这是一个爬取视频弹幕的代码

需求：根据视频关键字，爬取该关键字所搜出来的视频的弹幕。
例如设置关键字“996”，代码会爬取根据“996”搜索出来的视频的弹幕，可以设置爬取的页码，开始页码和结束页码，代码自动获取每个视频的cid，再根据cid通过api获取弹幕信息。
设置要爬取的页码。直接上代码：

# This is a sample Python script.
# 301-400
import json
import os.path
import os
import random
import threading
import time
from hashlib import sha1
import requests
import re
import jieba
import winsound
from fake_useragent import UserAgent
from threading import Thread
# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
class BainduSpider:

    def __init__(self):
        self.headers = {
            'Accept':"*/*",
            "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
            'User-Agent': UserAgent().random
        }
        #开始页码
        self.startPageNum = 1
        #结束页码
        self.finalPageNum = 10 #包括该页码
        self.errPageNum = 0
        self.keyWord = ""
        self.allVideoDanMuInfo = {"keyWord":'', "data":[]}
        self.danMuInfoList = []
        self.error = True

    def allListUrlSet(self, pageNum, keyWord):
        if pageNum == 1:
            return "https://search.bilibili.com/all?keyword=" + keyWord
        else:
            return "https://search.bilibili.com/all?keyword=" + keyWord + "&page=" + str(pageNum) + "&o=" + str((pageNum - 1)*30)

    # 根据url获取页面代码
    def requestText(self, url):
        listUrl = url
        list_html = requests.get(url=listUrl, headers=self.headers, timeout=30)
        list_html.encoding = "utf-8"
        list_html = list_html.text
        # print("requestText根据url获取页面代码:", list_html)
        return list_html

    # 筛选出关键数据数组
    def findKeyData(self, findText, htmlText):
        videoUrlList = re.findall(findText, htmlText)
        print("findKeyData筛选出关键数据数组")
        return videoUrlList

    # 获取单个视频页面数据
    def getDnMu(self, videoUrl):
        videoUrl = "https://" + videoUrl
        # 请求页面html数据
        htmlText = self.requestText(videoUrl)
        # print("弹幕页面数据：", htmlText)
        return htmlText

    # 获取视频cid
    def getCid(self,htmlText):
        findText = 'window.__INITIAL_STATE__={(.*?)};'
        cidList = re.findall(findText, htmlText)
        cidList = "{" + cidList[0] + "}"
        cidJson = json.loads(cidList)
        print("视频名称：", cidJson['videoData']['title'])
        print("cid信息：", cidJson['videoData']['cid'])
        cid = cidJson['videoData']['cid']
        bvid = cidJson['videoData']['bvid']
        title = cidJson['videoData']['title']
        videoInfo = {"cid":cid, "bvid":bvid, "title":title}
        return videoInfo

    # 根据cid获取弹幕信息
    def getDanMu(self, cid):
        url = "https://api.bilibili.com/x/v1/dm/list.so?oid=" + str(cid)
        # 获取信息
        danMuHTML = self.requestText(url)
        findText = '<d p=".*?">(.*?)</d>'
        danMuList = self.findKeyData(findText, danMuHTML)
        print("弹幕数量：", len(danMuList))
        return danMuList

#   关键字搜索
    def keyWordSearch(self):
        for i in range(self.startPageNum, self.finalPageNum+1):
            self.errPageNum += 1
            # 请求的url
            requestUrl = self.allListUrlSet(i, self.keyWord)
            # 请求到的页面代码数据
            htmlText = self.requestText(requestUrl)
            findText = '<li class="video-item matrix"><a href="//(.*?)" title='
            # 筛选出当前页面的视频链接
            videoUrlList = self.findKeyData(findText, htmlText)
            videoIndex = 0
            # 访问视频链接，获取每个视频的弹幕信息
            for videoUrl in videoUrlList:
                videoIndex = videoIndex + 1
                print("当前为第：" + str(i) + "页/（共" + str(self.finalPageNum - self.startPageNum + 1) + "页）；第：" + str(videoIndex) + "/（共" + str(len(videoUrlList)) + "）个视频")
                oneVideoHtml = self.getDnMu(videoUrl)
                # 获取cid
                videoInfo = self.getCid(oneVideoHtml)
                cid = videoInfo['cid']
                # 获取弹幕信息
                danMuList = self.getDanMu(cid)

                self.danMuInfoList.extend(danMuList)

                saveInfo = {"videoInfo":videoInfo, "danMu":danMuList}
                self.allVideoDanMuInfo['data'].append(saveInfo)
                # print("视频信息：", self.allVideoDanMuInfo)
                sleepTime = random.randint(1, 10)
                print("等待时间：", sleepTime)
                time.sleep(sleepTime)
        self.allVideoDanMuInfo['keyWord'] = self.keyWord
        self.saveData(self.allVideoDanMuInfo, self.danMuInfoList)
    # 数据存入文件
    def saveData(self, videoInfo, danMuList):
        print("。。。。。。存储信息。。。。")
        file = open("E://弹幕数据/" + self.keyWord + "(" + str(self.startPageNum) + "-" + str(self.errPageNum) + ").txt", 'w', encoding='utf-8')
        file.write(str(videoInfo))
        file.close()
        if self.error:
            for danmu in danMuList:
                with open("E://弹幕数据/" + self.keyWord + "(" + str(self.startPageNum) + "-" + str(self.errPageNum) + ")String.txt", mode='a', encoding='utf-8') as f:
                    f.write(danmu)
                    f.write('\n')
            self.error = False
        winsound.Beep(500, 2000)

# Press the green button in the gutter to run the script.
if __name__ == '__main__':
    # 设置要爬取的视频关键字
    keyWordList = ['零元购', '国足', '华为', '苹果', 'ios', '为爱冲锋']
    #国足
    try:
        baind = BainduSpider()
        for keyWord in keyWordList:
            baind.keyWord = keyWord
            baind.danMuInfoList = []
            baind.allVideoDanMuInfo['data'] = []
            baind.error = True
            baind.errPageNum = 0
            baind.keyWordSearch()
    except:
        baind.saveData(baind.allVideoDanMuInfo, baind.danMuInfoList)
        print("结束")

# See PyCharm help at https://www.jetbrains.com/help/pycharm/

生成词云的代码大家可以自己写一下，下面是根据“996”、“躺平”、“美国”、“零元购”的关键字爬取的弹幕词云