python 视频爬虫

打开网址：http://mv.688ing.com/

输入视频播放地址

发现很多链接以.ts结尾。

#
import requests
import os
def download():
    headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
    for i in range(1,100):
        if i <10:
            link='https://cn4.shangbaiyi.com.cn/hls/20180925/9d0be274601aa094df1d98084483f121/1537842226/film_0000.ts'+str(i)+'.ts'#构造下载链接
        elif i <100:
            link='https://cn4.shangbaiyi.com.cn/hls/20180925/9d0be274601aa094df1d98084483f121/1537842226/film_000.ts'+str(i)+'.ts'
        dest_resp = requests.get(link,headers=headers)
    #视频是二进制数据流，content就是为了获取二进制数据的方法
        data = dest_resp.content
    #保存数据的路径及文件名
        download_path = os.getcwd() + "\download"
        path = r'C:\Users\lenovo\Desktop\新建文件夹'
        with open(os.path.join(path, str(i) + ".ts"), 'wb') as f:#写入文件夹
            f.write(data)
        print(i)
    merge_file(r'C:\Users\lenovo\Desktop\新建文件夹')#存视频的文件夹
def merge_file(path):#合并视频
    os.chdir(path)
    cmd = "copy /b * new.tmp"
    os.system(cmd)
    os.system('del /Q *.ts')
    os.system('del /Q *.mp4')
    os.rename("new.tmp", "new.mp4")
if __name__ == '__main__':
    download()