└── file.py


/file.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | # -*- coding: utf-8 -*-
 3 | 
 4 | import os, shutil
 5 | import urllib.request, urllib.error, requests
 6 | 
 7 | 
 8 | # 打开并读取网页内容
 9 | def getUrlData(url):
10 |     try:
11 |         urlData = urllib.request.urlopen(url, timeout=3)  # .read().decode('utf-8', 'ignore')
12 |         return urlData
13 |     except Exception as err:
14 |         print(f'err getUrlData({url})\n', err)
15 |         return -1
16 | 
17 | 
18 | # 下载文件-urllib.request
19 | def getDown_urllib(url, file_path):
20 |     try:
21 |         urllib.request.urlretrieve(url, filename=file_path)
22 |         return True
23 |     except urllib.error.URLError as e:
24 |         # hasttr(e, 'code')，判断e 是否有.code属性，因为不确定是不是HTTPError错误，URLError包含HTTPError，但是HTTPError以外的错误是不返回错误码(状态码)的
25 |         if hasattr(e, 'code'):
26 |             print(e.code)  # 打印服务器返回的错误码（状态码），如403，404,501之类的
27 |         elif hasattr(e, 'reason'):
28 |             print(e.reason)  # 打印错误原因
29 | 
30 | 
31 | def getVideo_urllib(url_m3u8, path, videoName):
32 |     print('begin run ~~\n')
33 |     # urlData = getUrlData(url_m3u8).readlines()
34 |     urlData = getUrlData(url_m3u8)
35 |     num = 0
36 |     tempName_video = os.path.join(path, f'{videoName}.ts')  # f'{}' 相当于'{}'.format() 或 '%s'%videoName
37 |     # print(urlData)
38 |     for line in urlData:
39 |         # 解码，由于是直接使用了所抓取的链接内容，所以需要按行解码，如果提前解码则不能使用直接进行for循环，会报错
40 |         # 改用上面的readlines()或readline()也可以，但更繁琐些，同样需要按行解码，效率更低
41 |         url_ts = line.decode('utf-8')
42 |         tempName_ts = os.path.join(path, f'{num}.ts')  # f'{}' 相当于'{}'.format()
43 |         if not '.ts' in url_ts:
44 |             continue
45 |         else:
46 |             if not url_ts.startswith('http'):  # 判断字符串是否以'http'开头，如果不是则说明url链接不完整，需要拼接
47 |                 # 拼接ts流视频的url
48 |                 url_ts = url_m3u8.replace(url_m3u8.split('/')[-1], url_ts)
49 |         print(url_ts)
50 |         getDown_urllib(url_ts, tempName_ts)  # 下载视频流
51 |         if num == 0:
52 |             # 重命名，已存在则自动覆盖
53 |             shutil.move(tempName_ts, tempName_video)
54 |             num += 1
55 |             continue
56 |         cmd = f'copy /b {tempName_video}+{tempName_ts} {tempName_video}'
57 |         res = os.system(cmd)
58 |         if res == 0:
59 |             os.system(f'del {tempName_ts}')
60 |             # if num == 20:  # 限制下载的ts流个数，这个视频挺长有四百多个.ts文件，所以限制一下
61 |             #     break
62 |             num += 1
63 |             continue
64 |         print(f'Wrong, copy {num}.ts-->{videoName}.ts failure')
65 |         return False
66 |     os.system(f'del {path}/*.ts')  # 调用windows命令行（即cmd）工具，运行命令
67 |     filename = os.path.join(path, f'{videoName}.mp4')
68 |     shutil.move(tempName_video, filename)
69 |     print(f'{videoName}.mp4 finish down!')
70 | 
71 | 
72 | if __name__ == '__main__':
73 |     url_m3u8 = 'http://cntv.hls.cdn.myqcloud.com/asp/hls/2000/0303000a/3/default/e7b1fc31c9af496d85cf647cdffea9db/2000.m3u8'
74 |     path = r'G:\videos'
75 |     videoName = url_m3u8.split('/')[-2]
76 |     getVideo_urllib(url_m3u8, path, videoName)
77 | 
78 | 
79 | 


--------------------------------------------------------------------------------