「这是我参与11月更文挑战的第2天，活动详情查看：2021最后一次更文挑战」。
1 创建百度应用
1、在浏览器输入网址login.bce.baidu.com/或者百度搜索‘百度ai’点击第一个。点击主页的产品服务，看到文字识别。如下图所示：
2、点击创建应用 创建完应用后，才能获取百度AI的授权 3、创建完成后可查看相应API key和Secret Key
2 查看sdk文档
点击文字识别下面的技术文档cloud.baidu.com/doc/OCR/ind…，如图
可以根据官方提供的文档进行图文识别，下面博主为大家提供了java的工具类
3 java调用图文识别的工具类
3.1 获取access_token
import org.json.JSONObject;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
/**
* 获取token类
* https://github.com/ourlang
* @author 福小林
*/
public class AuthService {
/**
* 获取权限token
* @return 返回示例：
* {
* "access_token": "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567",
* "expires_in": 2592000
* }
*/
public static String getAuth() {
// 官网获取的API Key 更新为你注册的
String clientId = "sZoHMGl0jo1pSXQ1SeWiG8kv";
// 官网获取的 Secret Key 更新为你注册的
String clientSecret = "FPRCv0tbhoEXjDD6Gj7XWLhg64EqAelo";
return getAuth(clientId, clientSecret);
}
/**
* 获取API访问token
* 该token有一定的有效期，需要自行管理，当失效时需重新获取.
* @param ak - 百度云官网获取的 API Key
* @param sk - 百度云官网获取的 Securet Key
* @return assess_token 示例：
* "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567"
*/
private static String getAuth(String ak, String sk) {
// 获取token地址
String authHost = "https://aip.baidubce.com/oauth/2.0/token?";
String getAccessTokenUrl = authHost
// 1. grant_type为固定参数
+ "grant_type=client_credentials"
// 2. 官网获取的 API Key
+ "&client_id=" + ak
// 3. 官网获取的 Secret Key
+ "&client_secret=" + sk;
try {
URL realUrl = new URL(getAccessTokenUrl);
// 打开和URL之间的连接
HttpURLConnection connection = (HttpURLConnection) realUrl.openConnection();
connection.setRequestMethod("GET");
connection.connect();
// 定义 BufferedReader输入流来读取URL的响应
BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
StringBuilder result = new StringBuilder();
String line;
while ((line = in.readLine()) != null) {
result.append(line);
}
JSONObject jsonObject = new JSONObject(result.toString());
return jsonObject.getString("access_token");
} catch (Exception e) {
//打印错误日志
e.printStackTrace(System.err);
}
return null;
}
}
3.2 调用服务测试
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URLEncoder;
/**
* 图像文字识别公用接口类
* https://github.com/ourlang
* @author 福小林
*/
public class ImageTextUtil {
/**
* 调用百度的图文识别接口
*/
private static final String POST_URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic?access_token=" + AuthService.getAuth();
private static final String BASE64_START_MARK = "data:image/png;base64,";
/**
* 根据图片的base64编码实现图文识别功能
*
* @param imgStr base64图片字符串
* @return 识别结果，为json格式
* @throws URISyntaxException URI打开异常
* @throws IOException io流异常
*/
public static String getTextByBase64(String imgStr) throws URISyntaxException, IOException {
StringBuilder sb = new StringBuilder();
if (imgStr.startsWith(BASE64_START_MARK)){
imgStr=imgStr.substring(22);
}
String[] strings = splitStringByLength(imgStr, 1000);
for (String tempStr : strings) {
sb.append(tempStr);
}
String s = encodeUriComponent(sb.toString());
String param = "image=" + s;
return post(param);
}
/**
* @param url 图片url http地址
* @return 识别结果，为json格式
*/
public static String getTextByUrl(String url) throws IOException, URISyntaxException {
String param = "url=" + url;
return post(param);
}
/***
* 将字符串按固定长度切割成字符子串
* @param src 需要切割的字符串
* @param length 字符子串的长度
* @return 字符子串数组
*/
public static String[] splitStringByLength(String src, int length) {
//检查参数是否合法
if (null == src || src.isEmpty()) {
System.out.println("the string is null");
return null;
}
if (length <= 0) {
System.out.println("the length < 0");
return null;
}
//获取整个字符串可以被切割成字符子串的个数
int n = (src.length() + length - 1) / length;
String[] split = new String[n];
for (int i = 0; i < n; i++) {
if (i < (n - 1)) {
split[i] = src.substring(i * length, (i + 1) * length);
} else {
split[i] = src.substring(i * length);
}
}
return split;
}
/**
* 通过传递参数：url和image进行文字识别
*
* @param param 区分是url还是image识别
* @return 识别结果
* @throws URISyntaxException URI打开异常
* @throws IOException IO流异常
*/
private static String post(String param) throws URISyntaxException, IOException {
//开始搭建post请求
HttpClient httpClient = new DefaultHttpClient();
HttpPost post = new HttpPost();
URI url = new URI(POST_URL);
post.setURI(url);
//设置请求头，请求头必须为application/x-www-form-urlencoded，因为是传递一个很长的字符串，不能分段发送
post.setHeader("Content-Type", "application/x-www-form-urlencoded");
StringEntity entity = new StringEntity(param);
post.setEntity(entity);
HttpResponse response = httpClient.execute(post);
if (response.getStatusLine().getStatusCode() == 200) {
String str;
try {
//读取服务器返回过来的json字符串数据
str = EntityUtils.toString(response.getEntity());
return str;
} catch (Exception e) {
e.printStackTrace();
return null;
}
}
return null;
}
/**
* 返回编码后的字符串
*
* @param s 要编码的字符串
* @return 编码好的字符串
*/
public static String encodeUriComponent(String s) {
String result;
try {
result = URLEncoder.encode(s, "UTF-8")
.replaceAll("\\+", "%20")
.replaceAll("\\%21", "!")
.replaceAll("\\%27", "'")
.replaceAll("\\%28", "(")
.replaceAll("\\%29", ")")
.replaceAll("\\%7E", "~");
}
// This exception should never occur.
catch (UnsupportedEncodingException e) {
result = s;
}
return result;
}
public static void main(String[] args) {
try {
String textByUrl = getTextByUrl("http://lsdcloud.com/img/goImage/file.png");
System.out.println(textByUrl);
} catch (URISyntaxException | IOException e) {
e.printStackTrace();
}
}
}
3.3.输出结果如下
