Update spider_main.py

README.md

@@ -1,2 +1,9 @@
 # spider
+中途有修改
+#分为了"图片"/"main"两个分支，如果点开看不到所有文件可以在左上角分支处选择"图片"
 
+spider_main.py-弹幕爬虫代码
+cloudimage.py-词云图代码
+select_content.py-筛选AI弹幕代码
+ballgame.py-附加题代码
+其中弹幕生成文件**all_content.txt**超过5MB无法上传

ballgame.py

@@ -0,0 +1,20 @@
+import pandas as pd
+from collections import Counter
+
+# 读入所有弹幕
+with open('all_content.txt', mode='r', encoding='utf-8') as f:
+    data_list = f.readlines()
+# 六项球类关键词
+keywords = ['乒乓球','羽毛球','排球','篮球','足球','网球']
+# 筛选有关球类的弹幕
+selectdanmu = [danmu for danmu in data_list if any(keyword in danmu for keyword in keywords)]
+
+# 统计弹幕数量
+num = Counter(selectdanmu)
+top_common = num.most_common(20)
+# 展示数量前八条弹幕
+print(top_common)
+t = pd.DataFrame(top_common, columns=['弹幕内容', '数量'])
+# 导出excel文件
+excel_path = 'top_ball_danmu.xlsx'  
+t.to_excel(excel_path, index=False)

cloudimage2.py

@@ -9,7 +9,7 @@ text1=jieba.cut(text)
 # 以空格作为分隔符，将分词后的所有字符串合并成一个新的字符串
 text = ' '.join(text1)
 # 根据分词结果产生词云
-wc = WordCloud(font_path = "C:\Windows\Fonts\Microsoft YaHei UI\msyh.ttc",width=500, height=400, mode="RGBA", background_color=None).generate(text)
+wc = WordCloud(font_path = "C:\Windows\Fonts\Microsoft YaHei UI\msyh.ttc",width=618, height=500, mode="RGBA", background_color=None).generate(text)
 # 以图片的形式显示词云
 plt.imshow(wc, interpolation="bilinear")
 # 不显示图像坐标系

select_content.py

@@ -0,0 +1,21 @@
+import pandas as pd
+from collections import Counter
+
+# 读入所有弹幕
+with open('all_content.txt', mode='r', encoding='utf-8') as f:
+    data_list = f.readlines()
+# AI技术应用有关关键词
+ai_keywords = ['AI','人工智能','ai音效','ai视频','ai技术','机器学习', '深度学习', '自然语言处理','ai训练',
+            '大模型','自然语言处理','云计算','神经网络', '自动驾驶','ai设计','ai图','AI软件',]
+# 筛选有关AI的弹幕
+selectdanmu = [danmu for danmu in data_list if any(keyword in danmu for keyword in ai_keywords)]
+
+# 统计弹幕数量
+num = Counter(selectdanmu)
+top_common = num.most_common(8)
+# 展示数量前八条弹幕
+print(top_common)
+t = pd.DataFrame(top_common, columns=['弹幕内容', '数量'])
+# 导出excel文件
+excel_path = 'top8_ai_danmu.xlsx'  
+t.to_excel(excel_path, index=False)

