python3 下载.m3u8, 合并视频.ts 文件并合成为mp4格式的视频

### 欢迎访问我的博客 blog.ayla1688.cool, 原文地址：http://blog.ayla1688.cool/archives/314.html

 

### 推荐
**浏览器：**      chrome
**python版本:**  python3

### 找.m3u8文件

* 在视频播放页面打开开发者模式 ```f12```,
* 找到.m3u8格式的文件，文件内容如下：
```

#EXTM3U
#EXT-X-VERSION:3
#EXT-X-TARGETDURATION:7
#EXT-X-MEDIA-SEQUENCE:0
#EXTINF:6.266667,
6d9935d97da000000.ts
#EXTINF:2.866667,
6d9935d97da000001.ts
#EXTINF:4.566667,
6d9935d97da000002.ts
#EXTINF:2.366667,
6d9935d97da000003.ts
#EXTINF:4.966667,
6d9935d97da000004.ts
#EXTINF:3.333333,
6d9935d97da000005.ts
#EXTINF:5.233333,
6d9935d97da000006.ts
#EXTINF:2.533333,
....
```

将 ```.m3u8```格式文件下载，重命名为```jiangziya```, 不带文件后缀。

### 下载.ts文件并合并

```
# https://youku.cdn7-okzy.com/20201004/20968_67a726a5/1000k/hls/6d9935d97da000138.ts

import requests
import threading
import os
import datetime
import time

count = 0

# 获取所有ts视频的链接地址
def get_ts_urls():
    urls = []

    with open( os.getcwd() + "/ts/jiangziya", "r") as file:
        lines = file.readlines()
        for line in lines:
            if line.endswith(".ts\n"):
                urls.append("https://youku.cdn7-okzy.com/20201004/20968_67a726a5/1000k/hls/" + line.strip("\n"))

    return urls

# 开启多个进程
def threadDownload(start, end, urls):
    global count

    headers = {'Origin': 'http://www.86cg.tv',
               'Referer': 'http://www.86cg.tv/online/85620-1-1.html',
               'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'}
    download_path = os.getcwd() + "/ts/"

    for url in urls[start:end]:
        try:
            response = requests.get(url, stream=True, verify=False, headers=headers)
        except Exception as e:
            print("请求异常：%s" % e.args)
            exit(0)

        ts_path = download_path + url.split("/")[-1]
        with open(ts_path, "wb") as file:
            file.write(response.content)
        count += 1
        print("下载进度：%.2f" % (count / len(urls)))

# 下载， 开启100个进程， 每个进程下载50个.ts文件
def download(urls):
    num_thread = 100
    part = 50
    for i in range(num_thread):
        start = part * i
        if i == num_thread - 1:
            end = len(urls)
        else:
            end = start + part
        t = threading.Thread(target=threadDownload, kwargs={'start': start, 'end': end, 'urls': urls})
        t.setDaemon(True)
        t.start()

    main_thread = threading.current_thread()
    for t in threading.enumerate():
        if t is main_thread:
            continue
        t.join()

# 合并.ts 文件
def combine(files):
    root_path = os.getcwd() + "/ts/"
    file_name = "jiangziya.ts"
    with open(root_path + file_name, "wb+") as file:
        for i in range(len(files)):
            file.write(open(files[i], "rb").read())

    print("合并完成")

# 查找文件夹下所有的.ts格式文件
def fileWalker():
    root_path = os.getcwd() + "/ts"
    file_list = []

    for files in os.walk(root_path):
        # print(files)
        files[2].sort()
        for fn in files[2]:
            if fn.endswith(".ts"):
                file_list.append(root_path + "/" + fn)

    return file_list

if __name__ == "__main__":
    print("开始下载......")
    start = int(time.time())
    urls = get_ts_urls()
    download(urls)
    print("下载完成，开始合并ts文件")
    files = fileWalker()
    combine(files)
    end = int(time.time())

    print("下载完成，一共用时：%d" % (end-start))

```