1# 试卷分析与识别
2curl -i -k 'https://aip.baidubce.com/rest/2.0/ocr/v1/doc_analysis?access_token=【调用鉴权接口获取的token】' --data 'language_type=CHN_ENG&result_type=big&image=【图片Base64编码，需UrlEncode】' -H 'Content-Type:application/x-www-form-urlencoded'

1# encoding:utf-8
2
3import requests
4import base64
5
6'''
7试卷分析与识别
8'''
9
10request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/doc_analysis"
11# 二进制方式打开图片文件
12f = open('[本地文件]', 'rb')
13img = base64.b64encode(f.read())
14
15params = {"image":img,"language_type":"CHN_ENG","result_type":"big"}
16access_token = '[调用鉴权接口获取的token]'
17request_url = request_url + "?access_token=" + access_token
18headers = {'content-type': 'application/x-www-form-urlencoded'}
19response = requests.post(request_url, data=params, headers=headers)
20if response:
21    print (response.json())

1package com.baidu.ai.aip;
2
3import com.baidu.ai.aip.utils.Base64Util;
4import com.baidu.ai.aip.utils.FileUtil;
5import com.baidu.ai.aip.utils.HttpUtil;
6
7import java.net.URLEncoder;
8
9/**
10* 文档版面分析与识别
11*/
12public class DocAnalysis {
13
14    /**
15    * 重要提示代码中所需工具类
16    * FileUtil,Base64Util,HttpUtil,GsonUtils请从
17    * https://ai.baidu.com/file/658A35ABAB2D404FBF903F64D47C1F72
18    * https://ai.baidu.com/file/C8D81F3301E24D2892968F09AE1AD6E2
19    * https://ai.baidu.com/file/544D677F5D4E4F17B4122FBD60DB82B3
20    * https://ai.baidu.com/file/470B3ACCA3FE43788B5A963BF0B625F3
21    * 下载
22    */
23    public static String docAnalysis() {
24        // 请求url
25        String url = "https://aip.baidubce.com/rest/2.0/ocr/v1/doc_analysis";
26        try {
27            // 本地文件路径
28            String filePath = "[本地文件路径]";
29            byte[] imgData = FileUtil.readFileByBytes(filePath);
30            String imgStr = Base64Util.encode(imgData);
31            String imgParam = URLEncoder.encode(imgStr, "UTF-8");
32
33            String param = "language_type=" + "CHN_ENG" + "&result_type=" + "big" + "&image=" + imgParam;
34
35            // 注意这里仅为了简化编码每一次请求都去获取access_token，线上环境access_token有过期时间， 客户端可自行缓存，过期后重新获取。
36            String accessToken = "[调用鉴权接口获取的token]";
37
38            String result = HttpUtil.post(url, accessToken, param);
39            System.out.println(result);
40            return result;
41        } catch (Exception e) {
42            e.printStackTrace();
43        }
44        return null;
45    }
46
47    public static void main(String[] args) {
48        DocAnalysis.docAnalysis();
49    }
50}

