main.py

ai.py

@@ -0,0 +1,44 @@
+import pandas as pd
+from collections import Counter
+import re
+
+# 过滤出包含AI技术相关词汇的弹幕
+def filter_ai_related_danmakus(danmakus):
+    ai_keywords = [
+        'AI', '人工智能', '机器学习', '深度学习', '算法', '数据分析',
+        '自动化', '智能识别', '智能', '机器人', 
+        '视觉识别', '语音识别', '图像处理', '大数据', '自适应', '智能系统',
+        '智能决策', '神经网络', '自动驾驶', '虚拟现实', '增强现实', '模式识别',
+        '自然语言处理', '推荐系统', '智能助手', '深度神经网络', '智能合约',
+        '量化分析', '特征工程', '云计算', '边缘计算', '人脸识别', '手势识别'
+    ]
+    filtered_danmakus = []
+    for danmaku in danmakus:
+        if any(re.search(keyword, danmaku, re.IGNORECASE) for keyword in ai_keywords):
+            filtered_danmakus.append(danmaku)
+    return filtered_danmakus
+
+# 统计弹幕出现频次
+def count_danmakus(danmakus):
+    danmaku_counter = Counter(danmakus)
+    return danmaku_counter.most_common(8)  # 获取前8项
+
+# 主函数
+def main():
+    # 读取之前保存的弹幕数据
+    df = pd.read_csv('danmaku.csv')
+    danmakus = df['danmaku'].tolist()
+
+    # 筛选出与AI技术相关的弹幕
+    ai_related_danmakus = filter_ai_related_danmakus(danmakus)
+
+    # 统计并获取数量排名前8的弹幕
+    top_8_danmakus = count_danmakus(ai_related_danmakus)
+
+    # 输出结果
+    print("与本次赛事应用AI技术相关的前8条弹幕及其出现次数：")
+    for danmaku, count in top_8_danmakus:
+        print(f"{danmaku}: {count} 次")
+
+if __name__ == "__main__":
+    main()

cloud.py

@@ -0,0 +1,19 @@
+import pandas as pd
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+
+# 读取包含AI相关弹幕的CSV文件
+file_path = 'danmaku.csv'  
+df = pd.read_csv(file_path)
+
+# 将弹幕内容连接成一个长字符串，用于词云生成
+text = ' '.join(df['danmaku'].dropna().astype(str))
+
+# 生成词云
+wordcloud = WordCloud(width=800, height=400, background_color='white', font_path='/usr/share/fonts/truetype/simhei.ttf').generate(text)
+
+# 绘制词云图
+plt.figure(figsize=(10, 5))
+plt.imshow(wordcloud, interpolation='bilinear')
+plt.axis('off')
+plt.show()

