fix

README.md

@@ -1,2 +1,38 @@
-# bilibili-spider
+## 一.主任务要求
+**1.数据获取**
+
+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300的所有视频弹幕。
+
+**2.数据统计**
+
+统计AI技术应该方面的每种弹幕数量，并输出数量排名前8的弹幕。
+将统计的数据利用编程工具或开发包自动写入Excel表中。
+
+**3.数据可视化**
+
+对采集的数据集进行可视化表示，制作词云图，越美观越好。
+
+**4.数据结论**
+
+通过统计数据得出当前B站用户对于2024巴黎奥运会应用AI技术的主流看法。
+
+## 二.附加题
+
+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。
+
+可自动翻页（爬虫可以自动对后续页面进行爬取，而不需要我们指定第几页）
+
+指定爬取范围：如2020年1月1号 - 2021年9月1号
+
+## 三.使用技术栈
+
+* Http请求：OkHttp Jsoup
+* Json解析：Gson
+* Excel写入：EasyExcel
+* 词云生成：Kumo
+* 日志打印：Slf4j
 

pom.xml

@@ -14,14 +14,6 @@
         <spring-boot.version>2.6.13</spring-boot.version>
     </properties>
     <dependencies>
-        <dependency>
-            <groupId>org.springframework.boot</groupId>
-            <artifactId>spring-boot-starter</artifactId>
-        </dependency>
-        <dependency>
-            <groupId>org.springframework.boot</groupId>
-            <artifactId>spring-boot-starter-web</artifactId>
-        </dependency>
         <dependency>
             <groupId>org.springframework.boot</groupId>
             <artifactId>spring-boot-starter-test</artifactId>
@@ -36,14 +28,16 @@
             <groupId>org.projectlombok</groupId>
             <artifactId>lombok</artifactId>
         </dependency>
+        <!-- Logback Classic -->
         <dependency>
-            <groupId>com.squareup.okhttp3</groupId>
-            <artifactId>okhttp</artifactId>
-            <version>4.10.0</version>
+            <groupId>ch.qos.logback</groupId>
+            <artifactId>logback-classic</artifactId>
+            <version>1.2.10</version>
         </dependency>
+
         <dependency>
-            <groupId>org.mockito</groupId>
-            <artifactId>mockito-inline</artifactId>
+            <groupId>com.squareup.okhttp3</groupId>
+            <artifactId>okhttp</artifactId>
             <version>4.10.0</version>
         </dependency>
         <dependency>
@@ -64,12 +58,6 @@
             <version>1.27</version>
         </dependency>
         <!--Trip数等数据结构相关依赖-->
-        <dependency>
-            <groupId>org.apache.commons</groupId>
-            <artifactId>commons-collections4</artifactId>
-            <version>4.4</version>
-        </dependency>
-
         <dependency>
             <groupId>com.alibaba</groupId>
             <artifactId>easyexcel</artifactId>

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

@@ -1,6 +1,7 @@
 package com.flyingpig.bilibilispider.additionalWork;
 
 
+import com.flyingpig.bilibilispider.constant.HeaderConstant;
 import lombok.AllArgsConstructor;
 import lombok.Data;
 import lombok.NoArgsConstructor;
@@ -22,7 +23,7 @@ public class FzuNewsCrawler {
     private static final String BASE_URL = "https://info22.fzu.edu.cn/lm_list.jsp?";
     private static final String NEWS_URL = BASE_URL + "totalpage=948&PAGENUM=%d&urltype=tree.TreeTempUrl&wbtreeid=1460";
 
-
+    private static final String CONTENT_URL = "https://info22.fzu.edu.cn/content.jsp?";
     // 爬取福大通知和文件系统
     public List<FzuNews> crawlFzuNotificationsAndFileSystems(String newsBeginTime, String newsEndTime) throws Exception {
         List<FzuNews> fzuNewsList = new ArrayList<>(); // 保存新闻列表
@@ -61,7 +62,7 @@ public class FzuNewsCrawler {
                     // 获取新闻的作者、标题和正文链接
                     String author = newsElement.getElementsByTag("a").eq(0).text();
                     String title = newsElement.getElementsByTag("a").eq(1).text();
-                    String textHref = BASE_URL + newsElement.getElementsByTag("a").get(1).attr("href");
+                    String textHref = CONTENT_URL + newsElement.getElementsByTag("a").get(1).attr("href");
                     String text = fetchNewsText(textHref);
 
                     // 将新闻信息写入文件中
@@ -89,7 +90,8 @@ public class FzuNewsCrawler {
     // 获取新闻正文内容
     private String fetchNewsText(String textHref) throws Exception {
         StringBuilder textBuilder = new StringBuilder(); // 使用StringBuilder拼接正文内容
-        Document document = Jsoup.connect(textHref).get();
+        Document document = Jsoup.connect(textHref)
+                .header("User-Agent", HeaderConstant.USER_AGENT).get();
 
         // 获取所有<p>标签中的正文
         Elements paragraphs = document.getElementsByTag("p");

