首页 > OCR > 通用OCR（高精版） API

通用OCR（高精版） API

通用OCR（高精版） API：通用文字识别可准确识别印刷体、手写体、艺术体识别，兼容中英文、繁体、日文，多种图片/PDF格式，自动方向矫正，接口稳定快速输出｜支持定制化开发，免费测试！

￥0.00 （50次）

价格：

更多价格，联系右下角"客服"

立即购买

请求信息
返回信息
示例代码

接口信息

请求URL：https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1

请求方式：POST

返回类型：JSON

接口参数

请求参数（Header）

方式一：简单认证

参数	类型	说明
Authorization	string	'APPCODE ' + 您的AppCode (注意英文空格)
Content-Type	string	application/json

方式二：签名认证

参数	类型	说明
Content-Type	string	application/json
x-ca-key	string	您的AppKey
x-ca-timestamp	string	时间戳（毫秒）
x-ca-signature	string	签名sign

str = app_key×tamp&app_secret

sign = md5(str)

请求参数（Query）

请求参数（Body）

参数	是否必填	类型	说明
file_base64	选填	string	base64编码的图片文件，file_base64与image_url必须传一个。像素范围：[15,8192]，小于20M
file_url	选填	string	图片文件url，file_base64与image_url必须传一个。像素范围：[15,8192]，小于20M
file_id	必填	string	文件id，异步获取结果时，传此值
mode	选填	string	同步："sync"，异步："async"，默认为同步
max_pages(私用)	选填	int	最多识别页数，不传默认识别所有页

平台通过已登录用户信息获取当前账号临时 Access Keys、"发起请求" 可能对当前账号发起线上资源操作，请小心操作

简单认证

签名认证

Python

PHP

Java

同步
异步
75 lines

                                                //main.java
import com.alibaba.fastjson2.JSON;
import com.alibaba.fastjson2.JSONObject;
import org.apache.http.HttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import org.apache.commons.io.FileUtils;
import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Base64;
                                                        
public class Main {
                                                
    public static String get_base64(String path) {
        String b64 = "";
        try {
            // 使用Commons IO简化文件读取
            byte[] content = FileUtils.readFileToByteArray(new File(path));
            // 使用JDK自带的Base64
            b64 = Base64.getEncoder().encodeToString(content);
        } catch (IOException e) {
            e.printStackTrace();
        }
        return b64;
    }
                                                
    public static void main(String[] args) {
        String url = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"; // 请求接口
        String appcode = "你的APPCODE";
        String imgFile = "本地图片路径";
                                                
        Map headers = new HashMap<>();
        headers.put("Authorization", "APPCODE " + appcode);
        headers.put("Content-Type", "application/json");
                                                   
        // 请求体
        JSONObject requestObj = new JSONObject();
        requestObj.put("image_base64", get_base64(imgFile));
        String bodys = requestObj.toString();
                                                
        try (CloseableHttpClient httpClient = HttpClients.createDefault()) {
            // 创建POST请求
            HttpPost httpPost = new HttpPost(url);
                                                            
            // 设置请求头
            for (Map.Entry entry : headers.entrySet()) {
                httpPost.addHeader(entry.getKey(), entry.getValue());
            }
                                                            
            // 设置请求体
            StringEntity entity = new StringEntity(bodys, "UTF-8");
            httpPost.setEntity(entity);
                                                            
            // 执行请求
            HttpResponse response = httpClient.execute(httpPost);
                                                            
            int stat = response.getStatusLine().getStatusCode();
            if (stat != 200) {
                System.out.println("Http code: " + stat);
                return;
            }
                                                
            String res = EntityUtils.toString(response.getEntity());
            JSONObject res_obj = JSON.parseObject(res);
                                                
            System.out.println(res_obj.toJSONString());
        } catch (Exception e) {
                e.printStackTrace();
        }
    }
}
                                                
                                            
44 lines

                                                //图片转base64
function get_base64($path){
    if($fp = fopen($path, "rb", 0)) {
        $binary = fread($fp, filesize($path)); // 文件读取
        fclose($fp);
        $b64 = base64_encode($binary); // 转base64
    }else{
        $b64="";
        printf("%s 文件不存在", $path);
    }
    return $b64;
}

$url = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1";
$appcode = "你的appcode";
$img_path = "图片路径";
$method = "POST";
    
//请求头
$headers = array();
array_push($headers, "Authorization:APPCODE " . $appcode);
array_push($headers, "Content-Type:application/json");
    
