yt_dlp/extractor/pandoratv.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_str,
   4 )
   5 from ..utils import (
   6     ExtractorError,
   7     float_or_none,
   8     parse_duration,
   9     parse_qs,
  10     str_to_int,
  11     urlencode_postdata,
  12 )
  13
  14
  15 class PandoraTVIE(InfoExtractor):
  16     IE_NAME = 'pandora.tv'
  17     IE_DESC = '판도라TV'
  18     _VALID_URL = r'''(?x)
  19                         https?://
  20                             (?:
  21                                 (?:www\.)?pandora\.tv/view/(?P<user_id>[^/]+)/(?P<id>\d+)|  # new format
  22                                 (?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?|        # old format
  23                                 m\.pandora\.tv/?\?                                          # mobile
  24                             )
  25                     '''
  26     _TESTS = [{
  27         'url': 'http://jp.channel.pandora.tv/channel/video.ptv?c1=&prgid=53294230&ch_userid=mikakim&ref=main&lot=cate_01_2',
  28         'info_dict': {
  29             'id': '53294230',
  30             'ext': 'flv',
  31             'title': '頭を撫でてくれる？',
  32             'description': '頭を撫でてくれる？',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'duration': 39,
  35             'upload_date': '20151218',
  36             'uploader': 'カワイイ動物まとめ',
  37             'uploader_id': 'mikakim',
  38             'view_count': int,
  39             'like_count': int,
  40         }
  41     }, {
  42         'url': 'http://channel.pandora.tv/channel/video.ptv?ch_userid=gogoucc&prgid=54721744',
  43         'info_dict': {
  44             'id': '54721744',
  45             'ext': 'flv',
  46             'title': '[HD] JAPAN COUNTDOWN 170423',
  47             'description': '[HD] JAPAN COUNTDOWN 170423',
  48             'thumbnail': r're:^https?://.*\.jpg$',
  49             'duration': 1704.9,
  50             'upload_date': '20170423',
  51             'uploader': 'GOGO_UCC',
  52             'uploader_id': 'gogoucc',
  53             'view_count': int,
  54             'like_count': int,
  55         },
  56         'params': {
  57             # Test metadata only
  58             'skip_download': True,
  59         },
  60     }, {
  61         'url': 'http://www.pandora.tv/view/mikakim/53294230#36797454_new',
  62         'only_matching': True,
  63     }, {
  64         'url': 'http://m.pandora.tv/?c=view&ch_userid=mikakim&prgid=54600346',
  65         'only_matching': True,
  66     }]
  67
  68     def _real_extract(self, url):
  69         mobj = self._match_valid_url(url)
  70         user_id = mobj.group('user_id')
  71         video_id = mobj.group('id')
  72
  73         if not user_id or not video_id:
  74             qs = parse_qs(url)
  75             video_id = qs.get('prgid', [None])[0]
  76             user_id = qs.get('ch_userid', [None])[0]
  77             if any(not f for f in (video_id, user_id,)):
  78                 raise ExtractorError('Invalid URL', expected=True)
  79
  80         data = self._download_json(
  81             'http://m.pandora.tv/?c=view&m=viewJsonApi&ch_userid=%s&prgid=%s'
  82             % (user_id, video_id), video_id)
  83
  84         info = data['data']['rows']['vod_play_info']['result']
  85
  86         formats = []
  87         for format_id, format_url in info.items():
  88             if not format_url:
  89                 continue
  90             height = self._search_regex(
  91                 r'^v(\d+)[Uu]rl$', format_id, 'height', default=None)
  92             if not height:
  93                 continue
  94
  95             play_url = self._download_json(
  96                 'http://m.pandora.tv/?c=api&m=play_url', video_id,
  97                 data=urlencode_postdata({
  98                     'prgid': video_id,
  99                     'runtime': info.get('runtime'),
 100                     'vod_url': format_url,
 101                 }),
 102                 headers={
 103                     'Origin': url,
 104                     'Content-Type': 'application/x-www-form-urlencoded',
 105                 })
 106             format_url = play_url.get('url')
 107             if not format_url:
 108                 continue
 109
 110             formats.append({
 111                 'format_id': '%sp' % height,
 112                 'url': format_url,
 113                 'height': int(height),
 114             })
 115
 116         return {
 117             'id': video_id,
 118             'title': info['subject'],
 119             'description': info.get('body'),
 120             'thumbnail': info.get('thumbnail') or info.get('poster'),
 121             'duration': float_or_none(info.get('runtime'), 1000) or parse_duration(info.get('time')),
 122             'upload_date': info['fid'].split('/')[-1][:8] if isinstance(info.get('fid'), compat_str) else None,
 123             'uploader': info.get('nickname'),
 124             'uploader_id': info.get('upload_userid'),
 125             'view_count': str_to_int(info.get('hit')),
 126             'like_count': str_to_int(info.get('likecnt')),
 127             'formats': formats,
 128         }