1#include <iostream>
2#include <curl/curl.h>
3
4// libcurl库下载链接：https://curl.haxx.se/download.html
5// jsoncpp库下载链接：https://github.com/open-source-parsers/jsoncpp/
6const static std::string request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/doc_analysis";
7static std::string docAnalysis_result;
8/**
9 * curl发送http请求调用的回调函数，回调函数中对返回的json格式的body进行了解析，解析结果储存在全局的静态变量当中
10 * @param 参数定义见libcurl文档
11 * @return 返回值定义见libcurl文档
12 */
13static size_t callback(void *ptr, size_t size, size_t nmemb, void *stream) {
14    // 获取到的body存放在ptr中，先将其转换为string格式
15    docAnalysis_result = std::string((char *) ptr, size * nmemb);
16    return size * nmemb;
17}
18/**
19 * 文档版面分析与识别
20 * @return 调用成功返回0，发生错误返回其他错误码
21 */
22int docAnalysis(std::string &json_result, const std::string &access_token) {
23    std::string url = request_url + "?access_token=" + access_token;
24    CURL *curl = NULL;
25    CURLcode result_code;
26    int is_success;
27    curl = curl_easy_init();
28    if (curl) {
29        curl_easy_setopt(curl, CURLOPT_URL, url.data());
30        curl_easy_setopt(curl, CURLOPT_POST, 1);
31        curl_httppost *post = NULL;
32        curl_httppost *last = NULL;
33        curl_formadd(&post, &last, CURLFORM_COPYNAME, "language_type", CURLFORM_COPYCONTENTS, "CHN_ENG", CURLFORM_END);
34        curl_formadd(&post, &last, CURLFORM_COPYNAME, "result_type", CURLFORM_COPYCONTENTS, "big", CURLFORM_END);
35        curl_formadd(&post, &last, CURLFORM_COPYNAME, "image", CURLFORM_COPYCONTENTS, "【base64_img】", CURLFORM_END);
36
37        curl_easy_setopt(curl, CURLOPT_HTTPPOST, post);
38        curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, callback);
39        result_code = curl_easy_perform(curl);
40        if (result_code != CURLE_OK) {
41            fprintf(stderr, "curl_easy_perform() failed: %s\n",
42                    curl_easy_strerror(result_code));
43            is_success = 1;
44            return is_success;
45        }
46        json_result = docAnalysis_result;
47        curl_easy_cleanup(curl);
48        is_success = 0;
49    } else {
50        fprintf(stderr, "curl_easy_init() failed.");
51        is_success = 1;
52    }
53    return is_success;
54}

1<?php
2/**
3 * 发起http post请求(REST API), 并获取REST请求的结果
4 * @param string $url
5 * @param string $param
6 * @return - http response body if succeeds, else false.
7 */
8function request_post($url = '', $param = '')
9{
10    if (empty($url) || empty($param)) {
11        return false;
12    }
13
14    $postUrl = $url;
15    $curlPost = $param;
16    // 初始化curl
17    $curl = curl_init();
18    curl_setopt($curl, CURLOPT_URL, $postUrl);
19    curl_setopt($curl, CURLOPT_HEADER, 0);
20    // 要求结果为字符串且输出到屏幕上
21    curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
22    curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
23    // post提交方式
24    curl_setopt($curl, CURLOPT_POST, 1);
25    curl_setopt($curl, CURLOPT_POSTFIELDS, $curlPost);
26    // 运行curl
27    $data = curl_exec($curl);
28    curl_close($curl);
29
30    return $data;
31}
32
33$token = '[调用鉴权接口获取的token]';
34$url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/doc_analysis?access_token=' . $token;
35$img = file_get_contents('[本地文件路径]');
36$img = base64_encode($img);
37$bodys = array(
38    'language_type' => "CHN_ENG",
39    'result_type' => "big",
40    'image' => $img
41);
42$res = request_post($url, $bodys);
43
44var_dump($res);

1using System;
2using System.IO;
3using System.Net;
4using System.Text;
5using System.Web;
6
7namespace com.baidu.ai
8{
9    public class DocAnalysis
10    {
11        // 文档版面分析与识别
12        public static string docAnalysis()
13        {
14            string token = "[调用鉴权接口获取的token]";
15            string host = "https://aip.baidubce.com/rest/2.0/ocr/v1/doc_analysis?access_token=" + token;
16            Encoding encoding = Encoding.Default;
17            HttpWebRequest request = (HttpWebRequest)WebRequest.Create(host);
18            request.Method = "post";
19            request.KeepAlive = true;
20            // 图片的base64编码
21            string base64 = getFileBase64("[本地图片文件]");
22            String str = "language_type=" + "CHN_ENG" + "&result_type=" + "big" + "&image=" + HttpUtility.UrlEncode(base64);
23            byte[] buffer = encoding.GetBytes(str);
24            request.ContentLength = buffer.Length;
25            request.GetRequestStream().Write(buffer, 0, buffer.Length);
26            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
27            StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.Default);
28            string result = reader.ReadToEnd();
29            Console.WriteLine("文档版面分析与识别:");
30            Console.WriteLine(result);
31            return result;
32        }
33
34        public static String getFileBase64(String fileName) {
35            FileStream filestream = new FileStream(fileName, FileMode.Open);
36            byte[] arr = new byte[filestream.Length];
37            filestream.Read(arr, 0, (int)filestream.Length);
38            string baser64 = Convert.ToBase64String(arr);
39            filestream.Close();
40            return baser64;
41        }
42    }
43}