//请求体
$b64 = get_base64($img_path);
$data = array(
    "file_base64" => $b64
);
        $post_data = json_encode($data);
    
//请求
$curl = curl_init();
curl_setopt($curl, CURLOPT_CUSTOMREQUEST, $method);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, $headers);
curl_setopt($curl, CURLOPT_FAILONERROR, false);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_HEADER, true);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false);
curl_setopt($curl, CURLOPT_POSTFIELDS, $post_data);
    
$result = curl_exec($curl);
var_dump($result);
                                                    
                                                
                                            
36 lines

                                                # -*- coding: utf-8 -*-
import requests
import base64
import json

# 请求接口
URL = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"

# 图片/pdf文件转base64
def get_base64(file_path):
    with open(file_path, 'rb') as f:
        data = f.read()
    b64 = base64.b64encode(data).decode('utf8')
    return b64


def demo(appcode, file_path):
    # 请求头
    headers = {
        'Authorization': 'APPCODE %s' % appcode,
        'Content-Type': 'application/json'
    }

    # 请求体
    b64 = get_base64(file_path)
    data = {"file_base64": b64}

    # 请求
    response = requests.post(url=URL, headers=headers, json=data)
    content = json.loads(response.content)
    print(content)

if __name__=="__main__":
    appcode = "你的APPCODE"
    file_path = "本地图片路径"
    demo(appcode, file_path)         
                                                
                                            
异步调用示例

                                            # -*- coding: utf-8 -*-
import requests
import base64
import json
import time

# 请求接口
URL = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"

# 图片/pdf文件转base64
def get_base64(file_path):
    with open(file_path, 'rb') as f:
        data = f.read()
    b64 = base64.b64encode(data).decode('utf8')
    return b64

def demo(appcode, file_path):
    headers = {
        'Authorization': 'APPCODE %s' % appcode,
        'Content-Type': 'application/json'
    }
    b64 = get_base64(file_path)
    data = {
        "file_base64": b64,
        "mode": "async"
    }
    response = requests.post(url=URL, headers=headers, json=data)
    content = json.loads(response.content)
    print(content)
    success = content.get('success')
    file_id = content.get('file_id')
    if success:
        data = content.get('data')
        wait_time = data.get("wait_time")
        time.sleep(wait_time)
        while True:
            data = {"file_id": file_id}
            response = requests.post(url=URL, headers=headers, json=data)
            content = json.loads(response.content)
            data = content.get('data')
            status = data.get("status")
            wait_time = data.get("wait_time")
            if status == 2:
                print(data)
                break
            else:
                time.sleep(wait_time)
    else:
        msg = content.get('msg')
        print("msg:", msg)

if __name__=="__main__":
    appcode = "你的APPCODE"
    file_path = "本地文件路径"
    demo(appcode, file_path)
                                            
                                          
78 lines

                                                using System.Text;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;

namespace MyCSharpApp
{
    public class Program
    {
        public static string GetBase64(string path)
        {
            string b64 = "";
            try
            {
                // 读取文件内容
                byte[] content = File.ReadAllBytes(path);
                // 转换为Base64
                b64 = Convert.ToBase64String(content);
            }
            catch (Exception e)
            {
                Console.WriteLine(e.Message);
            }
            return b64;
        }
        public static async Task Main(string[] args)
        {
            string url = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"; // 请求接口
            string appcode = "你的APPCODE";
            string imgFile = "本地图片路径";

            // 设置请求头 
            Dictionary headers = new Dictionary
            {
                { "Authorization", "APPCODE " + appcode }
                // Content-Type 将在创建 StringContent 时设置
            };
            // 请求体
            JObject requestObj = new JObject();
            requestObj["file_base64"] = GetBase64(imgFile);
            string body = requestObj.ToString();

            try
            {
                using (HttpClient client = new HttpClient())
                {
                    // 设置请求头
                    foreach (var header in headers)
                    {
                        client.DefaultRequestHeaders.Add(header.Key, header.Value);
                    }

                    // 创建请求内容 
                    StringContent content = new StringContent(body, Encoding.UTF8, "application/json");
                    // 发送请求并获取响应
                    HttpResponseMessage response = await client.PostAsync(url, content);
                    if (!response.IsSuccessStatusCode)
                    {
                        Console.WriteLine($"Http code: {(int)response.StatusCode}");
                        return;
                    }
                    // 读取响应内容
                    string responseContent = await response.Content.ReadAsStringAsync();
                    JObject resObj = JObject.Parse(responseContent);
                    Console.WriteLine(resObj.ToString(Formatting.Indented));
                }
            }
            catch (Exception e)
            {
                Console.WriteLine(e.Message);
            }
        }
    }
}
         
