]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/daum.py
New upstream version 2019.09.01
[youtubedl] / youtube_dl / extractor / daum.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import re
6 import itertools
7
8 from .common import InfoExtractor
9 from ..compat import (
10 compat_parse_qs,
11 compat_urllib_parse_unquote,
12 compat_urllib_parse_urlencode,
13 compat_urlparse,
14 )
15 from ..utils import (
16 int_or_none,
17 str_to_int,
18 xpath_text,
19 unescapeHTML,
20 )
21
22
23 class DaumIE(InfoExtractor):
24 _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
25 IE_NAME = 'daum.net'
26
27 _TESTS = [{
28 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
29 'info_dict': {
30 'id': 'vab4dyeDBysyBssyukBUjBz',
31 'ext': 'mp4',
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)',
36 'duration': 2117,
37 'view_count': int,
38 'comment_count': int,
39 },
40 }, {
41 'url': 'http://m.tvpot.daum.net/v/65139429',
42 'info_dict': {
43 'id': '65139429',
44 'ext': 'mp4',
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)',
49 'duration': 154,
50 'view_count': int,
51 'comment_count': int,
52 },
53 }, {
54 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
55 'only_matching': True,
56 }, {
57 'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
58 'info_dict': {
59 'id': 'vwIpVpCQsT8$',
60 'ext': 'flv',
61 'title': '01-Korean War ( Trouble on the horizon )',
62 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
63 'upload_date': '20080223',
64 'thumbnail': r're:^https?://.*\.(?:jpg|png)',
65 'duration': 249,
66 'view_count': int,
67 'comment_count': int,
68 },
69 }, {
70 # Requires dte_type=WEB (#9972)
71 'url': 'http://tvpot.daum.net/v/s3794Uf1NZeZ1qMpGpeqeRU',
72 'md5': 'a8917742069a4dd442516b86e7d66529',
73 'info_dict': {
74 'id': 's3794Uf1NZeZ1qMpGpeqeRU',
75 'ext': 'mp4',
76 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611',
77 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회',
78 'upload_date': '20160611',
79 },
80 }]
81
82 def _real_extract(self, url):
83 video_id = compat_urllib_parse_unquote(self._match_id(url))
84 movie_data = self._download_json(
85 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json',
86 video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'})
87
88 # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
89 if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
90 return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
91
92 info = self._download_xml(
93 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id,
94 'Downloading video info', query={'vid': video_id})
95
96 formats = []
97 for format_el in movie_data['output_list']['output_list']:
98 profile = format_el['profile']
99 format_query = compat_urllib_parse_urlencode({
100 'vid': video_id,
101 'profile': profile,
102 })
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
107 formats.append({
108 'url': format_url,
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')),
113 })
114 self._sort_formats(formats)
115
116 return {
117 'id': video_id,
118 'title': info.find('TITLE').text,
119 'formats': formats,
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')),
126 }
127
128
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'
133
134 _TESTS = [{
135 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
136 'info_dict': {
137 'id': '52554690',
138 'ext': 'mp4',
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)',
143 'duration': 3868,
144 'view_count': int,
145 },
146 }, {
147 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
148 'only_matching': True,
149 }]
150
151 @classmethod
152 def suitable(cls, url):
153 return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super(DaumClipIE, cls).suitable(url)
154
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']
160
161 return {
162 '_type': 'url_transparent',
163 'id': video_id,
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')),
171 'ie_key': 'Daum',
172 }
173
174
175 class DaumListIE(InfoExtractor):
176 def _get_entries(self, list_id, list_id_type):
177 name = None
178 entries = []
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)
183
184 entries.extend([
185 self.url_result(
186 'http://tvpot.daum.net/v/%s' % clip['vid'])
187 for clip in list_info['clip_list']
188 ])
189
190 if not name:
191 name = list_info.get('playlist_bean', {}).get('name') or \
192 list_info.get('potInfo', {}).get('name')
193
194 if not list_info.get('has_more'):
195 break
196
197 return name, entries
198
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')
206 else:
207 self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
208
209
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'
214
215 _TESTS = [{
216 'note': 'Playlist url with clipid',
217 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
218 'info_dict': {
219 'id': '6213966',
220 'title': 'Woorissica Official',
221 },
222 'playlist_mincount': 181
223 }, {
224 'note': 'Playlist url with clipid - noplaylist',
225 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
226 'info_dict': {
227 'id': '73806844',
228 'ext': 'mp4',
229 'title': '151017 Airport',
230 'upload_date': '20160117',
231 },
232 'params': {
233 'noplaylist': True,
234 'skip_download': True,
235 }
236 }]
237
238 @classmethod
239 def suitable(cls, url):
240 return False if DaumUserIE.suitable(url) else super(DaumPlaylistIE, cls).suitable(url)
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 name, entries = self._get_entries(list_id, 'playlistid')
250
251 return self.playlist_result(entries, list_id, name)
252
253
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'
257
258 _TESTS = [{
259 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
260 'info_dict': {
261 'id': 'o2scDLIVbHc0',
262 'title': '마이 리틀 텔레비전',
263 },
264 'playlist_mincount': 213
265 }, {
266 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
267 'info_dict': {
268 'id': '73801156',
269 'ext': 'mp4',
270 'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
271 'upload_date': '20160117',
272 'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
273 },
274 'params': {
275 'noplaylist': True,
276 'skip_download': True,
277 }
278 }, {
279 'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
280 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
281 'info_dict': {
282 'id': '6196631',
283 'title': '마이 리틀 텔레비전 - 20160109',
284 },
285 'playlist_count': 11
286 }, {
287 'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
288 'only_matching': True,
289 }, {
290 'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733',
291 'only_matching': True,
292 }]
293
294 def _real_extract(self, url):
295 list_id = self._match_id(url)
296
297 clip_result = self._check_clip(url, list_id)
298 if clip_result:
299 return clip_result
300
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')
305
306 name, entries = self._get_entries(list_id, 'ownerid')
307
308 return self.playlist_result(entries, list_id, name)