文章目录

• 1 方法一
• • 1.1 新建HttpUtils，用来发送post请求
  • 1.2 获取 access token
  • 1.3 获取图片的文字信息
  • 1.4 测试
  • 1.5 结果
• 2 方法二使用jsoup
• • 2.1 获取 access token
  • 2.2 获取图片的文字信息
  • 2.3 测试

1 方法一

• 依赖

		com.alibaba.fastjson2fastjson22.0.16

1.1 新建HttpUtils，用来发送post请求

package com.xinglong.spider.util;import org.slf4j.Logger;
import org.slf4j.LoggerFactory;import java.io.*;
import java.net.ConnectException;
import java.net.SocketTimeoutException;
import java.net.URL;
import java.net.URLConnection;
import java.nio.charset.StandardCharsets;/*** @Author：胡云峰* @Date：2022/12/7 10:43*/
public class HttpUtils {private static final Logger log = LoggerFactory.getLogger(HttpUtils.class);/*** 向指定 URL 发送POST方法的请求** @param url 发送请求的 URL* @param param 请求参数，请求参数应该是 name1=value1&name2=value2 的形式。* @return 所代表远程资源的响应结果*/public static String sendPost(String url, String param,String contentType){PrintWriter out = null;BufferedReader in = null;StringBuilder result = new StringBuilder();try{log.info("sendPost - {}", url);URL realUrl = new URL(url);URLConnection conn = realUrl.openConnection();conn.setRequestProperty("accept", "*/*");conn.setRequestProperty("connection", "Keep-Alive");conn.setRequestProperty("user-agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");conn.setRequestProperty("Accept-Charset", "utf-8");conn.setRequestProperty("content-type", contentType);conn.setDoOutput(true);conn.setDoInput(true);out = new PrintWriter(conn.getOutputStream(),true);out.print(param);out.flush();in = new BufferedReader(new InputStreamReader(conn.getInputStream(), StandardCharsets.UTF_8));String line;while ((line = in.readLine()) != null){result.append(line);}log.info("recv - {}", result);}catch (ConnectException e){log.error("调用HttpUtils.sendPost ConnectException, url=" + url + ",param=" + param, e);}catch (SocketTimeoutException e){log.error("调用HttpUtils.sendPost SocketTimeoutException, url=" + url + ",param=" + param, e);}catch (IOException e){log.error("调用HttpUtils.sendPost IOException, url=" + url + ",param=" + param, e);}catch (Exception e){log.error("调用HttpsUtil.sendPost Exception, url=" + url + ",param=" + param, e);}finally{try{if (out != null){out.close();}if (in != null){in.close();}}catch (IOException ex){log.error("调用in.close Exception, url=" + url + ",param=" + param, ex);}}return result.toString();}
}

1.2 获取 access token

/*** @ author 胡云峰* 获取   access token* 注意： access_token的有效期为30天，需要每30天进行定期更换；*/public static String getAccessToken(){//向https://aip.baidubce.com/oauth/2.0/token发送请求String url = "https://aip.baidubce.com/oauth/2.0/token";//设置contentType格式String contentType = "application/x-www-form-urlencoded";// 固定值为client_credentialsString grant_type = "client_credentials";//应用的 API Key  这里使用自己的String client_id = "***********";//应用的 Secret Key  这里使用自己的String client_secret = "************";//参数String para = "grant_type="+grant_type+"&client_id="+client_id+"&client_secret=" + client_secret;//发起post请求String resp = HttpUtils.sendPost(url, para, contentType);//解析返回信息获取access_tokenJSONObject jsonObject = JSONObject.parseObject(resp);return jsonObject.get("access_token").toString();}

1.3 获取图片的文字信息

/*** 获取图片文字信息* @return*/public static String getOcrMessage(){String url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic" + "?access_token=" +getAccessToken();//设置contentType格式String contentType = "application/x-www-form-urlencoded";//image base64 //请求格式支持：PNG、JPG、JPEG、BMP、TIFF、PNM、WebPString imgStr = "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";//注意：一定要urlencoder，否则会出现图片格式不对的报错try {//使用Postman工具或 Python、PHP 等请求库会自动进行urlencode，无需自行处理imgStr = URLEncoder.encode(imgStr, "UTF-8");} catch (UnsupportedEncodingException e) {e.printStackTrace();}//发起请求String resp = HttpUtils.sendPost(url, "image=" + imgStr, contentType);//利用阿里的fastjson解析JSONObject jsonObject = JSONObject.parseObject(resp);String wordsResult = jsonObject.get("words_result").toString();//words_result是一个集合JSONArray jsonArray = JSONArray.parseArray(wordsResult);//组装解析后的结果StringBuilder sb = new StringBuilder();for (Object o : jsonArray) {//Object强转成JSONObjectJSONObject jObject = (JSONObject) o;//解析wordsString words = jObject.get("words").toString();//组装到sbsb.append(words);}//返回结果return sb.toString();}

1.4 测试

	public static void main(String[] args) {String ocrMessage = getOcrMessage();System.out.println(ocrMessage);}

1.5 结果

9*9=3

2 方法二使用jsoup

• 依赖

		com.alibaba.fastjson2fastjson22.0.16org.jsoupjsoup1.15.3

2.1 获取 access token

public static String getAccessToken() throws IOException {//获取请求连接Connection con = Jsoup.connect("https://aip.baidubce.com/oauth/2.0/token");con.header("Content-Type","application/x-www-form-urlencoded");con.data("grant_type","client_credentials");con.data("client_id","************");con.data("client_secret","****************");Connection.Response response = con.ignoreContentType(true).method(Connection.Method.POST).execute();String body = response.body();JSONObject jsonObject = JSONObject.parseObject(body);String accessToken = jsonObject.get("access_token").toString();return accessToken;}

2.2 获取图片的文字信息

public static String getOcrMessage(String imgStr) throws IOException {String url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic" + "?access_token=" + getAccessToken();Connection con = Jsoup.connect(url);con.header("Content-Type","application/x-www-form-urlencoded");con.data("image",imgStr);Connection.Response execute = con.ignoreContentType(true).method(Connection.Method.POST).execute();String body = execute.body();//利用阿里的fastjson解析JSONObject jsonObject = JSONObject.parseObject(body);String wordsResult = jsonObject.get("words_result").toString();//words_result是一个集合JSONArray jsonArray = JSONArray.parseArray(wordsResult);//组装解析后的结果StringBuilder sb = new StringBuilder();for (Object o : jsonArray) {//Object强转成JSONObjectJSONObject jObject = (JSONObject) o;//解析wordsString words = jObject.get("words").toString();//组装到sbsb.append(words);}//返回结果return sb.toString();}

2.3 测试

public static void main(String[] args) throws IOException {//image base64 使用jsoup不需要urlencodeString imgStr = "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";String ocrMessage = getOcrMessage(imgStr);System.out.println(ocrMessage);}