B站弹幕爬虫

python爬取B站弹幕爬虫

import requests
from xmltodict import parse
import pandas as pd

  

 

  
1
  
2
  
3
 

bullet_screen = []
"""BV号转cid函数"""
def CIDget(bvid):#获取视频cid url="https://api.bilibili.com/x/player/pagelist?bvid="+str(bvid)+"&jsonp=jsonp" response=requests.get(url) dirt=json.loads(response.text) cid=dirt['data'][0]['cid'] #cid号已得到 nowDMget(cid)#调用爬取弹幕函数
"""爬取当前的弹幕函数"""
def nowDMget(cid):#获取今天的弹幕  url="https://api.bilibili.com/x/v1/dm/list.so?oid="+str(cid) response=requests.get(url) response.encoding='utf-8' data=parse(response.text)#解析xml为有序字典 liat_DM=data['i']['d'] print(len(liat_DM)) for i in range(len(liat_DM)): print(liat_DM[i]['#text']) bullet_screen.append(liat_DM[i]["#text"])

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
 

CIDget("BV1vy4y1i7bS")
data = pd.DataFrame({"弹幕":bullet_screen})
data.to_excel("bingbing.xlsx") 
  

 

  
1
  
2
  
3
 

展示：

文章来源: beishan.blog.csdn.net，作者：北山啦，版权归原作者所有，如需转载，请联系作者。

原文链接：beishan.blog.csdn.net/article/details/112234136