python下载，需要密钥版下载，多线程版【二】

#多线程赋值用字典格式 试下第二种方法 顺便把for循环 用正则表达 看能不能快点
#适应两种 m3u8 读取的格式

import requests
import os
import datetime
import threading
import re
from queue import Queue
import random
import sys
from fake_useragent import UserAgent
#下载耗时：0:00:47
class xiazai():
    def __init__(self):
        self.url = xiazaidizhi
        work_dir = os.getcwd()
        # print(work_dir)
        # 用来保存ts文件
        file_dir = os.path.join(work_dir, wenjian)
        if not os.path.exists(file_dir):
            os.mkdir(file_dir)
        user_agent_list =[
            'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',
                       'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36',
                       'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36',
                       'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36',
                       'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
                       'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36',
                       'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0.6',
                       'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36',
                       'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36',
                       'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36'
        ]
        #t = random.choice(user_agent_list)
        t = UserAgent(use_cache_server=False, verify_ssl=False).random
        self.headers={
            'User-Agent':t
        }
        self.savefile()

    def savefile(self):
        r = requests.get(self.url, headers=self.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
            hls_mark = hls_mark.split('/')
            if len(hls_mark) > 3:
                hls_mark = '/'.join(hls_mark[-3:])
                self.base_url = re.split(r"[a-zA-Z0-9-_\.]+\.m3u8", self.url)[0]
                url_m3u8_hls = self.base_url + hls_mark
                print(url_m3u8_hls)
                # url_m3u8_hls = file_url.replace('index.m3u8', hls_mark)
                # file_m3u8 = url_m3u8_hls.split('/')[-1]
                return url_m3u8_hls
                # print(url_m3u8_hls)
            else:
                hls_mark = '/'.join(hls_mark[-3:])
                # self.base_url = re.split(r"[a-zA-Z0-9-_\.]+\.m3u8", self.url)[0]
                self.base_url = self.url.split('/')[:3]
                self.base_url = '/'.join(self.base_url)
                url_m3u8_hls = self.base_url + hls_mark
                print(url_m3u8_hls)
                # url_m3u8_hls = file_url.replace('index.m3u8', hls_mark)
                # file_m3u8 = url_m3u8_hls.split('/')[-1]
                return url_m3u8_hls
                # print(url_m3u8_hls)
        else:
            hls_mark = r.text.split('\n')[-1]
            hls_mark = hls_mark.split('/')
            if len(hls_mark) > 3:
                hls_mark = '/'.join(hls_mark[-3:])
                self.base_url = re.split(r"[a-zA-Z0-9-_\.]+\.m3u8", self.url)[0]
                url_m3u8_hls = self.base_url + hls_mark
                print(url_m3u8_hls)
                # url_m3u8_hls = file_url.replace('index.m3u8', hls_mark)
                # file_m3u8 = url_m3u8_hls.split('/')[-1]
                return url_m3u8_hls
                # print(url_m3u8_hls)
            else:
                hls_mark = '/'.join(hls_mark[-3:])
                #self.base_url = re.split(r"[a-zA-Z0-9-_\.]+\.m3u8", self.url)[0]
                self.base_url = self.url.split('/')[:3]
                self.base_url = '/'.join(self.base_url)
                url_m3u8_hls = self.base_url + hls_mark
                print(url_m3u8_hls)
                # url_m3u8_hls = file_url.replace('index.m3u8', hls_mark)
                # file_m3u8 = url_m3u8_hls.split('/')[-1]
                return url_m3u8_hls
                # print(url_m3u8_hls)

class xiazai1():
    def __init__(self):
        user_agent_list = [
            'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',
            'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36',
            'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36',
            'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36',
            'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
            'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36',
            'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0.6',
            'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36',
            'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36',
            'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36'
        ]
        t = UserAgent(use_cache_server=False, verify_ssl=False).random
        self.headers = {
            'User-Agent': t
        }

    def index(self):
        global url_m3u8_hls
        url_m3u8_hls = xiazai().savefile()
        try:
            r = requests.get(url_m3u8_hls, headers=self.headers).text
            # base_url = re.split(r"[a-zA-Z0-9-_\.]+\.m3u8", url_m3u8_hls)[0]
            with open(wenjian + '/' + 'index1.m3u8', 'w') as f:
                f.write(r)
                f.close()
        except:
            print('下载失败！')

    def tihuan(self):
        try:
            with open(wenjian + '/'+ 'index1.m3u8', 'r') as f:
                r = f.read()
                f.close()
            text_bytes = r.split('\n')
            return text_bytes
        except:
            print('下载失败！')

    def url(self):
        text_bytes = self.tihuan()
        dizhi_1 = []
        url_1 = []
        for miyao in text_bytes:
            if '.ts' in miyao:
                m = miyao.split('/')
                dizhi = m[-1]
                dizhi_1.append(dizhi)

                url = miyao
                url_1.append(url)

        return (dizhi_1, url_1)

    def key(self):
        text_bytes = self.tihuan()
        for miyao in text_bytes:
            if 'EXT-X-KEY' in miyao:
                miyao = miyao.replace('"', '')
                key = miyao.split('/')[1:]
                key = '/'.join(key)
                key = '/' + key
                return key

