Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cloudflarestream.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class CloudflareStreamIE(InfoExtractor):
  10     _VALID_URL = r'''(?x)
  11                     https?://
  12                         (?:
  13                             (?:watch\.)?cloudflarestream\.com/|
  14                             embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=
  15                         )
  16                         (?P<id>[\da-f]+)
  17                     '''
  18     _TESTS = [{
  19         'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
  20         'info_dict': {
  21             'id': '31c9291ab41fac05471db4e73aa11717',
  22             'ext': 'mp4',
  23             'title': '31c9291ab41fac05471db4e73aa11717',
  24         },
  25         'params': {
  26             'skip_download': True,
  27         },
  28     }, {
  29         'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/manifest/video.mpd',
  33         'only_matching': True,
  34     }]
  35
  36     @staticmethod
  37     def _extract_urls(webpage):
  38         return [
  39             mobj.group('url')
  40             for mobj in re.finditer(
  41                 r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1',
  42                 webpage)]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         formats = self._extract_m3u8_formats(
  48             'https://cloudflarestream.com/%s/manifest/video.m3u8' % video_id,
  49             video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls',
  50             fatal=False)
  51         formats.extend(self._extract_mpd_formats(
  52             'https://cloudflarestream.com/%s/manifest/video.mpd' % video_id,
  53             video_id, mpd_id='dash', fatal=False))
  54         self._sort_formats(formats)
  55
  56         return {
  57             'id': video_id,
  58             'title': video_id,
  59             'formats': formats,
  60         }