Python 简易下载m3u8 视频

import requests,re
import sys,time
import os
import numpy as np
import glob

work_dir = os.getcwd()
#print(work_dir)

# 用来保存ts文件
file_dir = os.path.join(work_dir,‘file_tmp‘)

if not os.path.exists(file_dir):
    os.mkdir(file_dir)


def savefile(file_url):
    # 配置headers防止被墙，一般问题不大
    headers = {
        ‘user-agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36‘
    }

    r = requests.get(file_url, headers=headers)
    # 合成带有hls的m3u8地址
    if r.text.split(‘\n‘)[-1] == ‘‘:
        hls_mark = r.text.split(‘\n‘)[-2]  # 以防\n结尾
    else:
        hls_mark = r.text.split(‘\n‘)[-1]
    url_m3u8_hls = file_url.replace(‘index.m3u8‘, hls_mark)
    file_m3u8 = url_m3u8_hls.split(‘/‘)[-1]
    duqu(url_m3u8_hls,file_m3u8)
    print(url_m3u8_hls)

    ‘‘‘
    if r.status_code == 200:
        with open(file_name, ‘wb‘) as f:
            f.write(r.content)
    ‘‘‘
def duqu(index,file_m3u8):
    # 配置headers防止被墙，一般问题不大
    headers = {
        ‘user-agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36‘
    }

    r = requests.get(index, headers=headers)
    with open(‘file_tmp/‘+file_m3u8, ‘wb‘) as f:
        f.write(r.content)
        f.close()
    xieru(file_m3u8,index)
def xieru(file_m3u8,index):
    with open(‘file_tmp/‘+file_m3u8,‘r‘) as f:
        r = f.read()
        f.close()
    # 合成带有hls的m3u8地址
    # iter_lines得到的是bytesstring
    text_bytes = r.split(‘\n‘)
    # 转化成正常string
    #text_string = [i.decode(‘utf-8‘) for i in text_bytes]
    # 筛选以.ts结尾的行
    # 有些情况下可能是以其他格式的文件，比如png，下载后修改后缀即可
    # ts_name = [i for i in text_string if i.endswith(‘.ts‘)]
    ts_name = [i for i in text_bytes if  i.startswith(‘#EXTINF‘)]
    ts_neirong = [i for i in text_bytes if not i.startswith(‘#‘)]
    ts_neirong.pop()
    #xiazai(ts_neirong,index)
    #print(ts_neirong)

    if ‘#‘ in ts_name:
        # 部分ts文件名中带有路径信息，只保留文件名即可
        #ts_name = [i.split(‘/‘)[-1] for i in ts_name]
        # 筛选带有时间的行
        url_xiazai = ts_name.replace(‘#EXTINF:‘, ‘‘)

        print(ts_time[:3])
def xiazai(ts_neirong,index):
    # 配置headers防止被墙，一般问题不大
    headers = {
        ‘user-agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36‘
    }
    for i in range(len(ts_neirong)):
        hls_mark = index.split(‘/‘)[-1]
        url_xiazai = index.replace(hls_mark, ts_neirong[i])
        print(url_xiazai)
        r = requests.get(url_xiazai, headers=headers)
        with open(‘file_tmp/‘+ts_neirong[i], ‘wb‘) as f:
            f.write(r.content)
            f.close()
url= ‘http://iqiyi.cdn9-okzy.com/20200907/15137_ed25d8c5/index.m3u8‘ #输入m3u8

savefile(url)