跟着b站视屏爬acfun视屏（m3u8）

# https://tx-safety-video.acfun.cn/mediacloud/acfun/acfun_video/d1b7a414393175ae-e2f26d4bac178e3f6d33e56ed8e12366-hls_1080p_h264_6m_1.m3u8

import json

import os

import requests

import re

from pprint import pprint

url='https://www.acfun.cn/v/ac41909431'

url_left='https://tx-safety-video.acfun.cn/mediacloud/acfun/acfun_video/'

page=0

headers={

  'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'

}

response=requests.get(url,headers=headers,timeout=5 )

# print(response.text)

title=re.findall('"title":"(.*?)",',response.text)[1]

# title1=re.findall('"fileName":"(.*?)",',response.text)

print(title)

# main_body=re.findall('window.pageInfo = window.videoInfo =(.*?)',response.text)[0]

html_data=re.findall('window.pageInfo = window.videoInfo = (.*);',response.text)[0]

# print(response.text)

# print(type(html_data))

# print(newbee)

json_data=json.loads(html_data)

# pprint(json_data)

# print(type(json_data))

json_data1=json_data['currentVideoInfo']['ksPlayJson']

m3u8_url=json.loads(json_data1)['adaptationSet'][0]['representation'][0]['url']

# print(type(json_data2),len(json_data2))

# print(m3u8_url)

url_resp=requests.get(url=m3u8_url,headers=headers).text

# print(url_resp)

ts_info_list=re.sub('#.*','',url_resp).split()

glab=0

# exit()

for ts_info in ts_info_list:

  """  glab=glab+1

  if glab>3:

    exit()

  """

  # print(ts_info)

  complete=url_left+ts_info

  # print(complete)

  content= requests.get(complete,headers=headers).content

   

  with open('video\\'+ f'{title}.mp4','ab') as f:

    page+=1

    f.write(content)