一种调用方法
# coding=utf-8

import sys
import json
import base64


# 保证兼容python2以及python3
IS_PY3 = sys.version_info.major == 3
if IS_PY3:
    from urllib.request import urlopen
    from urllib.request import Request
    from urllib.error import URLError
    from urllib.parse import urlencode
    from urllib.parse import quote_plus
else:
    import urllib2
    from urllib import quote_plus
    from urllib2 import urlopen
    from urllib2 import Request
    from urllib2 import URLError
    from urllib import urlencode
# 防止https证书校验不正确
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
API_KEY = 'dGgWcprUfQBHKM5UG2CdSzot'
SECRET_KEY = '3Gqe5MkzUdONgtppDceUutRGdpF7MVkU'
OCR_URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic"
"""  TOKEN start """
TOKEN_URL = 'https://aip.baidubce.com/oauth/2.0/token'
"""
    获取token
"""
def fetch_token():
    params = {'grant_type': 'client_credentials',
              'client_id': API_KEY,
              'client_secret': SECRET_KEY}
    post_data = urlencode(params)
    if (IS_PY3):
        post_data = post_data.encode('utf-8')
    req = Request(TOKEN_URL, post_data)
    try:
        f = urlopen(req, timeout=5)
        result_str = f.read()
    except URLError as err:
        print(err)
    if (IS_PY3):
        result_str = result_str.decode()

    result = json.loads(result_str)

    if ('access_token' in result.keys() and 'scope' in result.keys()):
        if not 'brain_all_scope' in result['scope'].split(' '):
            print ('please ensure has check the  ability')
            exit()
        return result['access_token']
    else:
        print ('please overwrite the correct API_KEY and SECRET_KEY')
        exit()
"""
    读取文件
"""
def read_file(image_path):
    f = None
    try:
        f = open(image_path, 'rb')
        return f.read()
    except:
        print('read image file fail')
        return None
    finally:
        if f:
            f.close()

"""
    调用远程服务
"""
def request(url, data):
    req = Request(url, data.encode('utf-8'))
    has_error = False
    try:
        f = urlopen(req)
        result_str = f.read()
        if (IS_PY3):
            result_str = result_str.decode()
        return result_str
    except  URLError as err:
        print(err)

if __name__ == '__main__':
    # 获取access token
    token = fetch_token()

    # 拼接通用文字识别高精度url
    image_url = OCR_URL + "?access_token=" + token

    text = ""

    # 读取书籍页面图片
    file_content = read_file('/home/cnliutz/微21.jpg')

    # 调用文字识别服务
    result = request(image_url, urlencode({'image': base64.b64encode(file_content)}))

    # 解析返回结果
    result_json = json.loads(result)
    with open('shibiejieguo.txt',"a",encoding="utf-8") as f:
        for words_result in result_json["words_result"]:
            text = text + words_result["words"]
            f.write(words_result["words"])

    # 打印文字
    print(text)