    def index_shengcheng(self):
        key1 = self.key()
        dizhi, url1 = self.url()
        try:
            with open(wenjian + '/' + 'index1.m3u8', 'r') as f:
                lines = f.readlines()  # 读取文本每一行
                list = []
                f = open(wenjian+'/'+'index.m3u8', 'w')
                for i in range(len(lines)):
                    list.append(lines[i])  # 将每一行的数据加入列表
                    if key1 in list[i]:
                        list[i] = re.sub(key1, 'key.key', list[i])
                    for t in range(len(dizhi)):
                        if dizhi[t] in list[i]:
                            list[i] = re.sub(url1[t], dizhi[t], list[i])
                        # print(list[i])
                    f.write(list[i])
        except:
            print('错误！')

    def duqu(self):
        #url_m3u8_hls = xiazai().savefile()
        try:
            r = requests.get(url_m3u8_hls, headers=self.headers).text
            base_url = re.split(r"[a-zA-Z0-9-_\.]+\.m3u8", url_m3u8_hls)[0]
            text_bytes = r.split('\n')
            # 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_time = [i for i in text_bytes if i.startswith('#EXTINF')]
            dm_time = 0
            for i in range(len(ts_time)):
                ts_time1 = ts_time[i].replace('#EXTINF:', '')
                ts_time2 = ts_time1.replace(',', '')
                dm_time = float(ts_time2) + dm_time
            '''
            # self.shijian(dm_time)
            ts_queue = Queue(10000)
            concatfile = wenjian+'/' + "s" + '.txt'
            # print(dm_time)
            for miyao in text_bytes:
                if 'EXT-X-KEY' in miyao:
                    miyao = miyao.replace('"','')
                    key = miyao.split('/')[1:]
                    key= '/'.join(key)
                    zhu_url = url_m3u8_hls.split('/')[:3]
                    zhu_url = '/'.join(zhu_url)
                    key_url = zhu_url + '/'+ key
                    r = requests.get(key_url, headers=self.headers)
                    with open(wenjian + '/'+'key.key','w') as f:
                        f.write(r.text)
                        f.close()
            for line in text_bytes:
                if '.ts' in line:
                    m = line.split('/')
                    if 'http' in line:
                        # print("ts>>", line)
                        ts_queue.put(line)
                    else:
                        if len(m) >=3:
                            base_url1 = url_m3u8_hls.split('/')[:3]
                            base_url1 = '/'.join(base_url1)
                            line = base_url1 + line
                            # print(line)
                            ts_queue.put(line)
                        else:
                            line = base_url + line
                            # print(line)
                            ts_queue.put(line)
                            # print(ts_queue.put(line))
                            # print('ts>>',line)
                    filename = re.search('([a-zA-Z0-9-]+.ts)', line).group(1).strip()
                    open(concatfile, 'a+').write("file %s\n" % filename)
                    # filename = re.search('([a-zA-Z0-9-]+.ts)', line).group(1).strip()
                    # ts_neirong = [i for i in text_bytes if not i.startswith('#')]
                    # ts_neirong.pop()
                    # self.xiazai(ts_neirong,url_m3u8_hls)
                    # print(ts_neirong)
            return ts_queue
        except:
            print('连接失败')
            sys.exit()

    def shijian(self,dm_time):
        shichang_time = str(datetime.timedelta(seconds=dm_time))
        print('视频时长：%s' % shichang_time)
    def xiazai1(self,ts_queue):
        #ffmpeg -f concat -safe 0 -i s.txt -c copy output.mp4
        #tt_name = threading.current_thread().getName()
        while not ts_queue.empty():
            url = ts_queue.get()
            try:
                r = requests.get(url, stream=True, headers=self.headers)
                filename = re.search('([a-zA-Z0-9-]+.ts)', url).group(1).strip()
                with open(wenjian+'/' + filename, 'wb') as fp:
                    fp.write(r.content)
                #print(tt_name + " " + filename + ' 下载成功')
            except:
                with open(wenjian+ '/'+ 'shibai.txt', 'a') as fp:
                    fp.write(url + '\n')
                print(url + '下载失败')




    def hebing(self,name):
        basedir = os.path.abspath(os.path.dirname(__file__))
        t = 'start /d "%s\%s" ffmpeg -f concat -safe 0 -i s.txt -c copy %s.mp4' %(basedir,wenjian,name)
        with open('2.bat', 'w') as f:
            f.write(t)
            f.close()
        # os.system(r'D:\Study\pythonProject\Python_down_m3u8\2.bat')
        os.startfile("2.bat")

if __name__=='__main__':
    #xiazai('http://iqiyi.cdn9-okzy.com/20201019/16908_b0f2428f/index.m3u8')
    xiazaidizhi = input("请输入m3u8链接：")
    wenjian = input("请输入保存文件名：")
    start = datetime.datetime.now().replace(microsecond=0)
    xiazai1().index()
    xiazai1().index_shengcheng()
    s = xiazai1().duqu()
    #print(s)
    # print(s,concatfile)
    threads = []
    for i in range(30):
        t = threading.Thread(target=xiazai1().xiazai1, name='th-' + str(i), kwargs={'ts_queue': s})
        threads.append(t)
    for t in threads:
        t.start()
    for t in threads:
        t.join()
    end = datetime.datetime.now().replace(microsecond=0)
    print('下载耗时：' + str(end - start))


#下载耗时：0:01:23

下载完会出来

 

 外加很多tx文件