python、java 调用百度文字识别API_java 调研 python ocr

百度智能云文字识别-官网

使用百度智能云文字识别API的前提是，在百度智能云中创建文字识别应用。
创建成功后我们能获取该应用的 APP_ID、API_Key、Secret_Key

python部分

1.获取授权的access_token

import requests 
# client_id 为官网获取的AK， client_secret 为官网获取的SK
host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=PcPyC85uM6bcAbCbfMGvCvg3&client_secret=OyItsZFYxBb0GAMsO6Zp1FN3rIQn2zUS'
response = requests.get(host)
if response:
    print(response.json())
1
2
3
4
5
6

2.进行本地图片的识别

import requests
import base64
import ssl,sys
#使用	通用文字识别
url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic'
#url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/general'    高精度文字识别
 
data = {}  
data['access_token']='24.2289cc8cff01bb58216efc99016fc9d9.3592000.1575883789.282335-17732285'
            
            
#读取图片   
file=open('D:/test.png','rb')    
image= file.read()  
file.close()  
      
data['image'] = base64.b64encode(image)
headers={
    "Content-Type":"application/x-www-form-urlencoded",
    "apikey":"PcPyC85uM6bcAbCbfMGvCvg2" 
}
    
res = requests.post(url=url,headers=headers,data=data)
result = res.json() 
# print(result)
# 将图中所以文字输出
print(result['words_result'])
for word in result['words_result']:
    print(word['words'])
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

java部分

import com.baidu.aip.ocr.AipOcr;
import org.json.JSONArray;
import org.json.JSONException;
import org.json.JSONObject;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;

import javax.servlet.http.HttpServletRequest;
import java.io.File;
import java.io.IOException;
import java.util.HashMap;

@CrossOrigin
@ResponseBody
@RestController
@RequestMapping("/api/orc")
public class OrcController {

    @Value("${ORC_PATH}")
    private String ORCPATH;

    public static final String APP_ID = "17732275";
    public static final String API_KEY = "PcPyC85uM6bcAbCbfMGvDvg2";
    public static final String SECRET_KEY = "OyItsZFYxBb0GAMsO6Zp1FN3rIQn2zCS";

    private AipOcr client;

    public OrcController(){
        client = new AipOcr(APP_ID, API_KEY, SECRET_KEY);//类构造时，创建一个AipOcr单例
    }

    @RequestMapping(value = "/img/upload",method = RequestMethod.POST)
    public String[] ImgUpload(@RequestParam("files") MultipartFile[] files,
                             HttpServletRequest request){
        String[] result = new String[files.length];
        int c=0;
        for(MultipartFile file:files){
            File desFile = new File(ORCPATH+"/"+file.getOriginalFilename());
            if(!desFile.getParentFile().exists()){
                desFile.getParentFile().mkdirs();   //创建父级文件路径
            }
            try {
                file.transferTo(desFile);
            }catch (IllegalStateException | IOException e){
                e.printStackTrace();
            }

            JSONObject res = client.basicGeneral(desFile.getAbsolutePath(), new HashMap<String, String>());
            try {
            	//解析通用文字识别返回的数据
                JSONArray words_result = res.getJSONArray("words_result");
                String words ="";
                for (int i = 0; i < words_result.length(); i++) {
                    JSONObject jo = words_result.getJSONObject(i);
                    words += jo.getString("words");
                }
                result[c]=words;
            } catch (JSONException e) {
                e.printStackTrace();
            }
            c++;
        }
        return result;
    }
}

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