1. 内容审核服务
内容安全是识别服务,支持对图片、视频、文本、语音等对象进行多样化场景检测,有效降低内容违规风险。
目前很多平台都支持内容检测,如阿里云、腾讯云、百度AI、网易云等国内大型互联网公司都对外提供了API。
目前用得较多的是阿里云的内容安全接口:云盾内容安全产品试用页面
1.1 文本内容审核
- 文本垃圾内容检测:https://help.aliyun.com/document_detail/70439.html?spm=a2c4g.11186623.6.659.35ac3db3l0wV5k
- 文本垃圾内容Java SDK: https://help.aliyun.com/document_detail/53427.html?spm=a2c4g.11186623.6.717.466d7544QbU8Lr
1.2 图片内容审核
- 图片垃圾内容检测:https://help.aliyun.com/document_detail/70292.html?spm=a2c4g.11186623.6.616.5d7d1e7f9vDRz4
- 图片垃圾内容Java SDK: https://help.aliyun.com/document_detail/53424.html?spm=a2c4g.11186623.6.715.c8f69b12ey35j4
2. 工具类的使用
2.1 配置文件添加
yml
aliyun:
accessKeyId: LTAI5tCWHCcfvqQzu8k2oKmX
secret: auoKUFsghimbfVQHpy7gtRyBkoR4vc
#aliyun.scenes=porn,terrorism,ad,qrcode,live,logo
scenes: terrorism
2.2 工具类
GreenImageScan.java
java
package com.heima.common.aliyun;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
import com.aliyuncs.green.model.v20180509.ImageSyncScanRequest;
import com.aliyuncs.http.FormatType;
import com.aliyuncs.http.HttpResponse;
import com.aliyuncs.http.MethodType;
import com.aliyuncs.http.ProtocolType;
import com.aliyuncs.profile.DefaultProfile;
import com.aliyuncs.profile.IClientProfile;
import com.heima.common.aliyun.util.ClientUploader;
import lombok.Getter;
import lombok.Setter;
import org.springframework.boot.context.properties.ConfigurationProperties;
import org.springframework.context.annotation.PropertySource;
import org.springframework.stereotype.Component;
import java.util.*;
@Getter
@Setter
@Component
@ConfigurationProperties(prefix = "aliyun")
public class GreenImageScan {
private String accessKeyId;
private String secret;
private String scenes;
public Map imageScan(List<byte[]> imageList) throws Exception {
IClientProfile profile = DefaultProfile
.getProfile("cn-shanghai", accessKeyId, secret);
DefaultProfile
.addEndpoint("cn-shanghai", "cn-shanghai", "Green", "green.cn-shanghai.aliyuncs.com");
IAcsClient client = new DefaultAcsClient(profile);
ImageSyncScanRequest imageSyncScanRequest = new ImageSyncScanRequest();
// 指定api返回格式
imageSyncScanRequest.setAcceptFormat(FormatType.JSON);
// 指定请求方法
imageSyncScanRequest.setMethod(MethodType.POST);
imageSyncScanRequest.setEncoding("utf-8");
//支持http和https
imageSyncScanRequest.setProtocol(ProtocolType.HTTP);
JSONObject httpBody = new JSONObject();
/**
* 设置要检测的场景, 计费是按照该处传递的场景进行
* 一次请求中可以同时检测多张图片,每张图片可以同时检测多个风险场景,计费按照场景计算
* 例如:检测2张图片,场景传递porn、terrorism,计费会按照2张图片鉴黄,2张图片暴恐检测计算
* porn: porn表示色情场景检测
*/
httpBody.put("scenes", Arrays.asList(scenes.split(",")));
/**
* 如果您要检测的文件存于本地服务器上,可以通过下述代码片生成url
* 再将返回的url作为图片地址传递到服务端进行检测
*/
/**
* 设置待检测图片, 一张图片一个task
* 多张图片同时检测时,处理的时间由最后一个处理完的图片决定
* 通常情况下批量检测的平均rt比单张检测的要长, 一次批量提交的图片数越多,rt被拉长的概率越高
* 这里以单张图片检测作为示例, 如果是批量图片检测,请自行构建多个task
*/
ClientUploader clientUploader = ClientUploader.getImageClientUploader(profile, false);
String url = null;
List<JSONObject> urlList = new ArrayList<JSONObject>();
for (byte[] bytes : imageList) {
url = clientUploader.uploadBytes(bytes);
JSONObject task = new JSONObject();
task.put("dataId", UUID.randomUUID().toString());
//设置图片链接为上传后的url
task.put("url", url);
task.put("time", new Date());
urlList.add(task);
}
httpBody.put("tasks", urlList);
imageSyncScanRequest.setHttpContent(org.apache.commons.codec.binary.StringUtils.getBytesUtf8(httpBody.toJSONString()),