main.py

@@ -0,0 +1,104 @@
+
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+import requests
+import pandas as pd
+import time
+import re
+from bs4 import BeautifulSoup
+
+
+# 搜索B站视频
+def search_bilibili_videos(keyword, pages=1):
+    videos = []
+    search_url = "https://api.bilibili.com/x/web-interface/search/all/v2"
+
+    for page in range(1, pages + 1):
+        params = {
+            'keyword': keyword,
+            'page': page,
+            'order': 'toalrank'  # 综合排序
+        }
+        headers = {
+            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:129.0) Gecko/20100101 Firefox/129.0',
+            # "Referer": "https://www.bilibili.com",
+            'cookie': 'buvid3=71DE7BF1-65B2-E9EF-A649-24AAA66F6C7678761infoc; b_nut=1725457378; _uuid=9D6B1761-AF8E-C361-377A-C98C108473410589523infoc; enable_web_push=DISABLE; home_feed_column=5; browser_resolution=1536-256; buvid_fp=4bcf0d8c44fc914c4c5fd2ed0dae4f4b; buvid4=5DF4D6D0-2AE4-BF08-68E4-9D5F0577449779973-024090413-QskMrVA3JCskGyxu8QjrHA%3D%3D; CURRENT_FNVAL=4048; rpdid=|(u))kkYu|R~0J\'u~klRl~J)R; SESSDATA=861f18ef%2C1741438809%2Cea6ab%2A91CjBoRWoAds6HeZgtds_Bgccg6ZxZDoepB94Evl7kVfLMtwSKMU2X2lFH5ZfOQAqlsCESVmlINjNpV050NnFucWlibklobHhOYlJlLW9laEtyRnd5aElhVzZMM1NXdnhxT1lzMHB5WUNvcnpOcjVuUDZhMWhhUmhQdU5rQzJaQlZ0RXN5dXMtb3RnIIEC; bili_jct=0bf03509e683bc052db716bbaf2463f1; DedeUserID=1517012437; DedeUserID__ckMd5=20fba854b81fb2cd; b_lsid=73C810398_191D6DEBF89; bsource=search_baidu; header_theme_version=CLOSE; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjYxNDYwMDgsImlhdCI6MTcyNTg4Njc0OCwicGx0IjotMX0.JZKSF_Wk7iJkslm76AUNtIij5YF8FPsezF14FG1KTbk; bili_ticket_expires=1726145948; sid=e6ubibh7'
+        }
+        response = requests.get(search_url, params=params, headers=headers)
+
+        if response.status_code == 200:
+            data = response.json()
+            for result in data['data']['result']:
+                if result['result_type'] == 'video':
+                    for video in result['data']:
+                        videos.append({
+                            'title': video['title'],
+                            'aid': video['aid'],
+                            'bvid': video['bvid'],
+                            'danmaku': video['danmaku'],
+                            'url': video['arcurl']
+                        })
+        time.sleep(1)  # 防止过快请求被封
+    return videos
+
+def get_cid(aid):
+    video_url = f"https://api.bilibili.com/x/player/pagelist?aid={aid}&jsonp=jsonp"
+    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:129.0) Gecko/20100101 Firefox/129.0'}
+    response = requests.get(video_url, headers=headers)
+    if response.status_code == 200:
+        data = response.json()
+
+        return data['data'][0]['cid']
+    return None
+# 获取弹幕
+def get_danmaku(cid):
+    danmaku_url = f"https://api.bilibili.com/x/v1/dm/list.so?oid={cid}"
+    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:129.0) Gecko/20100101 Firefox/129.0'}
+
+    response = requests.get(danmaku_url, headers=headers)
+    response.encoding = 'utf-8'
+
+    danmakus = []
+    obj=re.compile(r'<d p="(.*?)">(?P<danmaku>.*?)</d>', re.S)
+    if response.status_code == 200:
+        ds=obj.finditer(response.text)
+        for d in ds:
+            danmakus.append(d.group("danmaku"))
+        # soup = BeautifulSoup(response.text, 'lxml-xml')
+        # danmakus = [d.text for d in soup.find_all('d')]
+        return danmakus
+    return []
+def process_video(video):
+    cid = get_cid(video['aid'])
+    if cid:
+        danmakus = get_danmaku(cid)
+        print(f"获取视频 {video['title']} 的 {len(danmakus)} 条弹幕")
+        return danmakus
+    else:
+        print(f"无法获取视频 {video['title']} 的 cid")
+        return []
+
+
+# 主函数
+def main():
+    keyword = "2024巴黎奥运会"
+    pages = 10  # 每页默认返回30个视频，10页为300个视频
+    videos = search_bilibili_videos(keyword, pages=pages)
+
+    all_danmakus = []
+    with ThreadPoolExecutor(max_workers=10) as executor:
+        futures = [executor.submit(process_video, video) for video in videos]
+        for future in as_completed(futures):
+            danmakus = future.result()
+            all_danmakus.extend(danmakus)
+    with open('danmaku.xlsx', 'w', encoding='utf-8') as f:
+        for danmaku in all_danmakus:
+            f.write(danmaku + '\n')
+        # 保存为CSV文件
+    df = pd.DataFrame({'danmaku': all_danmakus})
+    df.to_csv('danmaku.csv', index=False, encoding='utf-8-sig')
+    print(f"共收集到 {len(all_danmakus)} 条弹幕，保存至 danmaku.csv")
+
+
+if __name__ == "__main__":
+    main()