视频地址 https://www.bilibili.com/bangumi/play/ss39462?spm_id_from=333.851.b_62696c695f7265706f72745f616e696d65.52
弹幕地址  固定的url地址 + 视频的cid+.xml  -- 源码搜索cid
比如:https://comment.bilibili.com/428471132.xml  

数据获取部分
# 完整代码
#   获取数据
import requests
from bs4 import BeautifulSoup
import pandas as pd

cid = 428471132
url = "https://comment.bilibili.com/{}.xml".format(cid)
response  = requests.get(url)
response.encoding = "utf-8"
#print(response.text)

#  解析数据
soup = BeautifulSoup(response.text,"lxml")
datas = soup.select('d')
#print(datas[0])

# 获取弹幕文字内容
comments = [data.text for data in datas]  
#print(comments)

#  属性信息
#  出现时间点 模式 字体 颜色 发送时间 弹幕词 用户ID  rowID 等
info_comments = [data.get('p').split(',') for data in datas] #  获取弹幕属性信息
#print(info_comments)

# 数据存储  
columns = ["出现时间点","模式","字体","颜色","发送时间","弹幕池","用户ID","rowID","未知参数"]
comment_datas = pd.DataFrame(info_comments,columns=columns)
#print(comment_datas)

# 数据组合
comment_datas["comments"] = comments
#print(comment_datas)
# 数据存储
comment_datas.to_csv("comments.csv",encoding="utf-8-sig")
print("finish...")
数据分析部分

一 绘制词云图

  # 加载数据
  import pandas as pd
  comment_datas = pd.read_csv("comments.csv",encoding="utf-8-sig")
  print(comment_datas)

##  绘制词云图
import jieba 
from tkinter import _flatten
import matplotlib.pyplot as plt 
from wordcloud import WordCloud 

#   数据获取
comments = comment_datas["comments"]
#    分词
jieba.load_userdict("hong.txt")  #  加载用户自定义词典
comments_cut = comments.apply(jieba.lcut)  # 对弹幕进行分词
#print(comments_cut)

#  去除停用词
with open("stoplist.txt","r",encoding="utf-8") as f:
    stop_words = f.read()
stop_words += "\n"
stop_words += ""
comments_after = comments_cut.apply(lambda x:[i for i in x if i not in stop_words])
#print(comments_after)

#    词频统计
results = _flatten(list(comments_after))
#print(results)
word_count=pd.Series(results).value_counts()
#print(word_count)

#    绘制词云  https://tool.lu/cutout/
pic = plt.imread("aixin.jpg")  #  读取一张词云轮廓
word_cloud = WordCloud(mask=pic,background_color='white',font_path="C:\Windows\Fonts\simhei.ttf")
word_cloud.fit_words(word_count)
plt.imshow(word_cloud)
plt.axis('off')
二 分析弹幕数量与日期,时间的关系
#  分析弹幕数量与日期,时间的关系


#  加载数据
import pandas as pd
from datetime import datetime

comment_datas = pd.read_csv("comments.csv",encoding="utf-8-sig")
comment_datas["发送时间"] = comment_datas["发送时间"].apply(lambda x :datetime.fromtimestamp(x).strftime('%Y-%m-%d %H:%M:%S'))
#print(comment_datas)

#  分析弹幕数量与日期,时间的关系

userID = comment_datas["用户ID"]
#print(userID)
#  每个用户发送多少次弹幕
userID_count = comment_datas["用户ID"].value_counts()
#print(userID_count)

#  求取发送次数弹幕的用户量
userID_count_count = comment_datas["用户ID"].value_counts().value_counts()
#print(userID_count_count)

#  排序依据大小排列
userID_count_count_sort = comment_datas["用户ID"].value_counts().value_counts().sort_index()
print(userID_count_count_sort)

#num = userID_count_count_sort[:6]
num = userID_count_count_sort[6:]
#num.append(userID_count_count_sort[6:].sum())
print(num.sum())

##  绘制条形图
import matplotlib.pyplot as plt 
num = userID_count_count_sort[:6]
plt.style.use('ggplot')
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.bar(range(6),num)
plt.xlabel("弹幕数量")
plt.ylabel("用户数量")
plt.title("弹幕发布数量分布图")
plt.show()

##  弹幕数量随时间变化图
#  去除时分秒的影响
dates = pd.to_datetime(comment_datas["发送时间"])
dates = [date.date() for date in dates]
dates = pd.Series(dates)
num = dates.value_counts().sort_index()
#print(date_counts)

#  绘制折线图
plt.figure(figsize=(16,9))
plt.plot(range(len(num)),num)
#plt.xticks(range(len(num))[::7],num.index[::7],rotation=45)
plt.xticks(range(len(num)),num.index,rotation=45)
plt.ylabel("弹幕数量")
plt.xlabel("日期变化")
plt.title("弹幕发布数量随日期变化图")
plt.show()


###  分析弹幕数量与日期,时间的关系 -- 以周为研究对象
import pandas as pd
comment_datas = pd.read_csv("comments.csv",encoding="utf-8-sig")
#comment_datas["发送时间"]
comment_datas["发送时间"] = comment_datas["发送时间"].apply(lambda x :datetime.fromtimestamp(x).strftime('%Y-%m-%d %H:%M:%S'))

dates = pd.to_datetime(comment_datas["发送时间"])
#print(dates)
date = pd.Series(dates.dt.weekday)
#print(date)
date_count = date.value_counts().sort_index()
#print(date_count)

plt.figure(figsize=(16,9))
plt.plot(range(len(date_count)),date_count)
plt.xticks(range(len(date_count)),["周日","周一","周二","周三","周四","周五","周六"],rotation=45)
plt.ylabel("弹幕数量")
plt.xlabel("日期变化")
plt.title("弹幕发布数量随日期变化图")
plt.show()