                                                
                                            
48 lines

                                                import requests
import base64
import json
import hashlib
import time

# 请求接口
URL = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"

# 图片/pdf转base64
def get_base64(file_path):
    with open(file_path, 'rb') as f:
        data = f.read()
    b64 = base64.b64encode(data).decode('utf8')
    return b64

# md5
def md5(s):
    return hashlib.md5(s.encode("utf8")).hexdigest()


def demo(app_key, app_secret, file_path):
    # 请求头
    t = int(time.time() * 1000)
    s = "%s&%s&%s" % (app_key, t, app_secret)
    sign = md5(s)
    headers = {'x-ca-key': app_key,
            'x-ca-timestamp': t,
            'x-ca-signature': sign,
            "Content-Type": "application/json"}


    # 请求体
    b64 = get_base64(file_path)
    data = {"file_base64": b64}


    # 请求
    response = requests.post(url=URL, headers=headers, json=data)
    content = json.loads(response.content)
    print(content)

if __name__=="__main__":
    app_key = "你的APP_KEY"
    app_secret = "你的APP_SECRET"
    file_path = "本地图片路径"

    demo(app_key, app_secret, file_path)
                                                    
                                                
                                            
异步调用示例

                                            # -*- coding: utf-8 -*-
import requests
import base64
import json
import hashlib
import time

# 请求接口
URL = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"

# 图片/pdf转base64
def get_base64(file_path):
    with open(file_path, 'rb') as f:
        data = f.read()
    b64 = base64.b64encode(data).decode('utf8')
    return b64

def md5(s):
    return hashlib.md5(s.encode("utf8")).hexdigest()

def demo(app_key, app_secret, file_path):
    t = int(time.time() * 1000)
    s = "%s&%s&%s" % (app_key, t, app_secret)
    sign = md5(s)
    headers = {'x-ca-key': app_key,
            'x-ca-timestamp': t,
            'x-ca-signature': sign,
            "Content-Type": "application/json"}
    b64 = get_base64(file_path)
    data = {
        "file_base64": b64,
        "mode": "async"
    }
    response = requests.post(url=URL, headers=headers, json=data)
    content = json.loads(response.content)
    print(content)
    success = content.get('success')
    file_id = content.get('file_id')
    if success:
        data = content.get('data')
        wait_time = data.get("wait_time")
        time.sleep(wait_time)
        while True:
            data = {"file_id": file_id}
            response = requests.post(url=URL, headers=headers, json=data)
            content = json.loads(response.content)
            data = content.get('data')
            status = data.get("status")
            wait_time = data.get("wait_time")
            if status == 2:
                print(data)
                break
            else:
                time.sleep(wait_time)
    else:
        msg = content.get('msg')
        print("msg:", msg)

if __name__=="__main__":
    app_key = "你的APP_KEY"
    app_secret = "你的APP_SECRET"
    file_path = "本地文件路径"
    demo(app_key, app_secret, file_path)
                                            
                                          
113 lines

                                                import com.alibaba.fastjson2.JSON;
import com.alibaba.fastjson2.JSONObject;
import org.apache.commons.io.FileUtils;
import org.apache.http.HttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Base64;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;

public class Demo {

    public static String get_base64(String path) {
        String b64="";
        try {
            File file = new File(path);
            if (!file.exists()) {
                System.err.println("文件不存在: " + path);
                return b64;
            }
            // 使用Commons IO简化文件读取
            byte[] content = FileUtils.readFileToByteArray(file);
            // 使用JDK自带的Base64
            b64 = Base64.getEncoder().encodeToString(content);
        } catch (IOException e) {
            System.err.println("读取文件失败: " + e.getMessage());
            e.printStackTrace();
        }
        return b64;
    }

    public static String MD5(String input) {
        try {
            MessageDigest md = MessageDigest.getInstance("MD5");
            byte[] messageDigest = md.digest(input.getBytes());

            StringBuilder hexString = new StringBuilder();
            for (byte b : messageDigest) {
                String hex = Integer.toHexString(0xff & b);
                if (hex.length() == 1)
                    hexString.append('0');
                hexString.append(hex);
            }

            return hexString.toString();

