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