yt_dlp/extractor/daum.py

   1 import itertools
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..utils import parse_qs
   6
   7
   8 class DaumBaseIE(InfoExtractor):
   9     _KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/'
  10
  11
  12 class DaumIE(DaumBaseIE):
  13     _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
  14     IE_NAME = 'daum.net'
  15
  16     _TESTS = [{
  17         'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
  18         'info_dict': {
  19             'id': 'vab4dyeDBysyBssyukBUjBz',
  20             'ext': 'mp4',
  21             'title': '마크 헌트 vs 안토니오 실바',
  22             'description': 'Mark Hunt vs Antonio Silva',
  23             'upload_date': '20131217',
  24             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
  25             'duration': 2117,
  26             'view_count': int,
  27             'comment_count': int,
  28             'uploader_id': '186139',
  29             'uploader': '콘간지',
  30             'timestamp': 1387310323,
  31         },
  32     }, {
  33         'url': 'http://m.tvpot.daum.net/v/65139429',
  34         'info_dict': {
  35             'id': '65139429',
  36             'ext': 'mp4',
  37             'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
  38             'description': 'md5:79794514261164ff27e36a21ad229fc5',
  39             'upload_date': '20150118',
  40             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
  41             'duration': 154,
  42             'view_count': int,
  43             'comment_count': int,
  44             'uploader': 'MBC 예능',
  45             'uploader_id': '132251',
  46             'timestamp': 1421604228,
  47         },
  48     }, {
  49         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
  50         'only_matching': True,
  51     }, {
  52         'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
  53         'info_dict': {
  54             'id': 'vwIpVpCQsT8$',
  55             'ext': 'flv',
  56             'title': '01-Korean War ( Trouble on the horizon )',
  57             'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름',
  58             'upload_date': '20080223',
  59             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
  60             'duration': 249,
  61             'view_count': int,
  62             'comment_count': int,
  63             'uploader': '까칠한 墮落始祖 황비홍님의',
  64             'uploader_id': '560824',
  65             'timestamp': 1203770745,
  66         },
  67     }, {
  68         # Requires dte_type=WEB (#9972)
  69         'url': 'http://tvpot.daum.net/v/s3794Uf1NZeZ1qMpGpeqeRU',
  70         'md5': 'a8917742069a4dd442516b86e7d66529',
  71         'info_dict': {
  72             'id': 's3794Uf1NZeZ1qMpGpeqeRU',
  73             'ext': 'mp4',
  74             'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
  75             'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
  76             'upload_date': '20170129',
  77             'uploader': '쇼! 음악중심',
  78             'uploader_id': '2653210',
  79             'timestamp': 1485684628,
  80         },
  81     }]
  82
  83     def _real_extract(self, url):
  84         video_id = urllib.parse.unquote(self._match_id(url))
  85         if not video_id.isdigit():
  86             video_id += '@my'
  87         return self.url_result(
  88             self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
  89
  90
  91 class DaumClipIE(DaumBaseIE):
  92     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
  93     IE_NAME = 'daum.net:clip'
  94     _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
  95
  96     _TESTS = [{
  97         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
  98         'info_dict': {
  99             'id': '52554690',
 100             'ext': 'mp4',
 101             'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
 102             'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
 103             'upload_date': '20130831',
 104             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
 105             'duration': 3868,
 106             'view_count': int,
 107             'uploader': 'GOMeXP',
 108             'uploader_id': '6667',
 109             'timestamp': 1377911092,
 110         },
 111     }, {
 112         'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
 113         'only_matching': True,
 114     }]
 115
 116     @classmethod
 117     def suitable(cls, url):
 118         return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super().suitable(url)
 119
 120     def _real_extract(self, url):
 121         video_id = self._match_id(url)
 122         return self.url_result(
 123             self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
 124
 125
 126 class DaumListIE(InfoExtractor):  # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