"UTF-8", FormatType.JSON);
/**
* 请设置超时时间, 服务端全链路处理超时时间为10秒,请做相应设置
* 如果您设置的ReadTimeout小于服务端处理的时间,程序中会获得一个read timeout异常
*/
imageSyncScanRequest.setConnectTimeout(3000);
imageSyncScanRequest.setReadTimeout(10000);
HttpResponse httpResponse = null;
try {
httpResponse = client.doAction(imageSyncScanRequest);
} catch (Exception e) {
e.printStackTrace();
}
Map<String, String> resultMap = new HashMap<>();
//服务端接收到请求,并完成处理返回的结果
if (httpResponse != null && httpResponse.isSuccess()) {
JSONObject scrResponse = JSON.parseObject(org.apache.commons.codec.binary.StringUtils.newStringUtf8(httpResponse.getHttpContent()));
System.out.println(JSON.toJSONString(scrResponse, true));
int requestCode = scrResponse.getIntValue("code");
//每一张图片的检测结果
JSONArray taskResults = scrResponse.getJSONArray("data");
if (200 == requestCode) {
for (Object taskResult : taskResults) {
//单张图片的处理结果
int taskCode = ((JSONObject) taskResult).getIntValue("code");
//图片要检测的场景的处理结果, 如果是多个场景,则会有每个场景的结果
JSONArray sceneResults = ((JSONObject) taskResult).getJSONArray("results");
if (200 == taskCode) {
for (Object sceneResult : sceneResults) {
String scene = ((JSONObject) sceneResult).getString("scene");
String label = ((JSONObject) sceneResult).getString("label");
String suggestion = ((JSONObject) sceneResult).getString("suggestion");
//根据scene和suggetion做相关处理
//do something
System.out.println("scene = [" + scene + "]");
System.out.println("suggestion = [" + suggestion + "]");
System.out.println("suggestion = [" + label + "]");
if (!suggestion.equals("pass")) {
resultMap.put("suggestion", suggestion);
resultMap.put("label", label);
return resultMap;
}
}
} else {
//单张图片处理失败, 原因视具体的情况详细分析
System.out.println("task process fail. task response:" + JSON.toJSONString(taskResult));
return null;
}
}
resultMap.put("suggestion","pass");
return resultMap;
} else {
/**
* 表明请求整体处理失败,原因视具体的情况详细分析
*/
System.out.println("the whole image scan request failed. response:" + JSON.toJSONString(scrResponse));
return null;
}
}
return null;
}
}
GreenTextScan.java
java
package com.heima.common.aliyun;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
import com.aliyuncs.exceptions.ClientException;
import com.aliyuncs.exceptions.ServerException;
import com.aliyuncs.green.model.v20180509.TextScanRequest;
import com.aliyuncs.http.FormatType;
import com.aliyuncs.http.HttpResponse;
import com.aliyuncs.profile.DefaultProfile;
import com.aliyuncs.profile.IClientProfile;
import lombok.Getter;
import lombok.Setter;
import org.springframework.boot.context.properties.ConfigurationProperties;
import org.springframework.context.annotation.PropertySource;
import org.springframework.stereotype.Component;
import java.util.*;
@Getter
@Setter
@Component
@ConfigurationProperties(prefix = "aliyun")
public class GreenTextScan {
private String accessKeyId;
private String secret;
public Map greeTextScan(String content) throws Exception {
System.out.println(accessKeyId);
IClientProfile profile = DefaultProfile
.getProfile("cn-shanghai", accessKeyId, secret);
DefaultProfile.addEndpoint("cn-shanghai", "cn-shanghai", "Green", "green.cn-shanghai.aliyuncs.com");
IAcsClient client = new DefaultAcsClient(profile);
TextScanRequest textScanRequest = new TextScanRequest();
