摘自:https://www.cnblogs.com/python147/p/14511627.html
1.前言
本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,如有问题请及时联系我们以作处理。
PS:如有需要Python学习资料的小伙伴可以点击下方链接自行获取
爬取视频的时候发现,现在的视频都是经过加密(m3u8),不再是mp4或者avi链接直接在网页显示,都是经过加密形成ts文件分段进行播放。
今天就教大家如果通过python爬取下载m3u8加密视频。
2.分析网页
1.电影视频来源
http://www.caisetv.com/
2.分析m3u8加密目录
http://www.caisetv.com/dongzuopian/chaidanzhuanjia/0-1.html
在视频播放的页面,通过F12可以查看网络数据包
https://xigua-cdn.haima-zuida.com/20210219/19948_fcbc225a/1000k/hls/index.m3u8
这里的ts就电影的加密分段视频
https://xigua-cdn.haima-zuida.com/20210219/19948_fcbc225a/1000k/hls/
上面的m3u8链接掉index.m3u8后,在拼上075a34cccdd000000.ts等ts名称就是分段视频的链接
如下所示:
https://xigua-cdn.haima-zuida.com/20210219/19948_fcbc225a/1000k/hls/075a34cccdd000000.ts
通过浏览器把这个分段视频下载后打开:
所以只要把所有的ts下载并合并就是完整的电影视频!!!
3.下载ts
1.下载ts分段视频
刚刚已经把ts的所有名称下载下来了
接下来通过python代码去读取这个文件,提取出名称,拼接链接后下载保存到一个文件夹里!
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0',}
###下载ts文件
def download(url,name):
r = requests.get(url, headers=headers)
with open(name+"", "wb") as code:
code.write(r.content)
with open("index.m3u8","r") as f:
ts_list = f.readlines()
#去掉前面没用的信息
ts_list = ts_list[5:]
urlheader="https://xigua-cdn.haima-zuida.com/20210219/19948_fcbc225a/1000k/hls/"
count = 0
for i in ts_list:
if "#" not in i:
i = i.replace("\n","")
download(urlheader+""+i,"cdzj2/"+str(count)+".ts")
count = count+1
print(count)
这样就可以把ts文件全部下载下来,但是一个一个下载很慢,下面通过多线程下载,提升下载速度!!!
2.多线程下载ts视频
for i in ts_list:
if "#" not in i:
i = i.replace("\n","")
n = i[-7:]
threading.Thread(target=download, args=(urlheader+""+i,"cdzj2/"+str(n),)).start()
#download(urlheader+""+i,"cdzj2/"+str(count)+".ts")
通过多线程很快就可以将这些ts文件下载到本地!!!
4.合并ts
cmd合并文件
copy /b *.ts new.mp4
通过这个命令(cmd终端中运行),在含有ts文件的文件夹中就可以将ts文件合并(按名称顺序进行排列合并),并保存成new.mp4
5.总结
1.分析m3u8加密文件
2.python下载ts文件
3.cmd合并ts保存成mp4格式
6.我的代码(全)
1 # -*- coding:utf-8 -*- 2 import os 3 import requests 4 import shutil 5 import time 6 import threading 7 8 9 def download(url, name): 10 """下载ts文件""" 11 12 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0', } 13 r = requests.get(url, headers=headers) 14 with open(name + "", "wb") as code: 15 code.write(r.content) 16 17 18 def m3u8_download_multi_thread(m3u8, mp4, thread_max=10): 19 ts_in = mp4 + os.sep + "ts" 20 if not os.path.exists(ts_in): 21 os.makedirs(ts_in) # mkdir -p ./a/b/c 22 23 urlheader = os.path.dirname(m3u8) 24 m3u8_local = mp4 + "/index.m3u8" 25 26 download(m3u8, m3u8_local) 27 28 with open(m3u8_local, "r") as f: 29 ts_list = f.readlines() 30 31 # 多线程 32 line = 0 33 count = 0 34 for i in ts_list: 35 # if count >= 10: 36 # break 37 line = line + 1 38 while thread_max <= len(threading.enumerate()): 39 time.sleep(1) 40 if "#" not in i: 41 count = count + 1 42 i = i.replace("\n", "") 43 print("line[%d]=%s" % (line, i)) 44 n = os.path.basename(i) 45 try: 46 threading.Thread(target=download, args=(urlheader + "/" + i, ts_in + "/" + str(n),)).start() 47 # download(urlheader+""+i,"cdzj2/"+str(count)+".ts") 48 except Exception as e: 49 print("threading.cnt=%d" % len(threading.enumerate())) 50 51 # 等待所有子线程结束 52 while 1 < len(threading.enumerate()): 53 time.sleep(1) 54 # print("thread_count=%d" % len(threading.enumerate())) 55 56 57 def m3u8_download_single_thread(m3u8, mp4): 58 ts_in = mp4 + os.sep + "ts" 59 if not os.path.exists(ts_in): 60 os.makedirs(ts_in) 61 62 urlheader = os.path.dirname(m3u8) 63 m3u8_local = mp4 + "/index.m3u8" 64 65 download(m3u8, m3u8_local) 66 67 with open(m3u8_local, "r") as f: 68 ts_list = f.readlines() 69 70 # 单线程 71 line = 0 72 for i in ts_list: 73 line = line + 1 74 if "#" not in i: 75 print("line[%d]=%s" % (line, i)) 76 i = i.replace("\n", "") 77 n = os.path.basename(i) 78 download(urlheader + "/" + i, ts_in + "/" + str(n) + ".ts") 79 80 81 def ts_join(mp4): 82 if os.path.exists(mp4 + os.sep + mp4): 83 os.remove(mp4 + os.sep + mp4) 84 85 os.chdir(mp4 + "/ts") 86 87 # copy /b *.ts new.mp4 88 with os.popen("copy /b *.ts " + mp4, "r") as p: 89 l = p.read() 90 print(l) 91 shutil.move(mp4, "..") 92 93 94 if __name__ == '__main__': 95 m3u8 = "https://p2.bdstatic.com/rtmp.liveshow.lss-user.baidubce.com/live/stream_bduid_3041161111_7873701187/merged_1669738224764_293317_1160_30460.m3u8" 96 mp4 = "神舟十五号.mp4" 97 m3u8_download_multi_thread(m3u8, mp4) 98 # m3u8_download_single_thread(m3u8, mp4) 99 ts_join(mp4)
标签:count,视频,OK,m3u8,ts,mp4,多线程,下载 From: https://www.cnblogs.com/LiuYanYGZ/p/16937272.html