爬取咪哩咪哩动漫视频

# -*- coding: utf-8 -*-
# __author__ = "maple"
import os
import subprocess
import time

import requests
import re
import concurrent.futures
from lxml import etree
#http://dalao.wahaha-kuyun.com/20201122/1556_fd900088/1000k/hls/228f9bea95b000033.ts  ts文件
'''
http://dalao.wahaha-kuyun.com/   20201122    /1556_fd900088/     1000k/hls/228f9bea95b000033.ts
我们观察几个ts链接（不同视频）看到ts链接共分为三部分  时间  id  ts文件名
1，先找ts文件名是怎么来的  复制一个名字全局搜索  可以看到在一个index.m3u8地址返回的内容里面
2,查找这个 index.m3u8地址是哪里来的  全局搜索可以看到是那个地址返回的内容有这个链接  
3，分析找到的地址参数  
'''



def get_m3u8(url,id,nub):
    '''
    获取m3u8地址,视频名称
    :param url:
    :return:
    '''
    headers = {
        'User-Agent':"User-Agent:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) "

    }
    urls = f'http://www.milimili.tv/anime/{id}/{nub}/'
    response = requests.get(url).text
    m3u8_url = re.findall("src='/yun/yun\.php\?vid=(.*?)'", response)[0]
    new_m3u8_url = m3u8_url.replace('index.m3u8', '1000k/hls/index.m3u8')
    res = requests.get(urls,headers=headers).text
    ret = etree.HTML(res)
    name = ''.join(ret.xpath('/html/body/div[2]/div[1]//text()')).replace('>','').replace(' ','').replace('咪哩咪哩','')
    return new_m3u8_url,name
def get_ts_url(url):
    '''
    获取ts视频流地址
    :param url:
    :return:
    '''
    response = requests.get(url).text
    ts_list = re.findall('(.*?).ts', response)
    li = {}
    for ts in ts_list:
        ts_url = url.replace('index.m3u8', ts) + '.ts'
        li[ts] = ts_url
    return li

def save_video(url,name):
    '''
    保存视频
    :param url:
    :return:
    '''
    response = requests.get(url).content
    with open(name+'.ts','wb') as f: #地址改成自己的
        f.write(response)
    print(name)

if __name__ == '__main__':
    executor = concurrent.futures.ThreadPoolExecutor(max_workers=10)
    id = int(input('请输入视频id：').strip())                                                   # id  集数
    nub = int(input('请输入视频集数：').strip()) #集数根据地址栏为准 列http://www.milimili.tv/anime/3753/13/
    url = f'http://www.milimili.tv/e/action/player_i.php?id={id}&pid={nub}'
    new_m3u8_url,video_name = get_m3u8(url,id,nub)
    ts_dict = get_ts_url(new_m3u8_url)
    for name in ts_dict:
        executor.submit(save_video, ts_dict[name],name)
    executor.shutdown()
    print('====正在合成视频：{}===='.format(video_name))
    command = 'copy /b *.ts {}.mp4'.format(video_name)
    subprocess.Popen(command, shell=True)
    time.sleep(10)
    print('====合成视频成功：{}===='.format(video_name))
    for ts in ts_dict:
        os.remove(f'{ts}.ts')