Update UrlConstant.java

.mvn/wrapper/maven-wrapper.properties

@@ -0,0 +1,2 @@
+distributionUrl=https://repo.maven.apache.org/maven2/org/apache/maven/apache-maven/3.9.3/apache-maven-3.9.3-bin.zip
+wrapperUrl=https://repo.maven.apache.org/maven2/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar

README.md

@@ -18,8 +18,7 @@
 
 ## 二.附加题
 
-爬取福州大学的通知、文件系统
+### (1)爬取福州大学的通知、文件系统
-
 地址：https://info22.fzu.edu.cn/lm_list.jsp?wbtreeid=1460【要开校园网访问】
 
 包含发布时间，作者，标题以及正文。
@@ -28,6 +27,9 @@
 
 指定爬取范围：如2020年1月1号 - 2021年9月1号
 
+### (2)爬取B站评论
+利用爬虫B站爬取所需弹幕数据，搜索关键词“2024巴黎奥运会”，爬取综合排序前50的所有视频第一页评论。
+
 ## 三.使用技术栈
 
 * Http请求：OkHttp Jsoup

pom.xml

@@ -19,6 +19,19 @@
             <artifactId>spring-boot-starter-test</artifactId>
             <scope>test</scope>
         </dependency>
+        <dependency>
+            <groupId>org.mockito</groupId>
+            <artifactId>mockito-core</artifactId>
+            <version>4.0.0</version>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.mockito</groupId>
+            <artifactId>mockito-inline</artifactId>
+            <version>4.0.0</version>
+            <scope>test</scope>
+        </dependency>
         <dependency>
             <groupId>com.google.code.gson</groupId>
             <artifactId>gson</artifactId>

src/main/java/com/flyingpig/bilibilispider/additionalWork/BiliBiliReply.java

@@ -0,0 +1,59 @@
+package com.flyingpig.bilibilispider.additionalWork;
+
+import com.google.gson.JsonArray;
+import com.google.gson.JsonElement;
+import com.google.gson.JsonObject;
+import com.google.gson.JsonParser;
+import okhttp3.HttpUrl;
+
+import static com.flyingpig.bilibilispider.constant.UrlConstant.*;
+import static com.flyingpig.bilibilispider.util.RequestUtil.requesttToGetBodyString;
+
+public class BiliBiliReply {
+
+    public static void main(String[] args) {
+
+        String searchUrl = HttpUrl.parse(BILIBILI_SEARCH_URL).newBuilder()
+                .addQueryParameter("keyword", "2024巴黎奥运会")
+                .addQueryParameter("search_type", "video")
+                .addQueryParameter("page", String.valueOf(1))
+                .addQueryParameter("page_size", String.valueOf(50))
+                .build().toString();
+
+
+        JsonArray searchResultArray = JsonParser.parseString(requesttToGetBodyString(searchUrl))
+                .getAsJsonObject().getAsJsonObject("data")
+                .getAsJsonArray("result");
+
+        for (int i = 0; i < searchResultArray.size(); i++) {
+            String aid = searchResultArray.get(i).getAsJsonObject().get("aid").getAsString();
+
+            System.out.println("正在爬取视频的aid为："+aid+"的评论");
+
+            String getReplyUrl = HttpUrl.parse(REAPLY_URL).newBuilder()
+                    .addQueryParameter("next", "1")
+                    .addQueryParameter("type", "1")
+                    .addQueryParameter("mode", "3")
+                    .addQueryParameter("oid", aid.toString())
+                    .build().toString();
+
+            // 解析字符串为 JsonObject
+            JsonObject requestObject = JsonParser.parseString(requesttToGetBodyString(getReplyUrl)).getAsJsonObject();
+            if (requestObject.get("code").toString().equals("12002")) {
+                continue;
+            }
+
+
+            JsonArray repliesArray = requestObject.getAsJsonObject("data").getAsJsonArray("replies");
+
+            // 遍历 replies 数组
+            for (JsonElement replyElement : repliesArray) {
+                System.out.println(replyElement.getAsJsonObject().getAsJsonObject("content").get("message").getAsString());
+            }
+
+
+        }
+    }
+
+}
+

src/main/java/com/flyingpig/bilibilispider/constant/UrlConstant.java

@@ -9,4 +9,6 @@ public class UrlConstant {
     public static final String BILIBILI_GETCID_URL = "https://api.bilibili.com/x/player/pagelist";
 
     public static final String DM_URL = "https://comment.bilibili.com/";
+
+    public static final String REAPLY_URL = "https://api.bilibili.com/x/v2/reply/main";
 }