spider_main.py

@@ -1,69 +1,68 @@
-import requests
-import json
-import re
-import wordcloud
-from bs4 import BeautifulSoup
-from video_bid import videobid
-# 基本模块
-# 所需视频bid号列表、弹幕内容、cid号列表
-list1 = []
-list2 = []
-anslist = []
-# 请求标头 模拟浏览器
-headers = {
-    #Cookie 用户信息  u-a 用户代理 referer 反爬
-        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0",
-        "cookie":"_uuid=C910E215C-7103E-4E54-9515-10FF7599AAECF78232infoc; buvid_fp=e7bba7e4bae311a280afa29479dcd19d; buvid3=A7EFF3D3-823F-E623-0EC8-4DE13D84710980740infoc; b_nut=1709977881; buvid4=B0B9DD4D-D469-44F5-6A8F-B2BCC72B405380740-024030909-YSaors5wcVdXxPAyYUcK7w%3D%3D; CURRENT_FNVAL=4048; rpdid=0zbfAGEiQM|8kXSwyAg|26E|3w1Swd2X; DedeUserID=440181187; DedeUserID__ckMd5=7aea6a85d9bac605; CURRENT_QUALITY=80; header_theme_version=CLOSE; enable_web_push=DISABLE; SESSDATA=218ebe14%2C1742048643%2C74a54%2A92CjCwT-WOtbM-xsZKbPnRuVAbDVtv--QmJvHh6khSys1se0CpcdYi5_2hO4THAprUtX0SVjMxenRnVjNiQ0JDd1ZtLVU1OWs3OUdOczNYWlZ6aWU2dkg2RHpWb2hZc00xOWJjWm9MVjdGNUcwLVY1ckYzOC1BUHViR0dvajZoeWpQb1M3ek9DUC13IIEC; bili_jct=51295d2894045195c66fdadf6b1b7a91; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY3NTU4OTQsImlhdCI6MTcyNjQ5NjYzNCwicGx0IjotMX0.Dr-RHjAMQ0qLpe3McjbIChH_d_S3UYkbXlb2doqMdWw; bili_ticket_expires=1726755834; home_feed_column=5; browser_resolution=1536-695; bp_t_offset_440181187=978115949112590336; sid=6xn7yn2o; b_lsid=BA647F49_1920109E5DD",
-        "referer":"https://www.bilibili.com/"
-}
-def video_bid(num1):
-    # 获取综合排序前300视频的bid
-    # 请求网址
-    page_url = f"https://search.bilibili.com/all?keyword={"2024巴黎奥运会"}&page={num1}"
-    
-    response = requests.get(url=page_url, headers=headers)# 发送请求
-    response.encoding = response.apparent_encoding
-    data_list = re.findall('"bvid":"(.*?)"', response.text)# 正则表达式获取bid
-    global list1   # 声明为全局变量
-    list1.extend(data_list) # 每次循环导入数据
-def video_cid(num2):
-    # 获取视频cid
-    # 请求网址
-    cid_url = f'https://api.bilibili.com/x/player/pagelist?bvid={num2}&jsonp=jsonp'
-    response = requests.get(url=cid_url, headers=headers) # 发送请求
-    response.encoding = response.apparent_encoding
-    content = json.loads(response.text)# 获取cid号
-    datalist = []
-#    if "data" in content and "cid" in content["data"][0]:
-    cid = content["data"][0]["cid"]
-    if isinstance(cid, list):
-        datalist.extend(cid)
-    else:
-        datalist.append(cid)
-    global list2# 声明为全局变量
-    list2.extend(datalist)
-def video_bullet(num3):
-    # 爬取弹幕
-    bullet_url = f'https://comment.bilibili.com/{num3}.xml'    # 弹幕URL
-    response = requests.get(url=bullet_url, headers=headers)    # 发送请求
-    response.encoding = response.apparent_encoding
-    global anslist
-    chat_xml = BeautifulSoup(response.text,"xml")   # 解析XML响应 提取文本
-    ss = chat_xml.find_all("d") #爬取所有的弹幕
-    for d in ss:
-        anslist.append(d.text)
-if __name__ == '__main__':
-    # 每页30个视频 爬取第1页到第10页的bid号
-    for page in (1,11):
-        video_bid(page)
-    # 对于每个bid号爬取cid号
-    for bv in list1:
-        video_cid(bv)
-    # 对于每个CID号，爬取弹幕内容
-    for cid in list2:
-        video_bullet(cid)
-    # 将弹幕内容导出到本地文件
-    blscn = '\n'.join(anslist)
-    with open('所有弹幕.txt', mode='a', encoding='utf-8') as f:
