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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     float_or_none,
   9     ExtractorError,
  10 )
  11
  12
  13 class UplynkIE(InfoExtractor):
  14     IE_NAME = 'uplynk'
  15     _VALID_URL = r'https?://.*?\.uplynk\.com/(?P<path>ext/[0-9a-f]{32}/(?P<external_id>[^/?&]+)|(?P<id>[0-9a-f]{32}))\.(?:m3u8|json)(?:.*?\bpbs=(?P<session_id>[^&]+))?'
  16     _TEST = {
  17         'url': 'http://content.uplynk.com/e89eaf2ce9054aa89d92ddb2d817a52e.m3u8',
  18         'info_dict': {
  19             'id': 'e89eaf2ce9054aa89d92ddb2d817a52e',
  20             'ext': 'mp4',
  21             'title': '030816-kgo-530pm-solar-eclipse-vid_web.mp4',
  22             'uploader_id': '4413701bf5a1488db55b767f8ae9d4fa',
  23         },
  24         'params': {
  25             # m3u8 download
  26             'skip_download': True,
  27         },
  28     }
  29
  30     def _extract_uplynk_info(self, uplynk_content_url):
  31         path, external_id, video_id, session_id = re.match(UplynkIE._VALID_URL, uplynk_content_url).groups()
  32         display_id = video_id or external_id
  33         formats = self._extract_m3u8_formats('http://content.uplynk.com/%s.m3u8' % path, display_id, 'mp4')
  34         if session_id:
  35             for f in formats:
  36                 f['extra_param_to_segment_url'] = {
  37                     'pbs': session_id,
  38                 }
  39         self._sort_formats(formats)
  40         asset = self._download_json('http://content.uplynk.com/player/assetinfo/%s.json' % path, display_id)
  41         if asset.get('error') == 1:
  42             raise ExtractorError('% said: %s' % (self.IE_NAME, asset['msg']), expected=True)
  43
  44         return {
  45             'id': asset['asset'],
  46             'title': asset['desc'],
  47             'thumbnail': asset.get('default_poster_url'),
  48             'duration': float_or_none(asset.get('duration')),
  49             'uploader_id': asset.get('owner'),
  50             'formats': formats,
  51         }
  52
  53     def _real_extract(self, url):
  54         return self._extract_uplynk_info(url)
  55
  56
  57 class UplynkPreplayIE(UplynkIE):
  58     IE_NAME = 'uplynk:preplay'
  59     _VALID_URL = r'https?://.*?\.uplynk\.com/preplay2?/(?P<path>ext/[0-9a-f]{32}/(?P<external_id>[^/?&]+)|(?P<id>[0-9a-f]{32}))\.json'
  60     _TEST = None
  61
  62     def _real_extract(self, url):
  63         path, external_id, video_id = re.match(self._VALID_URL, url).groups()
  64         display_id = video_id or external_id
  65         preplay = self._download_json(url, display_id)
  66         content_url = 'http://content.uplynk.com/%s.m3u8' % path
  67         session_id = preplay.get('sid')
  68         if session_id:
  69             content_url += '?pbs=' + session_id
  70         return self._extract_uplynk_info(content_url)