3 from __future__ import unicode_literals
8 from .common import InfoExtractor
11 compat_urllib_parse_unquote,
12 compat_urllib_parse_urlencode,
23 class DaumIE(InfoExtractor):
24 _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
28 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
30 'id': 'vab4dyeDBysyBssyukBUjBz',
32 'title': '마크 헌트 vs 안토니오 실바',
33 'description': 'Mark Hunt vs Antonio Silva',
34 'upload_date': '20131217',
35 'thumbnail': r're:^https?://.*\.(?:jpg|png)',
41 'url': 'http://m.tvpot.daum.net/v/65139429',
45 'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
46 'description': 'md5:79794514261164ff27e36a21ad229fc5',
47 'upload_date': '20150604',
48 'thumbnail': r're:^https?://.*\.(?:jpg|png)',
54 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
55 'only_matching': True,
57 'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
61 'title': '01-Korean War ( Trouble on the horizon )',
62 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
63 'upload_date': '20080223',
64 'thumbnail': r're:^https?://.*\.(?:jpg|png)',
70 # Requires dte_type=WEB (#9972)
71 'url': 'http://tvpot.daum.net/v/s3794Uf1NZeZ1qMpGpeqeRU',
72 'md5': 'a8917742069a4dd442516b86e7d66529',
74 'id': 's3794Uf1NZeZ1qMpGpeqeRU',
76 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611',
77 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회',
78 'upload_date': '20160611',
82 def _real_extract(self, url):
83 video_id = compat_urllib_parse_unquote(self._match_id(url))
84 movie_data = self._download_json(
85 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json',
86 video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'})
88 # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
89 if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
90 return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
92 info = self._download_xml(
93 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id,
94 'Downloading video info', query={'vid': video_id})
97 for format_el in movie_data['output_list']['output_list']:
98 profile = format_el['profile']
99 format_query = compat_urllib_parse_urlencode({
103 url_doc = self._download_xml(
104 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
105 video_id, note='Downloading video data for %s format' % profile)
106 format_url = url_doc.find('result/url').text
109 'format_id': profile,
110 'width': int_or_none(format_el.get('width')),
111 'height': int_or_none(format_el.get('height')),
112 'filesize': int_or_none(format_el.get('filesize')),
114 self._sort_formats(formats)
118 'title': info.find('TITLE').text,
120 'thumbnail': xpath_text(info, 'THUMB_URL'),
121 'description': xpath_text(info, 'CONTENTS'),
122 'duration': int_or_none(xpath_text(info, 'DURATION')),
123 'upload_date': info.find('REGDTTM').text[:8],
124 'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
125 'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
129 class DaumClipIE(InfoExtractor):
130 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
131 IE_NAME = 'daum.net:clip'
132 _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
135 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
139 'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
140 'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
141 'upload_date': '20130831',
142 'thumbnail': r're:^https?://.*\.(?:jpg|png)',
147 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
148 'only_matching': True,
152 def suitable(cls, url):
153 return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super(DaumClipIE, cls).suitable(url)
155 def _real_extract(self, url):
156 video_id = self._match_id(url)
157 clip_info = self._download_json(
158 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
159 video_id, 'Downloading clip info')['clip_bean']
162 '_type': 'url_transparent',
164 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
165 'title': unescapeHTML(clip_info['title']),
166 'thumbnail': clip_info.get('thumb_url'),
167 'description': clip_info.get('contents'),
168 'duration': int_or_none(clip_info.get('duration')),
169 'upload_date': clip_info.get('up_date')[:8],
170 'view_count': int_or_none(clip_info.get('play_count')),
175 class DaumListIE(InfoExtractor):
176 def _get_entries(self, list_id, list_id_type):
179 for pagenum in itertools.count(1):
180 list_info = self._download_json(
181 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % (
182 pagenum, list_id_type, list_id), list_id, 'Downloading list info - %s' % pagenum)
186 'http://tvpot.daum.net/v/%s' % clip['vid'])
187 for clip in list_info['clip_list']
191 name = list_info.get('playlist_bean', {}).get('name') or \
192 list_info.get('potInfo', {}).get('name')
194 if not list_info.get('has_more'):
199 def _check_clip(self, url, list_id):
200 query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query)
201 if 'clipid' in query_dict:
202 clip_id = query_dict['clipid'][0]
203 if self._downloader.params.get('noplaylist'):
204 self.to_screen('Downloading just video %s because of --no-playlist' % clip_id)
205 return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip')
207 self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
210 class DaumPlaylistIE(DaumListIE):
211 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
212 IE_NAME = 'daum.net:playlist'
213 _URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s'
216 'note': 'Playlist url with clipid',
217 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
220 'title': 'Woorissica Official',
222 'playlist_mincount': 181
224 'note': 'Playlist url with clipid - noplaylist',
225 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
229 'title': '151017 Airport',
230 'upload_date': '20160117',
234 'skip_download': True,
239 def suitable(cls, url):
240 return False if DaumUserIE.suitable(url) else super(DaumPlaylistIE, cls).suitable(url)
242 def _real_extract(self, url):
243 list_id = self._match_id(url)
245 clip_result = self._check_clip(url, list_id)
249 name, entries = self._get_entries(list_id, 'playlistid')
251 return self.playlist_result(entries, list_id, name)
254 class DaumUserIE(DaumListIE):
255 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.(?:do|tv)\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
256 IE_NAME = 'daum.net:user'
259 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
261 'id': 'o2scDLIVbHc0',
262 'title': '마이 리틀 텔레비전',
264 'playlist_mincount': 213
266 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
270 'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
271 'upload_date': '20160117',
272 'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
276 'skip_download': True,
279 'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
280 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
283 'title': '마이 리틀 텔레비전 - 20160109',
287 'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
288 'only_matching': True,
290 'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733',
291 'only_matching': True,
294 def _real_extract(self, url):
295 list_id = self._match_id(url)
297 clip_result = self._check_clip(url, list_id)
301 query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query)
302 if 'playlistid' in query_dict:
303 playlist_id = query_dict['playlistid'][0]
304 return self.url_result(DaumPlaylistIE._URL_TEMPLATE % playlist_id, 'DaumPlaylist')
306 name, entries = self._get_entries(list_id, 'ownerid')
308 return self.playlist_result(entries, list_id, name)