Python解析m3u8拼接下载mp4视频文件的示例代码
这篇文章主要介绍了Python解析m3u8拼接下载mp4视频文件的示例代码,本文给大家介绍的非常详细，对大家的学习或工作具有一定的参考借鉴价值，需要的朋友可以参考下
一、关于m3u8：
m3u8是苹果公司推出一种视频播放标准，是m3u的一种，不过编码方式是utf-8，是一种文件检索格式，将视频切割成一小段一小段的ts格式的视频文件，然后存在服务器中（现在为了减少I/o访问次数，一般存在服务器的内存中），通过m3u8解析出来路径，然后去请求。
示例：
1 2 3 4 5 6 7 8 9 | #EXTM3U#EXT-X-TARGETDURATION:10#EXTINF:9,http://data.video.iqiyi.com/videos/vts/20210301/69/b8/73ad4ef04fde4586ef2799ecd67241ce.ts?qypid=2645242154145600_04000000001000000000_96&start=496696&end=779448&contentlength=282752&sd=20200&qdv=1&qd_uid=0&qd_tvid=2645242154145600&qd_vip=0&qd_src=02029022240000000000&qd_tm=1614590393988&qd_ip=0&qd_p=0&qd_k=4eb685f1966cbd08e6a9648fe0b8c007&ve=&sgti=&dfp=&qd_sc=f9a4f133a622871b6739734615ef178d#EXTINF:9,http://data.video.iqiyi.com/videos/vts/20210301/69/b8/73ad4ef04fde4586ef2799ecd67241ce.ts?qypid=2645242154145600_04000000001000000000_96&start=779448&end=1008432&contentlength=228984&sd=29200&qdv=1&qd_uid=0&qd_tvid=2645242154145600&qd_vip=0&qd_src=02029022240000000000&qd_tm=1614590393988&qd_ip=0&qd_p=0&qd_k=4eb685f1966cbd08e6a9648fe0b8c007&ve=&sgti=&dfp=&qd_sc=f9a4f133a622871b6739734615ef178d#EXTINF:9,http://data.video.iqiyi.com/videos/vts/20210301/69/b8/73ad4ef04fde4586ef2799ecd67241ce.ts?qypid=2645242154145600_04000000001000000000_96&start=5934408&end=6141020&contentlength=206612&sd=198733&qdv=1&qd_uid=0&qd_tvid=2645242154145600&qd_vip=0&qd_src=02029022240000000000&qd_tm=1614590393988&qd_ip=0&qd_p=0&qd_k=4eb685f1966cbd08e6a9648fe0b8c007&ve=&sgti=&dfp=&qd_sc=f9a4f133a622871b6739734615ef178d#EXT-X-ENDLIST |
预览器打开会出现下载ts文件
我们想要的mp4文件就是一个个ts文件按照顺序拼接成的，废话不多说直接上代码。
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | # -*- coding:utf-8 -*- """Author：SPIDERMANTime: 2021/3/1 Software: PyCharm"""import loggingimport osfrom glob import iglobimport requestsimport m3u8from urllib.parse import urljoinfrom concurrent.futures import ThreadPoolExecutorfrom natsort import natsortedclass M3u8Download: def __init__(self,m3u8_url): self.m3u8_url = m3u8_url self.headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' } self.threadpool = ThreadPoolExecutor(max_workers=10) self.file_name = 'weibo.mp4' logging.basicConfig(format='[%(asctime)s][*%(levelname)s]:%(message)s', level=logging.INFO) def get_ts_url(self,m3u8_url): """ 解析ts_url :param m3u8_url: :return: """ m3u8_obj = m3u8.load(m3u8_url) base_uri = m3u8_obj.base_uri logging.info('[*]get_base_uri'+base_uri) for seg in m3u8_obj.segments: yield urljoin(base_uri, seg.uri) def download__ts(self, urlinfo): """ 下载ts文件 :param urlinfo: :return: """ url, ts_name = urlinfo res = requests.get(url, headers=self.headers) with open(ts_name, 'wb') as fp: fp.write(res.content) logging.info('[*download]'+ts_name) def download_all_ts(self): """ 下载所有函数 :return: """ ts_urls = self.get_ts_url(self.m3u8_url) logging.info('[*download]download:'+self.m3u8_url) for index, ts_url in enumerate(ts_urls): print(ts_url) self.threadpool.submit(self.download__ts, [ts_url, f'{index}.ts']) self.threadpool.shutdown() def remove_ts(self,ts_path): """ 删除ts文件 :param ts_path: :return: """ for ts in iglob(ts_path): os.remove(ts) logging.info('[*remove]remove all *.ts') def run(self): self.download_all_ts() ts_path = '*.ts' all_ts = iglob(ts_path) with open(self.file_name, 'wb') as fn: #根据ts排序 for ts in natsorted(all_ts): #读ts写mp4 with open(ts, 'rb') as ft: scline = ft.read() fn.write(scline) self.remove_ts(ts_path)if __name__ == '__main__': m3u8Download.run() |
console.log("公众号:Java技术迷")
console.log("wx:spiderskill")
到此这篇关于Python解析m3u8拼接下载mp4视频文件的文章就介绍到这了,