首页 > OCR > 表格OCR API

表格OCR识别API接口

表格OCR（API）定义：支持有线表格、条纹表格、无线表格、手写表格识别，支持置信度对比并标红，支持多类型覆盖，精准识别表格上所包含的文字信息并输出，支持html、json、xlxs等输出格式。

￥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：http(s)://ocr-api.shiliuai.com/api/table_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
Content-type	string	application/json
Authorization	string	'APPCODE ' + 您的AppCode (注意英文空格)

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

注：签名方法

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
image_base64	必填	string	base64编码的图片文件,像素范围：[15,8192]，小于20M
format	选填	string	输出格式，可选："dict"/"json"/"html"/"xlsx"，默认为"dict"

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

75 lines

                                                            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/table_ocr/v1";
                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");

                JSONObject requestObj = new JSONObject();
                requestObj.put("image_base64", get_base64(imgFile));
                String bodys = requestObj.toString();

                try (CloseableHttpClient httpClient = HttpClients.createDefault()) {
                    HttpPost httpPost = new HttpPost(url);
            
                    for (Map.Entry entry : headers.entrySet()) {
                        httpPost.addHeader(entry.getKey(), entry.getValue());
                    }
            
                    StringEntity entity = new StringEntity(bodys, "UTF-8");
                    httpPost.setEntity(entity);
            
                    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/table_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(
            "image_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/table_ocr/v1"
        
        # 图片转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 = {"image_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)         
                                                    
                                                
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/table_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["image_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/table_ocr/v1"
        
        # 图片转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%d%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 = {"image_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)
                                                        
                                                    
                                                
53 lines

                                                            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/table_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";
        $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(
            "image_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);
                                                    
                                                    
                                                
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;
                    }
                    byte[] content = FileUtils.readFileToByteArray(file);
                    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/table_ocr/v1";
                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);

                JSONObject requestObj = new JSONObject();
                requestObj.put("image_base64", get_base64(imgFile));
                String bodys = requestObj.toString();

                try (CloseableHttpClient httpClient = HttpClients.createDefault()) {
                    HttpPost httpPost = new HttpPost(url);
            
                    for (Map.Entry entry : headers.entrySet()) {
                        httpPost.addHeader(entry.getKey(), entry.getValue());
                    }
            
                    StringEntity entity = new StringEntity(bodys, "UTF-8");
                    httpPost.setEntity(entity);
            
                    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/table_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["image_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);
                    }
                }
            }
        }
                                                    
                                                

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
image_id	string	图片请求ID
request_id	string	唯一请求ID
data	data	具体看下面

data 成功示例：

data = { # 以format="dict"为例

"tables": # 没有内容时为[]

[

{

"ex":1, #one past end column index(单元格所占的列数(colspan)为ex - sx)

"ey":1, #one past end row index(单元格所占的行数(rowspan)为ey - sy)

"height":96, #cell height,图片上单元格的高度

"sx":0, #start from column(单元格的起始列id)

"sy":0, #start row(单元格的起始行id)

"width":573 #cell width，图片上单元格的宽度

"text":["某某某"] #单元格文字

{

"text":["某某某"] #文本

"type":"reference" # 文本类型，包含equation/reference/header/footer/text/title/

# figure/figure_caption/table_caption

......

]

}

data 失败示例：

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
403	禁止访问
429	请求过多
500	内部错误
604	接口停用
1001	服务异常，返回具体的错误原因

商品介绍

简介

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

表格OCR接口能够根据指定的要求返回识别出的文字。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OCR API	每次调用消耗一积分
如有问题联系右侧“客服”