python spider tvbanywherena

TVB北美和加拿大的电视剧地址(需要翻看):https://tvbanywherena.com/cantonese

以下是完成代码，通过python获取m3u8、下载声音、视频切片、解密、合并。

#!/usr/bin/python # -*- coding: UTF-8 -*- import m3u8 import os import requests import threading from Crypto.Cipher import AES   def download(download_path, key, vi, url, file_name):     """     下载分片文件 需要通过下载内容m3u8中EXT-X-KEY解密     :param download_path: 本地磁盘路径下载文件     :param key:EXT-X-KEY     :param vi:IV     :param url: 下载地址     :param file_name:存储文件名     :return:     """     try:         requests.packages.urllib3.disable_warnings()         res = requests.get(url, stream=True, verify=False)         content_video_part = AES.new(key, AES.MODE_CBC, vi).decrypt(res.content)         ts_path = download_path   "/{}".format(file_name)         with open(ts_path, 'ab') as f:  # 追加保存解密结果             f.write(content_video_part)     except Exception as e:         print("异常要求:%:%s" % e.args)         return     print("TS下载文件！！\n")   def file_filter(f):     if f[-3:] in ['.ts']:         return True     else:         return False   def merge(download_path, hebing_path):     """     所以它被分成一个文件     :param download_path: 分片文件目录     :param hebing_path: 结果目录     :return:     """     all_ts = os.listdir(download_path)     # 筛选     all_ts = list(filter(file_filter, all_ts))     # 排序     all_ts.sort(key=lambda x: int(x[:-3]))     li_audio = [os.path.join(download_path "/",filename) for filename in all_ts]     command = 'ffmpeg -i "concat:%s" -codec copy %s' %('|'.join(li_audio), hebing_path)     os.system(command)     print("合并完成！！")   def merge_video_voice(mp4_path, wav_path, path):     """     合并音频和视频文件     :param mp4_path:视频文件路径     :param wav_path:音频文件路径     :param path:合并结果路径     :return:     """     command = 'ffmpeg -i %s -i %s -c copy %s' % (mp4_path, wav_path, path)     print(command)     os.system(command)     print("合并完成！！")   def get_m3u8_info(uri):     """      :param uri: m3u8 url     :return: 分片url，EXT-X-KEY，IV     """     play_list = m3u8.load(uri=uri, verify_ssl=False)     key = requests.get(play_list.keys[0].uri, verify=False).content     return play_list.segments, key, bytes.fromhex(play_list.keys[0].iv[2:])   if __name__ == '__main__':     # video master m3u8     mp4_m3u8_url = "";     # voice master m3u8     wav_m3u8_url = "";     # download path     download_path = r"/Users/Desktop/pianzhongchuanqi"     # 合并结果path     hebing_path = r"/Users/Desktop/pianzhongchuanqi"      segments, key, vi = get_m3u8_info(mp4_m3u8_url)      for index, segment in enumerate(segments):         t = threading.Thread(target=download, args=(download_path "/mp4", key, vi, segment.uri, str(index) ".ts",))         t.start()     while threading.activeCount() !=1:         pass      merge(download_path "/mp4", hebing_path "/total.mp4")      segments, key, vi = get_m3u8_info(wav_m3u8_url)      for index, segment in enumerate(segments):         t = threading.Thread(target=download, args=(download_path "/wav", key, vi, segment.uri, str(index) ".ts",))         t.start()     while threading.activeCount() !=1:         pass      merge(download_path "/wav", hebing_path "/total.wav")      # video voice 合并     merge_video_voice(hebing_path "/total.mp4", hebing_path "/total.wav", hebing_path "/final.mp4")   

相关剧集m3u8链接获取方式：

注：网站需要翻q才能过去看，但是m3u不需要翻。