yt_dlp/extractor/uplynk.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     float_or_none,
   7     smuggle_url,
   8     traverse_obj,
   9     unsmuggle_url,
  10     update_url_query,
  11 )
  12
  13
  14 class UplynkBaseIE(InfoExtractor):
  15     _UPLYNK_URL_RE = r'''(?x)
  16         https?://[\w-]+\.uplynk\.com/(?P<path>
  17             ext/[0-9a-f]{32}/(?P<external_id>[^/?&]+)|
  18             (?P<id>[0-9a-f]{32})
  19         )\.(?:m3u8|json)
  20         (?:.*?\bpbs=(?P<session_id>[^&]+))?'''
  21
  22     def _extract_uplynk_info(self, url):
  23         uplynk_content_url, smuggled_data = unsmuggle_url(url, {})
  24         mobj = re.match(self._UPLYNK_URL_RE, uplynk_content_url)
  25         if not mobj:
  26             raise ExtractorError('Necessary parameters not found in Uplynk URL')
  27         path, external_id, video_id, session_id = mobj.group('path', 'external_id', 'id', 'session_id')
  28         display_id = video_id or external_id
  29         headers = traverse_obj(
  30             smuggled_data, {'Referer': 'Referer', 'Origin': 'Origin'}, casesense=False)
  31         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  32             f'http://content.uplynk.com/{path}.m3u8', display_id, 'mp4', headers=headers)
  33         if session_id:
  34             for f in formats:
  35                 f['extra_param_to_segment_url'] = f'pbs={session_id}'
  36         asset = self._download_json(
  37             f'http://content.uplynk.com/player/assetinfo/{path}.json', display_id)
  38         if asset.get('error') == 1:
  39             msg = asset.get('msg') or 'unknown error'
  40             raise ExtractorError(f'{self.IE_NAME} said: {msg}', expected=True)
  41
  42         return {
  43             'id': asset['asset'],
  44             'title': asset['desc'],
  45             'thumbnail': asset.get('default_poster_url'),
  46             'duration': float_or_none(asset.get('duration')),
  47             'uploader_id': asset.get('owner'),
  48             'formats': formats,
  49             'subtitles': subtitles,
  50         }
  51
  52
  53 class UplynkIE(UplynkBaseIE):
  54     IE_NAME = 'uplynk'
  55     _VALID_URL = UplynkBaseIE._UPLYNK_URL_RE
  56     _TEST = {
  57         'url': 'http://content.uplynk.com/e89eaf2ce9054aa89d92ddb2d817a52e.m3u8',
  58         'info_dict': {
  59             'id': 'e89eaf2ce9054aa89d92ddb2d817a52e',
  60             'ext': 'mp4',
  61             'title': '030816-kgo-530pm-solar-eclipse-vid_web.mp4',
  62             'uploader_id': '4413701bf5a1488db55b767f8ae9d4fa',
  63             'duration': 530.2739166666679,
  64             'thumbnail': r're:^https?://.*\.jpg$',
  65         },
  66         'params': {
  67             'skip_download': 'm3u8',
  68         },
  69     }
  70
  71     def _real_extract(self, url):
  72         return self._extract_uplynk_info(url)
  73
  74
  75 class UplynkPreplayIE(UplynkBaseIE):
  76     IE_NAME = 'uplynk:preplay'
  77     _VALID_URL = r'https?://[\w-]+\.uplynk\.com/preplay2?/(?P<path>ext/[0-9a-f]{32}/(?P<external_id>[^/?&]+)|(?P<id>[0-9a-f]{32}))\.json'
  78
  79     def _real_extract(self, url):
  80         url, smuggled_data = unsmuggle_url(url, {})
  81         path, external_id, video_id = self._match_valid_url(url).groups()
  82         display_id = video_id or external_id
  83         preplay = self._download_json(url, display_id)
  84         content_url = f'http://content.uplynk.com/{path}.m3u8'
  85         session_id = preplay.get('sid')
  86         if session_id:
  87             content_url = update_url_query(content_url, {'pbs': session_id})
  88         return self._extract_uplynk_info(smuggle_url(content_url, smuggled_data))