腾讯文字批量识别

发表于 更新于 分类于 ， 阅读次数： Waline： 阅读次数： 本文字数： 2.8k 阅读时长 ≈ 6 分钟
利用Python和腾讯接口进行文字批量识别
1
腾讯文字批量识别
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2020-10-13 12:22:35
# @Author  : Your Name (you@example.org)
# @Link    : http://example.org
# @Version : $Id$

import json
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.ocr.v20181119 import ocr_client, models
import base64
import os
import time

"""
参考资料：
 API 中心: 
 https://cloud.tencent.com/document/api/866/33517
 API Explorer:
 https://console.cloud.tencent.com/api/explorer?Product=ocr&Version=2018-11-19&Action=GeneralBasicOCR&SignVersion=
"""

#获取开始时间
start = time.time()

def get_file_content(filePath):
    print(filePath)
    with open(filePath, 'rb') as fp:
        return fp.read()

def write_on_txt(content,filePath,linefeed = "1"):
    """
    content：要写入的内容
    filePath：要写入文件的路径
    linefeed ：判断是否换行
        - 1 为不换行 
        - 其他 为换行
    """
    #只需要将之前的”w"改为“a"即可，代表追加内容
    with open(filePath,"a") as file:
        try:
            file.write(content)
        except:
            print("写入错误")
        else:
            if linefeed != "1":
                file.write("\n")
#图片路径
image_path = r"G:\Pictures\jy\test" # 或者"G:/Pictures/jy"格式
#文本路径
txt_path = r"G:\Pictures\jy\OCR\图片.txt"

for root,dirs,files in os.walk(image_path):
    for file in files:
        # 使用join函数将文件名称和文件所在根目录连接起来
        file_dir = os.path.join(root, file)
        print(file_dir)
        write_on_txt("=============================",txt_path,"0")
        write_on_txt("文件名:"+ file_dir,txt_path,"0")

        try:
            cred = credential.Credential("腾讯 api 的 id", "腾讯 api 的秘钥")  
            httpProfile = HttpProfile()
            httpProfile.endpoint = "ocr.ap-chengdu.tencentcloudapi.com"  #就近地域接入（推荐，只支持非金融区），
                                                              #其他格式：西南地区(成都)    ocr.ap-chengdu.tencentcloudapi.com

            clientProfile = ClientProfile()
            clientProfile.httpProfile = httpProfile
            client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile) #地域参数，用来标识希望操作哪个地域的数据

            with open(file_dir, 'rb') as f:  # 以二进制读取本地图片
                data = f.read()
                encodestr = str(base64.b64encode(data), 'utf-8')  # base64编码图片 
                params = {
                "ImageBase64": encodestr,
                "LanguageType": "auto"
                }

            req = models.GeneralBasicOCRRequest()  # 通用高精度：GeneralAccurateOCR；
                                                      # 手写识别：GeneralHandwritingOCRRequest()
            req.from_json_string(json.dumps(params))

            resp = client.GeneralBasicOCR(req) 
            print()
            for text in resp.TextDetections: # 输出文字
                print(text.DetectedText)
                write_on_txt(text.DetectedText,txt_path,"0")    
        except TencentCloudSDKException as err: 
            print(err) 
end = time.time()
print('Running time: %1.2f Seconds'%(end-start))

相关文章