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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     int_or_none,
   7     parse_duration,
   8 )
   9
  10
  11 class MwaveIE(InfoExtractor):
  12     _VALID_URL = r'https?://mwave\.interest\.me/mnettv/videodetail\.m\?searchVideoDetailVO\.clip_id=(?P<id>[0-9]+)'
  13     _URL_TEMPLATE = 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=%s'
  14     _TEST = {
  15         'url': 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=168859',
  16         # md5 is unstable
  17         'info_dict': {
  18             'id': '168859',
  19             'ext': 'flv',
  20             'title': '[M COUNTDOWN] SISTAR - SHAKE IT',
  21             'thumbnail': 're:^https?://.*\.jpg$',
  22             'uploader': 'M COUNTDOWN',
  23             'duration': 206,
  24             'view_count': int,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         vod_info = self._download_json(
  32             'http://mwave.interest.me/onair/vod_info.m?vodtype=CL&sectorid=&endinfo=Y&id=%s' % video_id,
  33             video_id, 'Download vod JSON')
  34
  35         formats = []
  36         for num, cdn_info in enumerate(vod_info['cdn']):
  37             stream_url = cdn_info.get('url')
  38             if not stream_url:
  39                 continue
  40             stream_name = cdn_info.get('name') or compat_str(num)
  41             f4m_stream = self._download_json(
  42                 stream_url, video_id,
  43                 'Download %s stream JSON' % stream_name)
  44             f4m_url = f4m_stream.get('fileurl')
  45             if not f4m_url:
  46                 continue
  47             formats.extend(
  48                 self._extract_f4m_formats(f4m_url + '&hdcore=3.0.3', video_id, f4m_id=stream_name))
  49         self._sort_formats(formats)
  50
  51         return {
  52             'id': video_id,
  53             'title': vod_info['title'],
  54             'thumbnail': vod_info.get('cover'),
  55             'uploader': vod_info.get('program_title'),
  56             'duration': parse_duration(vod_info.get('time')),
  57             'view_count': int_or_none(vod_info.get('hit')),
  58             'formats': formats,
  59         }
  60
  61
  62 class MwaveMeetGreetIE(InfoExtractor):
  63     _VALID_URL = r'https?://mwave\.interest\.me/meetgreet/view/(?P<id>\d+)'
  64     _TEST = {
  65         'url': 'http://mwave.interest.me/meetgreet/view/256',
  66         'info_dict': {
  67             'id': '173294',
  68             'ext': 'flv',
  69             'title': '[MEET&GREET] Park BoRam',
  70             'thumbnail': 're:^https?://.*\.jpg$',
  71             'uploader': 'Mwave',
  72             'duration': 3634,
  73             'view_count': int,
  74         }
  75     }
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79         webpage = self._download_webpage(url, video_id)
  80         clip_id = self._html_search_regex(
  81             r'<iframe[^>]+src="/mnettv/ifr_clip\.m\?searchVideoDetailVO\.clip_id=(\d+)',
  82             webpage, 'clip ID')
  83         clip_url = MwaveIE._URL_TEMPLATE % clip_id
  84         return self.url_result(clip_url, 'Mwave', clip_id)