3 from __future__ import unicode_literals
8 from .common import InfoExtractor
11 compat_urllib_parse_unquote,
21 class DaumIE(InfoExtractor):
22 _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
26 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
28 'id': 'vab4dyeDBysyBssyukBUjBz',
30 'title': '마크 헌트 vs 안토니오 실바',
31 'description': 'Mark Hunt vs Antonio Silva',
32 'upload_date': '20131217',
33 'thumbnail': 're:^https?://.*\.(?:jpg|png)',
39 'url': 'http://m.tvpot.daum.net/v/65139429',
43 'title': 'md5:a100d65d09cec246d8aa9bde7de45aed',
44 'description': 'md5:79794514261164ff27e36a21ad229fc5',
45 'upload_date': '20150604',
46 'thumbnail': 're:^https?://.*\.(?:jpg|png)',
52 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
53 'only_matching': True,
55 'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
59 'title': '01-Korean War ( Trouble on the horizon )',
60 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
61 'upload_date': '20080223',
62 'thumbnail': 're:^https?://.*\.(?:jpg|png)',
69 def _real_extract(self, url):
70 video_id = compat_urllib_parse_unquote(self._match_id(url))
71 query = compat_urllib_parse.urlencode({'vid': video_id})
72 movie_data = self._download_json(
73 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
74 video_id, 'Downloading video formats info')
76 # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
77 if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
78 return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
80 info = self._download_xml(
81 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
82 'Downloading video info')
85 for format_el in movie_data['output_list']['output_list']:
86 profile = format_el['profile']
87 format_query = compat_urllib_parse.urlencode({
91 url_doc = self._download_xml(
92 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
93 video_id, note='Downloading video data for %s format' % profile)
94 format_url = url_doc.find('result/url').text
98 'width': int_or_none(format_el.get('width')),
99 'height': int_or_none(format_el.get('height')),
100 'filesize': int_or_none(format_el.get('filesize')),
102 self._sort_formats(formats)
106 'title': info.find('TITLE').text,
108 'thumbnail': xpath_text(info, 'THUMB_URL'),
109 'description': xpath_text(info, 'CONTENTS'),
110 'duration': int_or_none(xpath_text(info, 'DURATION')),
111 'upload_date': info.find('REGDTTM').text[:8],
112 'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
113 'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
117 class DaumClipIE(InfoExtractor):
118 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
119 IE_NAME = 'daum.net:clip'
122 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
126 'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
127 'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
128 'upload_date': '20130831',
129 'thumbnail': 're:^https?://.*\.(?:jpg|png)',
134 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
135 'only_matching': True,
138 def _real_extract(self, url):
139 video_id = self._match_id(url)
140 clip_info = self._download_json(
141 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
142 video_id, 'Downloading clip info')['clip_bean']
145 '_type': 'url_transparent',
147 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
148 'title': unescapeHTML(clip_info['title']),
149 'thumbnail': clip_info.get('thumb_url'),
150 'description': clip_info.get('contents'),
151 'duration': int_or_none(clip_info.get('duration')),
152 'upload_date': clip_info.get('up_date')[:8],
153 'view_count': int_or_none(clip_info.get('play_count')),
158 class DaumListIE(InfoExtractor):
159 def _get_entries(self, list_id, list_id_type):
162 for pagenum in itertools.count(1):
163 list_info = self._download_json(
164 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % (
165 pagenum, list_id_type, list_id), list_id, 'Downloading list info - %s' % pagenum)
169 'http://tvpot.daum.net/v/%s' % clip['vid'])
170 for clip in list_info['clip_list']
174 name = list_info.get('playlist_bean', {}).get('name') or \
175 list_info.get('potInfo', {}).get('name')
177 if not list_info.get('has_more'):
183 class DaumPlaylistIE(DaumListIE):
184 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
185 IE_NAME = 'daum.net:playlist'
188 'note': 'Playlist url with clipid',
189 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
192 'title': 'Woorissica Official',
194 'playlist_mincount': 181
196 'note': 'Playlist url with clipid - noplaylist',
197 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
201 'title': '151017 Airport',
202 'upload_date': '20160117',
206 'skip_download': True,
210 def _real_extract(self, url):
211 if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'):
212 return self.url_result(url, 'DaumClip')
214 list_id = self._match_id(url)
215 self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
217 name, entries = self._get_entries(list_id, 'playlistid')
219 return self.playlist_result(entries, list_id, name)
222 class DaumUserIE(DaumListIE):
223 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.do\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
224 IE_NAME = 'daum.net:user'
227 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
229 'id': 'o2scDLIVbHc0',
230 'title': '마이 리틀 텔레비전',
232 'playlist_mincount': 213
234 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
238 'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
239 'upload_date': '20160117',
240 'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
244 'skip_download': True,
247 'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
248 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
251 'title': '마이 리틀 텔레비전 - 20160109',
255 'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
256 'only_matching': True,
259 def _real_extract(self, url):
260 if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'):
261 return self.url_result(url, 'DaumClip')
263 if DaumPlaylistIE.suitable(url):
264 return self.url_result(url, 'DaumPlaylist')
266 list_id = self._match_id(url)
267 self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
268 name, entries = self._get_entries(list_id, 'ownerid')
270 return self.playlist_result(entries, list_id, name)