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

@@ -6,4 +6,5 @@ package com.flyingpig.bilibilispider.constant;
 public class HeaderConstant {
     public static final String COOKIE = "buvid3=06742E53-942C-670A-D496-6E2A79F196FF52832infoc; b_nut=1694915352; i-wanna-go-back=-1; b_ut=7; _uuid=F744F108A-8F810-A165-2EA4-7B4956ACF910C53152infoc; buvid4=8D3A427A-5715-145B-3AA8-9ACC6E30889D54861-023091709-5h4N7ejh5A4ENQhvWFdRwQ%3D%3D; hit-new-style-dyn=1; hit-dyn-v2=1; header_theme_version=CLOSE; rpdid=0zbfAGEiSg|12slY8UuG|pS|3w1QHGXk; LIVE_BUVID=AUTO6216955654982035; buvid_fp_plain=undefined; enable_web_push=DISABLE; dy_spec_agreed=1; is-2022-channel=1; CURRENT_BLACKGAP=0; DedeUserID=398014090; DedeUserID__ckMd5=da87c9926c73fac5; FEED_LIVE_VERSION=V_WATCHLATER_PIP_WINDOW3; SESSDATA=618de7e5%2C1726673190%2C8e231%2A32CjAB8DOA4RwqxG7hQy82813je1HM5n0r08KRLyQfyA9zqBalG7QRrNNsuqvI7RejMHwSVnloTURqNE5qWmZmV0M3b0hqS0dTU21ES3NEbU9BX1JwNTNHU0VYMXc2YXNYRU9aOTJ2Q1ZXZkV4aWUyMzQ1VFo0eWpOMGVxUVQydVFfVmVGWjNoY1d3IIEC; bili_jct=51d42647c6b3da22794e018c68e239ba; CURRENT_FNVAL=4048; CURRENT_QUALITY=80; fingerprint=86d24a6d98af903f094c42f9498dfc3d; PVID=3; buvid_fp=86d24a6d98af903f094c42f9498dfc3d; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjQ4ODkxMDUsImlhdCI6MTcyNDYyOTg0NSwicGx0IjotMX0.SuRMicGtcUVVh2xh7DrFQCJReFKXavWzf07sThaixyU; bili_ticket_expires=1724889045; home_feed_column=5; browser_resolution=1440-641; sid=7oephj0f; bp_t_offset_398014090=970621780936884224; b_lsid=410A8B269_1919809748E; bsource=search_google; xxoo-tmp=zhHans";
 
+    public static final String USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3";
 }

src/main/java/com/flyingpig/bilibilispider/task/BilibiliSpiderTask.java

@@ -4,8 +4,12 @@ import com.flyingpig.bilibilispider.constant.FileName;
 import com.google.gson.JsonArray;
 import com.google.gson.JsonParser;
 import lombok.extern.slf4j.Slf4j;
-import org.springframework.web.util.UriComponentsBuilder;
-import java.io.*;
+import okhttp3.HttpUrl;
+
+import java.io.ByteArrayOutputStream;
+import java.io.File;
+import java.io.FileWriter;
+import java.io.IOException;
 import java.util.ArrayList;
 import java.util.Collections;
 import java.util.List;
@@ -13,8 +17,10 @@ import java.util.concurrent.*;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 import java.util.zip.Inflater;
+
 import static com.flyingpig.bilibilispider.constant.UrlConstant.*;
-import static com.flyingpig.bilibilispider.util.RequestUtil.*;
+import static com.flyingpig.bilibilispider.util.RequestUtil.requestToGetBodyBytes;
+import static com.flyingpig.bilibilispider.util.RequestUtil.requesttToGetBodyString;
 
 @Slf4j
 public class BilibiliSpiderTask {
@@ -31,11 +37,13 @@ public class BilibiliSpiderTask {
                 final int page = j;
                 Future<List<Long>> future = executor.submit(() -> {
                     List<Long> pageCidList = new ArrayList<>();
-                    String searchUrl = UriComponentsBuilder.fromHttpUrl(BILIBILI_SEARCH_URL)
-                            .queryParam("keyword", keyword)
-                            .queryParam("search_type", "video")
-                            .queryParam("page", page)
-                            .queryParam("page_size", 50).toUriString();
+
+                    String searchUrl = HttpUrl.parse(BILIBILI_SEARCH_URL).newBuilder()
+                            .addQueryParameter("keyword", keyword)
+                            .addQueryParameter("search_type", "video")
+                            .addQueryParameter("page", String.valueOf(page))
+                            .addQueryParameter("page_size", String.valueOf(50))
+                            .build().toString();
 
                     log.info("爬取第 {} 页", page);
 
@@ -45,11 +53,12 @@ public class BilibiliSpiderTask {
 
                     for (int i = 0; i < searchResultArray.size(); i++) {
                         String bvid = searchResultArray.get(i).getAsJsonObject().get("bvid").getAsString();
-                        log.info("视频bvid: {}", bvid);
 
-                        String getCidUrl = UriComponentsBuilder.fromHttpUrl(BILIBILI_GETCID_URL)
-                                .queryParam("bvid", bvid)
-                                .queryParam("jsonp", "jsonp").toUriString();
+                        String getCidUrl = HttpUrl.parse(BILIBILI_GETCID_URL).newBuilder()
+                                .addQueryParameter("bvid", bvid)
+                                .addQueryParameter("jsonp", "jsonp")
+                                .build()
+                                .toString();
 
                         Long cid = JsonParser.parseString(requesttToGetBodyString(getCidUrl))
                                 .getAsJsonObject().getAsJsonArray("data")
@@ -143,6 +152,7 @@ public class BilibiliSpiderTask {
             }
             decompressData = outputStream.toByteArray();
         } catch (Exception e) {
+            log.error("解压数据失败", e);
         } finally {
             outputStream.close();
         }

src/main/java/com/flyingpig/bilibilispider/task/DataAnalysisTask.java

@@ -38,6 +38,7 @@ public class DataAnalysisTask {
     }
 
 
+
     public static HashMap<String, Integer> getTop8BarrageListAboutAI() {
 
         System.out.println(aiKeywords.size());
@@ -125,4 +126,6 @@ public class DataAnalysisTask {
         return new HashMap<>(sortedMap);
     }
 
+
+
 }