python 下载m3u8视频「建议收藏」

大家好，又见面了，我是你们的朋友全栈君。

有一个朋友，通过一个网站（https://leetcode-cn.com/problems/course-schedule/solution/ke-cheng-biao-by-leetcode-solution/），看到一个视频，感觉不错，就想下载下来，可是下载不了，然后就求助与我，（此处省略一万字废话。。。）下面进入正题。

• 网页界面如下图所示，红框中的即为将要下载的视频：

• 按F12，打开开发者工具，清除会话记录，然后刷新网页

• 下载该文件，文件内容如下：

代码如下：

import os
import requests

headers = {
    "accept": "*/*",
    "accept-encoding": "gzip, deflate, br",
    "accept-language": "zh-CN,zh;q=0.9",
    "cache-control": "no-cache",
    "origin": "https://leetcode-cn.com",
    "pragma": "no-cache",
    "referer": "https://leetcode-cn.com/problems/course-schedule/solution/ke-cheng-biao-by-leetcode-solution/",
    "sec-fetch-dest": "empty",
    "sec-fetch-mode": "cors",
    "sec-fetch-site": "same-site",
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36",
}


def get_m3u8_file(m3u8_url, file_path):
    """
    下载m3u8文件
    :param m3u8_url: m3u8文件的URL
    :param file_path: 要下载的文件位置
    :return:
    """
    resp = requests.get(m3u8_url, headers=headers)
    if resp.status_code == 200:
        content = resp.text
        with open(file_path, "w") as f:
            f.write(content)

•  然后在输入框搜索“ts”，点击其中一个，发现ts文件请求URL除了最后两位数字不同（依次增加）以外，其他全部一致，而且和m3u8文件中的ts文件名称一致

•  获取ts文件名称（筛选出以“.ts”结尾的行或者筛除以“#”开头的行）

代码如下：

import os


def get_ts_name_list(file_path):
    """
    获取ts文件名称列表
    :param file_path: m3u8文件路径
    :return: ts文件名称列表
    """
    ts_name_list = []
    with open(file_path, "rb") as f:
        cont_list = f.readlines()
    for cont in cont_list:
        cont = cont.decode().strip()
        if cont.endswith(".ts"):
            ts_name_list.append(cont.split("/")[-1])
            # if not cont.startswith("#"):
            #     ts_name_list.append(cont.split("/")[-1])
    return ts_name_list

运行结果：

[‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00001.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00002.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00003.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00004.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00005.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00006.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00007.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00008.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00009.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00010.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00011.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00012.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00013.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00014.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00015.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00016.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00017.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00018.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00019.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00020.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00021.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00022.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00023.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00024.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00025.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00026.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00027.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00028.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00029.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00030.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00031.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00032.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00033.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00034.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00035.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00036.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00037.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00038.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00039.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00040.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00041.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00042.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00043.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00044.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00045.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00046.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00047.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00048.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00049.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00050.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00051.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00052.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00053.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00054.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00055.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00056.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00057.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00058.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00059.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00060.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00061.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00062.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00063.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00064.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00065.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00066.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00067.ts’, ‘c5c5c3d84d7b4c70bdef21cd7ef011e6-942a9205b7a3d6bdf7b63fbc60a35b45-hd-00068.ts’]

• 下载ts文件

代码如下：

def get_ts_files(file_dir, ts_url_template, ts_name_list):
    """
    循环下载ts文件
    :param file_dir: 文件下载所在文件夹
    :param ts_url_template: ts文件请求URL模板
    :param ts_name_list: ts文件名称列表
    :return: 
    """
    for ts_name in ts_name_list:
        ts_url = ts_url_template + ts_name
        resp = requests.get(ts_url, headers=headers)
        if resp.status_code == 200:
            with open(os.path.join(file_dir, ts_name), "wb") as f:
                f.write(resp.content)
            print("%s-->下载成功！" % ts_name)
        else:
            print("%s-->下载失败！" % ts_name)