        } catch (NoSuchAlgorithmException e) {
            e.printStackTrace();
        }

        return null;
    }

    public static void main(String[] args) {
        String url = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"; // 请求接口

        String imgFile = "本地图片路径";

        String app_key = "你的APPKEY";
        String app_secret = "你的APPSECRET";
        String timestamp = System.currentTimeMillis() + "";
        String sign = MD5(app_key + "&" + timestamp + "&" + app_secret);

        Map headers = new HashMap<>();
        headers.put("Content-Type", "application/json");
        headers.put("x-ca-key", app_key);
        headers.put("x-ca-timestamp", timestamp);
        headers.put("x-ca-signature", sign);

        // 请求体
        JSONObject requestObj = new JSONObject();
        requestObj.put("file_base64", get_base64(imgFile));
        String bodys = requestObj.toString();

        try (CloseableHttpClient httpClient = HttpClients.createDefault()) {
            // 创建POST请求
            HttpPost httpPost = new HttpPost(url);
            
            // 设置请求头
            for (Map.Entry entry : headers.entrySet()) {
                httpPost.addHeader(entry.getKey(), entry.getValue());
            }
            
            // 设置请求体
            StringEntity entity = new StringEntity(bodys, "UTF-8");
            httpPost.setEntity(entity);
            
            // 执行请求
            HttpResponse response = httpClient.execute(httpPost);
            
            int stat = response.getStatusLine().getStatusCode();
            if (stat != 200) {
                System.out.println("Http code: " + stat);
                System.out.println("Http  " + EntityUtils.toString(response.getEntity()));

                return;
            }

            String res = EntityUtils.toString(response.getEntity());
            JSONObject res_obj = JSON.parseObject(res);

            System.out.println(res_obj.toJSONString());
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}
                                                
                                            
111 lines

                                                using System.Security.Cryptography;
using System.Text;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;

namespace MyCSharpApp
{
    public class Program
    {
        public static string GetBase64(string path)
        {
            string b64 = "";
            try
            {
                // 读取文件内容
                byte[] content = File.ReadAllBytes(path);
                // 转换为Base64
                b64 = Convert.ToBase64String(content);
            }
            catch (Exception e)
            {
                Console.Error.WriteLine("读取文件失败: " + e.Message);
                Console.WriteLine(e.Message);
            }
            return b64;
        }

        public static string CalculateMD5(string input)
        {
            try
            {
                // 创建MD5哈希提供程序
                using (MD5 md5 = MD5.Create())
                {
                    // 计算输入字符串的哈希值
                    byte[] inputBytes = Encoding.UTF8.GetBytes(input);
                    byte[] hashBytes = md5.ComputeHash(inputBytes);

                            // 将字节数组转换为十六进制字符串
                            StringBuilder sb = new StringBuilder();
                            for (int i = 0; i < hashBytes.Length; i++)
                            {
                                sb.Append(hashBytes[i].ToString("x2"));
                            }
                            return sb.ToString();
                        }
                    }
                    catch (Exception e)
                    {
                        Console.WriteLine(e.Message);
                        return string.Empty; // 返回空字符串而不是null
                    }
                }

                public static async Task Main(string[] args)
                {
                    string url = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1"; // 请求接口
                    string imgFile = "本地图片路径";
                    string app_key = "你的APPKEY";
                    string app_secret = "你的APPSECRET";
                    string timestamp = DateTimeOffset.Now.ToUnixTimeMilliseconds().ToString();
                    string sign = CalculateMD5(app_key + "&" + timestamp + "&" + app_secret);

                    // 设置请求头
                    Dictionary headers = new Dictionary
                    {
                        { "x-ca-key", app_key },
                        { "x-ca-timestamp", timestamp },
                        { "x-ca-signature", sign }
                    };

                    // 请求体
                    JObject requestObj = new JObject();
                    requestObj["file_base64"] = GetBase64(imgFile);
                    string body = requestObj.ToString();
                    try
                    {
                        using (HttpClient client = new HttpClient())
                        {
                            // 设置请求头
                            foreach (var header in headers)
                            {
                                client.DefaultRequestHeaders.Add(header.Key, header.Value);
                            }

                            // 创建请求内容
                            StringContent content = new StringContent(body, Encoding.UTF8, "application/json");

                            // 发送请求并获取响应
                            HttpResponseMessage response = await client.PostAsync(url, content);