textScanRequest.setAcceptFormat(FormatType.JSON); // 指定api返回格式
textScanRequest.setHttpContentType(FormatType.JSON);
textScanRequest.setMethod(com.aliyuncs.http.MethodType.POST); // 指定请求方法
textScanRequest.setEncoding("UTF-8");
textScanRequest.setRegionId("cn-shanghai");
List<Map<String, Object>> tasks = new ArrayList<Map<String, Object>>();
Map<String, Object> task1 = new LinkedHashMap<String, Object>();
task1.put("dataId", UUID.randomUUID().toString());
/**
* 待检测的文本,长度不超过10000个字符
*/
task1.put("content", content);
tasks.add(task1);
JSONObject data = new JSONObject();
/**
* 检测场景,文本垃圾检测传递:antispam
**/
data.put("scenes", Arrays.asList("antispam"));
data.put("tasks", tasks);
System.out.println(JSON.toJSONString(data, true));
textScanRequest.setHttpContent(data.toJSONString().getBytes("UTF-8"), "UTF-8", FormatType.JSON);
// 请务必设置超时时间
textScanRequest.setConnectTimeout(3000);
textScanRequest.setReadTimeout(6000);
Map<String, String> resultMap = new HashMap<>();
try {
HttpResponse httpResponse = client.doAction(textScanRequest);
if (httpResponse.isSuccess()) {
JSONObject scrResponse = JSON.parseObject(new String(httpResponse.getHttpContent(), "UTF-8"));
System.out.println(JSON.toJSONString(scrResponse, true));
if (200 == scrResponse.getInteger("code")) {
JSONArray taskResults = scrResponse.getJSONArray("data");
for (Object taskResult : taskResults) {
if (200 == ((JSONObject) taskResult).getInteger("code")) {
JSONArray sceneResults = ((JSONObject) taskResult).getJSONArray("results");
for (Object sceneResult : sceneResults) {
String scene = ((JSONObject) sceneResult).getString("scene");
String label = ((JSONObject) sceneResult).getString("label");
String suggestion = ((JSONObject) sceneResult).getString("suggestion");
System.out.println("suggestion = [" + label + "]");
if (!suggestion.equals("pass")) {
resultMap.put("suggestion", suggestion);
resultMap.put("label", label);
return resultMap;
}
}
} else {
return null;
}
}
resultMap.put("suggestion", "pass");
return resultMap;
} else {
return null;
}
} else {
return null;
}
} catch (ServerException e) {
e.printStackTrace();
} catch (ClientException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
}
2.3 测试使用
AliyunTest.java
java
package com.heima.wemedia;
import com.heima.common.aliyun.GreenImageScan;
import com.heima.common.aliyun.GreenTextScan;
import com.heima.file.service.FileStorageService;
import org.junit.Test;
import org.junit.runner.RunWith;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.test.context.SpringBootTest;
import org.springframework.test.context.junit4.SpringRunner;
import java.util.Arrays;
import java.util.Map;
@SpringBootTest(classes = WemediaApplication.class)
@RunWith(SpringRunner.class)
public class AliyunTest {
@Autowired
private GreenTextScan greenTextScan;
@Autowired
private GreenImageScan greenImageScan;
@Autowired
private FileStorageService fileStorageService;
@Test
public void testScanText() throws Exception {
Map map = greenTextScan.greeTextScan("我是一个好人,冰毒");
System.out.println(map);
}
@Test
public void testScanImage() throws Exception {
byte[] bytes = fileStorageService.downLoadFile("http://192.168.200.130:9000/leadnews/2021/04/26/ef3cbe458db249f7bd6fb4339e593e55.jpg");
Map map = greenImageScan.imageScan(Arrays.asList(bytes));
System.out.println(map);
}
}