-        f.write(blscn)
+import requests
+import json
+import re
+import wordcloud
+from bs4 import BeautifulSoup
+# from video_bid import videobid
+# 基本模块
+# 所需视频bid号列表、弹幕内容、cid号列表
+list1 = []
+list2 = []
+anslist = []
+# 请求标头 模拟浏览器
+headers = {
+    #Cookie 用户信息  u-a 用户代理 referer 反爬
+        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0",
+        "cookie":"_uuid=C910E215C-7103E-4E54-9515-10FF7599AAECF78232infoc; buvid_fp=e7bba7e4bae311a280afa29479dcd19d; buvid3=A7EFF3D3-823F-E623-0EC8-4DE13D84710980740infoc; b_nut=1709977881; buvid4=B0B9DD4D-D469-44F5-6A8F-B2BCC72B405380740-024030909-YSaors5wcVdXxPAyYUcK7w%3D%3D; CURRENT_FNVAL=4048; rpdid=0zbfAGEiQM|8kXSwyAg|26E|3w1Swd2X; DedeUserID=440181187; DedeUserID__ckMd5=7aea6a85d9bac605; CURRENT_QUALITY=80; header_theme_version=CLOSE; enable_web_push=DISABLE; SESSDATA=218ebe14%2C1742048643%2C74a54%2A92CjCwT-WOtbM-xsZKbPnRuVAbDVtv--QmJvHh6khSys1se0CpcdYi5_2hO4THAprUtX0SVjMxenRnVjNiQ0JDd1ZtLVU1OWs3OUdOczNYWlZ6aWU2dkg2RHpWb2hZc00xOWJjWm9MVjdGNUcwLVY1ckYzOC1BUHViR0dvajZoeWpQb1M3ek9DUC13IIEC; bili_jct=51295d2894045195c66fdadf6b1b7a91; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY3NTU4OTQsImlhdCI6MTcyNjQ5NjYzNCwicGx0IjotMX0.Dr-RHjAMQ0qLpe3McjbIChH_d_S3UYkbXlb2doqMdWw; bili_ticket_expires=1726755834; home_feed_column=5; browser_resolution=1536-695; bp_t_offset_440181187=978115949112590336; sid=6xn7yn2o; b_lsid=BA647F49_1920109E5DD",
+        "referer":"https://www.bilibili.com/"
+}
+def video_bid(num1):
+    # 获取综合排序前300视频的bid
+    # 请求网址
+    page_url = f"https://search.bilibili.com/all?keyword={"2024巴黎奥运会"}&page={num1}"
+    
+    response = requests.get(url=page_url, headers=headers)# 发送请求
+    response.encoding = response.apparent_encoding
+    data_list = re.findall('"bvid":"(.*?)"', response.text)# 正则表达式获取bid
+    global list1   # 声明为全局变量
+    list1.extend(data_list) # 每次循环导入数据
+def video_cid(num2):
+    # 获取视频cid
+    # 请求网址
+    cid_url = f'https://api.bilibili.com/x/player/pagelist?bvid={num2}&jsonp=jsonp'
+    response = requests.get(url=cid_url, headers=headers) # 发送请求
+    response.encoding = response.apparent_encoding
+    content = json.loads(response.text)# 获取cid号
+    datalist = []
+    cid = content["data"][0]["cid"]
+    if isinstance(cid, list):
+        datalist.extend(cid)
+    else:
+        datalist.append(cid)
+    global list2# 声明为全局变量
+    list2.extend(datalist)
+def video_bullet(num3):
+    # 爬取弹幕
+    bullet_url = f'https://comment.bilibili.com/{num3}.xml'    # 弹幕URL
+    response = requests.get(url=bullet_url, headers=headers)    # 发送请求
+    response.encoding = response.apparent_encoding
+    global anslist
+    chat_xml = BeautifulSoup(response.text,"xml")   # 解析XML响应 提取文本
+    ss = chat_xml.find_all("d") #爬取所有的弹幕
+    for d in ss:
+        anslist.append(d.text)
+if __name__ == '__main__':
+    # 每页30个视频 爬取第1页到第10页的bid号
+    for page in (1,11):
+        video_bid(page)
+    # 对于每个bid号 爬取cid号
+    for bv in list1:
+        video_cid(bv)
+    # 对于每个cid号 爬取弹幕内容
+    for cid in list2:
+        video_bullet(cid)
+    # 将弹幕内容导出到本地文件
+    blscn = '\n'.join(anslist)
+    with open('所有弹幕.txt', mode='a', encoding='utf-8') as f:
+        f.write(blscn)
     print("endprint")  #检测是否正常退出