运行结果如下：

• 将所有的ts文件合并成一个整体的ts文件

代码如下：

def merge_ts_files(file_dir, file_name, ts_name_list):
    """
    将多个ts文件进行合并
    :param file_dir: ts文件所在文件夹
    :param file_name: 合并后的文件名称
    :param ts_name_list: ts文件名称列表
    :return: 
    """
    file_out = os.path.join(file_dir, file_name)
    with open(file_out, 'wb') as f_out:
        for ts_name in ts_name_list:
            with open(os.path.join(file_dir, ts_name), "rb") as f_in:
                f_out.write(f_in.read())
    print("合并ts文件成功！")

• 大功告成，看效果

最后附上全部代码（可直接运行）：

import os
import requests

headers = {
    "accept": "*/*",
    "accept-encoding": "gzip, deflate, br",
    "accept-language": "zh-CN,zh;q=0.9",
    "cache-control": "no-cache",
    "origin": "https://leetcode-cn.com",
    "pragma": "no-cache",
    "referer": "https://leetcode-cn.com/problems/course-schedule/solution/ke-cheng-biao-by-leetcode-solution/",
    "sec-fetch-dest": "empty",
    "sec-fetch-mode": "cors",
    "sec-fetch-site": "same-site",
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36",
}


def get_m3u8_file(m3u8_url, file_path):
    """
    下载m3u8文件
    :param m3u8_url: m3u8文件的URL
    :param file_path: 要下载的文件路径
    :return:
    """
    resp = requests.get(m3u8_url, headers=headers)
    if resp.status_code == 200:
        content = resp.text
        with open(file_path, "w") as f:
            f.write(content)


def get_ts_name_list(file_path):
    """
    获取ts文件名称列表
    :param file_path: m3u8文件路径
    :return: ts文件名称列表
    """
    ts_name_list = []
    with open(file_path, "rb") as f:
        cont_list = f.readlines()
    for cont in cont_list:
        cont = cont.decode().strip()
        if cont.endswith(".ts"):
            ts_name_list.append(cont.split("/")[-1])
            # if not cont.startswith("#"):
            #     ts_name_list.append(cont.split("/")[-1])
    return ts_name_list


def get_ts_files(file_dir, ts_url_template, ts_name_list):
    """
    循环下载ts文件
    :param file_dir: 文件下载所在文件夹
    :param ts_url_template: ts文件请求URL模板
    :param ts_name_list: ts文件名称列表
    :return:
    """
    for ts_name in ts_name_list:
        ts_url = ts_url_template + ts_name
        resp = requests.get(ts_url, headers=headers)
        if resp.status_code == 200:
            with open(os.path.join(file_dir, ts_name), "wb") as f:
                f.write(resp.content)
            print("%s-->下载成功！" % ts_name)
        else:
            print("%s-->下载失败！" % ts_name)


def merge_ts_files(file_dir, file_name, ts_name_list):
    """
    将多个ts文件进行合并
    :param file_dir: ts文件所在文件夹
    :param file_name: 合并后的文件名称
    :param ts_name_list: ts文件名称列表
    :return:
    """
    file_out = os.path.join(file_dir, file_name)
    with open(file_out, 'wb') as f_out:
        for ts_name in ts_name_list:
            with open(os.path.join(file_dir, ts_name), "rb") as f_in:
                f_out.write(f_in.read())
    print("合并ts文件成功！")


if __name__ == '__main__':
    # 用来保存ts文件
    file_dir = './ts_file'
    if not os.path.exists(file_dir):
        os.mkdir(file_dir)
    # m3u8文件URL
    m3u8_url = "https://video.leetcode-cn.com/5d1c2e6731b448aaa9965202c997a26c/c5c5c3d84d7b4c70bdef21cd7ef011e6-1380cfc54b15bf9d5088f6deaff5a053-hd.m3u8"
    # 提取文件名
    file_name = m3u8_url.split('/')[-1]
    file_path = os.path.join(file_dir, file_name)
    # 下载m3u8文件
    get_m3u8_file(m3u8_url, file_path)
    # 获取文件中ts文件名称列表
    ts_name_list = get_ts_name_list(file_path)
    # ts文件URL模板
    ts_url_template = "https://video.leetcode-cn.com/5d1c2e6731b448aaa9965202c997a26c/"
    # 下载ts文件
    get_ts_files(file_dir, ts_url_template, ts_name_list)
    # 合并ts文件
    ts_file_name = file_name.split(".")[0] + ".ts"
    merge_ts_files(file_dir, ts_file_name, ts_name_list)