yt_dlp/extractor/pandoratv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_str,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     float_or_none,
  12     parse_duration,
  13     parse_qs,
  14     str_to_int,
  15     urlencode_postdata,
  16 )
  17
  18
  19 class PandoraTVIE(InfoExtractor):
  20     IE_NAME = 'pandora.tv'
  21     IE_DESC = '판도라TV'
  22     _VALID_URL = r'''(?x)
  23                         https?://
  24                             (?:
  25                                 (?:www\.)?pandora\.tv/view/(?P<user_id>[^/]+)/(?P<id>\d+)|  # new format
  26                                 (?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?|        # old format
  27                                 m\.pandora\.tv/?\?                                          # mobile
  28                             )
  29                     '''
  30     _TESTS = [{
  31         'url': 'http://jp.channel.pandora.tv/channel/video.ptv?c1=&prgid=53294230&ch_userid=mikakim&ref=main&lot=cate_01_2',
  32         'info_dict': {
  33             'id': '53294230',
  34             'ext': 'flv',
  35             'title': '頭を撫でてくれる？',
  36             'description': '頭を撫でてくれる？',
  37             'thumbnail': r're:^https?://.*\.jpg$',
  38             'duration': 39,
  39             'upload_date': '20151218',
  40             'uploader': 'カワイイ動物まとめ',
  41             'uploader_id': 'mikakim',
  42             'view_count': int,
  43             'like_count': int,
  44         }
  45     }, {
  46         'url': 'http://channel.pandora.tv/channel/video.ptv?ch_userid=gogoucc&prgid=54721744',
  47         'info_dict': {
  48             'id': '54721744',
  49             'ext': 'flv',
  50             'title': '[HD] JAPAN COUNTDOWN 170423',
  51             'description': '[HD] JAPAN COUNTDOWN 170423',
  52             'thumbnail': r're:^https?://.*\.jpg$',
  53             'duration': 1704.9,
  54             'upload_date': '20170423',
  55             'uploader': 'GOGO_UCC',
  56             'uploader_id': 'gogoucc',
  57             'view_count': int,
  58             'like_count': int,
  59         },
  60         'params': {
  61             # Test metadata only
  62             'skip_download': True,
  63         },
  64     }, {
  65         'url': 'http://www.pandora.tv/view/mikakim/53294230#36797454_new',
  66         'only_matching': True,
  67     }, {
  68         'url': 'http://m.pandora.tv/?c=view&ch_userid=mikakim&prgid=54600346',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_extract(self, url):
  73         mobj = self._match_valid_url(url)
  74         user_id = mobj.group('user_id')
  75         video_id = mobj.group('id')
  76
  77         if not user_id or not video_id:
  78             qs = parse_qs(url)
  79             video_id = qs.get('prgid', [None])[0]
  80             user_id = qs.get('ch_userid', [None])[0]
  81             if any(not f for f in (video_id, user_id,)):
  82                 raise ExtractorError('Invalid URL', expected=True)
  83
  84         data = self._download_json(
  85             'http://m.pandora.tv/?c=view&m=viewJsonApi&ch_userid=%s&prgid=%s'
  86             % (user_id, video_id), video_id)
  87
  88         info = data['data']['rows']['vod_play_info']['result']
  89
  90         formats = []
  91         for format_id, format_url in info.items():
  92             if not format_url:
  93                 continue
  94             height = self._search_regex(
  95                 r'^v(\d+)[Uu]rl$', format_id, 'height', default=None)
  96             if not height:
  97                 continue
  98
  99             play_url = self._download_json(
 100                 'http://m.pandora.tv/?c=api&m=play_url', video_id,
 101                 data=urlencode_postdata({
 102                     'prgid': video_id,
 103                     'runtime': info.get('runtime'),
 104                     'vod_url': format_url,
 105                 }),
 106                 headers={
 107                     'Origin': url,
 108                     'Content-Type': 'application/x-www-form-urlencoded',
 109                 })
 110             format_url = play_url.get('url')
 111             if not format_url:
 112                 continue
 113
 114             formats.append({
 115                 'format_id': '%sp' % height,
 116                 'url': format_url,
 117                 'height': int(height),
 118             })
 119         self._sort_formats(formats)
 120
 121         return {
 122             'id': video_id,
 123             'title': info['subject'],
 124             'description': info.get('body'),
 125             'thumbnail': info.get('thumbnail') or info.get('poster'),
 126             'duration': float_or_none(info.get('runtime'), 1000) or parse_duration(info.get('time')),
 127             'upload_date': info['fid'].split('/')[-1][:8] if isinstance(info.get('fid'), compat_str) else None,
 128             'uploader': info.get('nickname'),
 129             'uploader_id': info.get('upload_userid'),
 130             'view_count': str_to_int(info.get('hit')),
 131             'like_count': str_to_int(info.get('likecnt')),
 132             'formats': formats,
 133         }