                            if (!response.IsSuccessStatusCode)
                            {
                                Console.WriteLine($"Http code: {(int)response.StatusCode}");
                                Console.WriteLine($"Http {await response.Content.ReadAsStringAsync()}");
                                return;
                            }

                            // 读取响应内容
                            string responseContent = await response.Content.ReadAsStringAsync();
                            JObject resObj = JObject.Parse(responseContent);

                            Console.WriteLine(resObj.ToString(Formatting.Indented));
                        }
                    }
                    catch (Exception e)
                    {
                        Console.WriteLine(e.Message);
                    }
                }
            }
        }
                                                
                                            
PHP签名认证示例

                                                //图片转base64
function get_base64($path){
    if($fp = fopen($path, "rb", 0)) {
        $binary = fread($fp, filesize($path)); // 文件读取
        fclose($fp);
        $b64 = base64_encode($binary); // 转base64
    }else{
        $b64="";
        printf("%s 文件不存在", $path);
    }
    return $b64;
}

$url = "https://ocr-api.shiliuai.com/api/advanced_general_ocr/v1";
$img_path = "图片路径";
$method = "POST";

//请求头
$app_key = "你的app_key";
$app_secret = "你的app_secret";
$timestamp = round(microtime(true) * 1000);
$sign_string = $app_key . "&" . $timestamp . "&" . $app_secret;
$sign = md5($sign_string);

$headers = array();
array_push($headers, "Content-Type:application/json");
array_push($headers, "x-ca-key:" . $app_key);
array_push($headers, "x-ca-timestamp:" . $timestamp);
array_push($headers, "x-ca-signature:" . $sign);

//请求体
$b64 = get_base64($img_path);
$data = array(
    "file_base64" => $b64
);
$post_data = json_encode($data);

//请求
$curl = curl_init();
curl_setopt($curl, CURLOPT_CUSTOMREQUEST, $method);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, $headers);
curl_setopt($curl, CURLOPT_FAILONERROR, false);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_HEADER, true);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false);
curl_setopt($curl, CURLOPT_POSTFIELDS, $post_data);

$result = curl_exec($curl);
var_dump($result);
                                                
                                            

返回信息

错误码说明

参数	参数类型	说明
code	int	错误码
msg	string	错误信息（英文）
msg_cn	string	错误信息（中文）
success	bool	识别是否成功
file_id	string	请求文件ID
request_id	string	唯一请求ID
data	data	具体看下面

data 成功示例：

data = {

"page_count": 5, // int, 文件页面总数

"process_pages": 3, // int, 处理页面数

"status": 2, // int, 处理状态，0: 已加入队列, 1: 正在处理中, 2: 已完成，同步时此值为2

"wait_time": 0.0 // float, 大概还需等待时间，同步时此值为0

// 如果status==2:

"pages": [

{

"width": 2000, // int, 页面宽度

"height": 2500, // int, 页面高度

"lines": [

{

"text": "你好", // string, 文字内容

"prob": 0.995, // float, [0, 1], 文字内容置信度

"keypoints": [[50, 20], [150, 20], [150, 60], [50, 60]] // list, [[xi, yi]], 文字区域角点位置，以左上角为起点，按顺时针排列

......

]

......,

]

}

data 失败示例：

'code': error code,

'msg': error message,

'msg_cn': 中文错误信息,

'success': False,

'file_id': file id,

'request_id': request id,

'data': {}

错误码	说明
200	成功
400	错误请求，比如参数错误
401	未经授权
500	内部错误

商品介绍

简介

通用(高精)OCR定义：通用文字识别可准确识别印刷体、手写体、艺术体识别，兼容中英文、繁体、日文，以及文字位置等信息，支持多种图片/PDF格式，自动方向矫正，接口稳定快速输出｜支持定制化开发，免费测试！

接入场景

支持各种程序和设备接入，包括小程序、APP、采集设备等，灵活适用于不同应用场景。

主要功能

高精OCR接口能够快速准确识别各种网络图片中的文字。其主要功能包括：

1.多类型覆盖：支持模糊、光照不均、透视畸变、复杂背景等低质量图像识别。

2.实时性高：提供弹性伸缩的低延时服务。

3.服务稳定：提供弹性服务，扩展性好，算法持续的迭代优化对用户稳定性无影响。

4.超高精度及性能：识别准确率高，识别速度快，响应及时。

商品价格

API类型	价格说明
通用(高精)OCR API	每页调用消耗一积分
如有问题联系右侧"客服"