首页 > 技术文章 > 阿里云安全 - 文本内容垃圾检测

60kmph 2021-04-03 09:43 原文

阿里云安全 - 文本内容垃圾检测

示例代码地址:https://help.aliyun.com/document_detail/53427.html?spm=a2c4g.11186623.6.717.466d7544QbU8Lr

创建项目aliyun-sdk-demo

安装sdk

<dependencies>
    <!-- 阿里云内容安全sdk -->
    <dependency>
        <groupId>com.aliyun</groupId>
        <artifactId>aliyun-java-sdk-core</artifactId>
        <version>4.1.1</version>
    </dependency>
    <dependency>
        <groupId>com.aliyun</groupId>
        <artifactId>aliyun-java-sdk-green</artifactId>
        <version>3.5.1</version>
    </dependency>
    <dependency>
        <groupId>com.alibaba</groupId>
        <artifactId>fastjson</artifactId>
        <version>1.2.51</version>
    </dependency>
    <dependency>
        <groupId>com.aliyun.oss</groupId>
        <artifactId>aliyun-sdk-oss</artifactId>
        <version>2.8.3</version>
    </dependency>

    <dependency>
        <groupId>commons-io</groupId>
        <artifactId>commons-io</artifactId>
        <version>2.4</version>
    </dependency>

    <dependency>
        <groupId>commons-codec</groupId>
        <artifactId>commons-codec</artifactId>
        <version>1.10</version>
    </dependency>
</dependencies>

示例代码

package com.itheima.aliyun.util;

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.aliyun.oss.ClientException;
import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
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 java.util.*;

public class Main {

    public static void main(String[] args) throws Exception {
        IClientProfile profile = DefaultProfile
            .getProfile("cn-shanghai", "LTAI4FmKL2EKYCGgN2az5M57", "XjgvRoAGzM3rWQxKWDJx98VWOmO0Hz");
        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", "我是一个文本,买卖冰毒是违法的");
        tasks.add(task1);
        JSONObject data = new JSONObject();

        /**
         * 检测场景。文本垃圾检测请传递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);
        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 suggestion = ((JSONObject)sceneResult).getString("suggestion");
                                //根据scene和suggetion做相关处理。
                                //suggestion == pass表示未命中垃圾。suggestion == block表示命中了垃圾,可以通过label字段查看命中的垃圾分类。
                                System.out.println("args = [" + scene + "]");
                                System.out.println("args = [" + suggestion + "]");
                            }
                        }else{
                            System.out.println("task process fail:" + ((JSONObject)taskResult).getInteger("code"));
                        }
                    }
                } else {
                    System.out.println("detect not success. code:" + scrResponse.getInteger("code"));
                }
            }else{
                System.out.println("response not success. status:" + httpResponse.getStatus());
            }
        } catch (ServerException e) {
            e.printStackTrace();
        } catch (ClientException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}

测试一:输入以上的内容,检测通过

1612182839320

测试二:如果在上述文本内容中添加“冰毒买卖”,就会未通过

1612182853700

推荐阅读