 127     def _get_entries(self, list_id, list_id_type):
 128         name = None
 129         entries = []
 130         for pagenum in itertools.count(1):
 131             list_info = self._download_json(
 132                 f'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page={pagenum}&{list_id_type}={list_id}',
 133                 list_id, f'Downloading list info - {pagenum}')
 134
 135             entries.extend([
 136                 self.url_result(
 137                     'http://tvpot.daum.net/v/{}'.format(clip['vid']))
 138                 for clip in list_info['clip_list']
 139             ])
 140
 141             if not name:
 142                 name = list_info.get('playlist_bean', {}).get('name') or \
 143                     list_info.get('potInfo', {}).get('name')
 144
 145             if not list_info.get('has_more'):
 146                 break
 147
 148         return name, entries
 149
 150     def _check_clip(self, url, list_id):
 151         query_dict = parse_qs(url)
 152         if 'clipid' in query_dict:
 153             clip_id = query_dict['clipid'][0]
 154             if not self._yes_playlist(list_id, clip_id):
 155                 return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip')
 156
 157
 158 class DaumPlaylistIE(DaumListIE):
 159     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
 160     IE_NAME = 'daum.net:playlist'
 161     _URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s'
 162
 163     _TESTS = [{
 164         'note': 'Playlist url with clipid',
 165         'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
 166         'info_dict': {
 167             'id': '6213966',
 168             'title': 'Woorissica Official',
 169         },
 170         'playlist_mincount': 181,
 171     }, {
 172         'note': 'Playlist url with clipid - noplaylist',
 173         'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
 174         'info_dict': {
 175             'id': '73806844',
 176             'ext': 'mp4',
 177             'title': '151017 Airport',
 178             'upload_date': '20160117',
 179         },
 180         'params': {
 181             'noplaylist': True,
 182             'skip_download': True,
 183         },
 184     }]
 185
 186     @classmethod
 187     def suitable(cls, url):
 188         return False if DaumUserIE.suitable(url) else super().suitable(url)
 189
 190     def _real_extract(self, url):
 191         list_id = self._match_id(url)
 192
 193         clip_result = self._check_clip(url, list_id)
 194         if clip_result:
 195             return clip_result
 196
 197         name, entries = self._get_entries(list_id, 'playlistid')
 198
 199         return self.playlist_result(entries, list_id, name)
 200
 201
 202 class DaumUserIE(DaumListIE):
 203     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.(?:do|tv)\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
 204     IE_NAME = 'daum.net:user'
 205
 206     _TESTS = [{
 207         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
 208         'info_dict': {
 209             'id': 'o2scDLIVbHc0',
 210             'title': '마이 리틀 텔레비전',
 211         },
 212         'playlist_mincount': 213,
 213     }, {
 214         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
 215         'info_dict': {
 216             'id': '73801156',
 217             'ext': 'mp4',
 218             'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
 219             'upload_date': '20160117',
 220             'description': 'md5:5e91d2d6747f53575badd24bd62b9f36',
 221         },
 222         'params': {
 223             'noplaylist': True,
 224             'skip_download': True,
 225         },
 226     }, {
 227         'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
 228         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
 229         'info_dict': {
 230             'id': '6196631',
 231             'title': '마이 리틀 텔레비전 - 20160109',
 232         },
 233         'playlist_count': 11,
 234     }, {
 235         'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
 236         'only_matching': True,
 237     }, {
 238         'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733',
 239         'only_matching': True,
 240     }]
 241
 242     def _real_extract(self, url):
 243         list_id = self._match_id(url)
 244
 245         clip_result = self._check_clip(url, list_id)
 246         if clip_result:
 247             return clip_result
 248
 249         query_dict = parse_qs(url)
 250         if 'playlistid' in query_dict:
 251             playlist_id = query_dict['playlistid'][0]
 252             return self.url_result(DaumPlaylistIE._URL_TEMPLATE % playlist_id, 'DaumPlaylist')
 253
 254         name, entries = self._get_entries(list_id, 'ownerid')
 255
 256         return self.playlist_result(entries, list_id, name)