Python | 爬虫实战，爬取美剧天堂影视，合并ts文件为mp4文件

仅供学习参考

以美剧天堂为例，链接：https://www.mjtta.cc/p/822380/263/0

F12打开开发者工具，进度条拖至尾部，可以看到

ts文件最小为0000000，链接为：https://p.bvvvvvvv7f.com/video/youshuo/HD/0000000.ts

ts文件最大为0003169，链接为：https://p.bvvvvvvv7f.com/video/youshuo/HD/0003169.ts

所以我们只需构建一个循环，依次requests请求下载文件即可

import requests

header = {
    "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0",
    "accept-language":"zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6"
}

for i in range(0,3169):
    cid = str(i).zfill(7)
    url = f'https://p.bvvvvvvv7f.com/video/youshuo/HD/{cid}.ts'
    resp = requests.get(url,headers=header)
    f = open(f"游说/video{cid}.ts",mode="wb")
    f.write(resp.content)
    f.close()
    resp.close()
    print(url,"over")
print('over')

 考虑到下载内容较多，可以用异步协程处理

import asyncio
import aiohttp
import aiofiles
import os

header = {
    "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0",
    "accept-language":"zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6"
}

async def down(cid):
    down_url = f'https://p.bvvvvvvv7f.com/video/youshuo/HD/{cid}.ts'
    async with aiohttp.ClientSession() as Session:
        async with Session.get(down_url,headers = header) as down_resp:
            async with aiofiles.open(f"游说/video{cid}.ts",mode="wb") as f:
                content = await down_resp.read()  # 读取全部字节数据
                await f.write(content)
                print(down_url,',over')

#检验文件是否已存在，对未下载文件，进行下载处理
async def file():
    tasks = []
    for i in range(3169):
        cid = str(i).zfill(7)
        file_path = f"游说/video{cid}.ts"
        if not os.path.isfile(file_path):
            tasks.append(asyncio.create_task(down(cid)))
            print(f"缺少文件: {file_path}，已加入下载队伍")
    if len(tasks) != 0:
        await asyncio.wait(tasks)
    else:
        print('已全部下载')

if __name__ == '__main__':
    asyncio.run(file())

如遇到反爬机制，可分段下载，如0-1000,1000-2000等

运行结果：

将ts文件合并为mp4

def ts_to_mp4(ts_dir, output_mp4):
    script_dir = os.path.dirname(os.path.abspath(__file__))
    with open(os.path.join(script_dir, output_mp4), 'wb') as out_f:
        for i in range(3169):
            cid = str(i).zfill(7)
            ts_file = os.path.join(script_dir, ts_dir, f"video{cid}.ts")
            if os.path.exists(ts_file):
                with open(ts_file, 'rb') as in_f:
                    out_f.write(in_f.read())
            else:
                print(f"文件缺失 {ts_file}")
        print('合并完成')

if __name__ == '__main__':
    asyncio.run(file())
    ts_to_mp4("游说", "游说.mp4")

或者使用subprocess

import os
import subprocess

def merge_ts_to_mp4(ts_dir, output_mp4):
    #生成文件路径列表
    ts_files = []
    for i in range(928):
        cid = str(i)
        if len(str(i)) == 1:
            cid = '00' + f'{i}'
        elif len(str(i)) == 2:
            cid = '0' + f'{i}'
        ts_file = f"{ts_dir}/video{cid}.ts"
        ts_files.append(ts_file)


    # 创建临时文件列表
    with open("filelist.txt", "w", encoding="utf-8") as f:
        for file in ts_files:
            f.write(f"file '{os.path.abspath(file)}'\n")  # 使用绝对路径避免路径错误

    # FFmpeg合并命令
    command = [
        "ffmpeg",
        "-f", "concat",
        "-safe", "0",
        "-i", "filelist.txt",
        "-c:v", "copy",          # 复制视频流
        "-c:a", "copy",          # 复制音频流
        "-bsf:a", "aac_adtstoasc",  # 修复AAC流问题
        output_mp4
    ]
    
    try:
        subprocess.run(command, check=True)
        print(f"合并成功：{output_mp4}")
    except subprocess.CalledProcessError as e:
        print(f"合并失败：{e}")
    finally:
        if os.path.exists("filelist.txt"):
            os.remove("filelist.txt")  # 清理临时文件


merge_ts_to_mp4("游说", "游说.mp4")

运行结果：