用python爬取B站弹幕-小白级

最新推荐文章于 2024-03-31 19:20:14 发布

Asssshzy

最新推荐文章于 2024-03-31 19:20:14 发布

阅读量358

点赞数 2

文章标签： python

本文链接：https://blog.csdn.net/Asssshzy/article/details/108006951

版权

小白用来练手的~
欢迎指出不足！！

import requests
import re

#1.url
url='https://api.bilibili.com/x/v2/dm/history?type=1&oid=158237505&date=2020-07-24'
#2.模拟浏览器发送请求和接收响应
headers={
    
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36",
    "cookie": "_uuid=C69B827E-9B0E-1FF3-294C-DE624162060043168infoc; buvid3=F449AB21-B42A-48CA-BC0E-925ACC97DCA153949infoc; sid=hz5t6lpe; CURRENT_FNVAL=16; LIVE_BUVID=AUTO3715819124973159; rpdid=|(u~)|mlYlYl0J'ul)umukl|m; im_notify_type_34000160=0; CURRENT_QUALITY=64; DedeUserID=34000160; DedeUserID__ckMd5=dac27b25482efead; SESSDATA=0edde50c%2C1600082785%2Ccc335*31; bili_jct=f5b8fb6bb6bd37b3909dc2c8793bedc8; PVID=1; _ga=GA1.2.234555465.1584540191; bsource=search_baidu; bfe_id=5db70a86bd1cbe8a88817507134f7bb5"
    
        }

resp=requests.get(url,headers=headers)
#乱码问题
html_doc=resp.content.decode('utf-8')

#3.解析网页数据
res=re.compile('<d.*?>(.*?)</d>')
danmu=re.findall(res,html_doc)
print(danmu)