2 from __future__ import unicode_literals
8 from .common import InfoExtractor
23 class DailymotionBaseInfoExtractor(InfoExtractor):
25 def _build_request(url):
26 """Build a request with the family filter disabled"""
27 request = sanitized_Request(url)
28 request.add_header('Cookie', 'family_filter=off; ff=off')
31 def _download_webpage_handle_no_ff(self, url, *args, **kwargs):
32 request = self._build_request(url)
33 return self._download_webpage_handle(request, *args, **kwargs)
35 def _download_webpage_no_ff(self, url, *args, **kwargs):
36 request = self._build_request(url)
37 return self._download_webpage(request, *args, **kwargs)
40 class DailymotionIE(DailymotionBaseInfoExtractor):
41 _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)'
42 IE_NAME = 'dailymotion'
45 ('stream_h264_ld_url', 'ld'),
46 ('stream_h264_url', 'standard'),
47 ('stream_h264_hq_url', 'hq'),
48 ('stream_h264_hd_url', 'hd'),
49 ('stream_h264_hd1080_url', 'hd180'),
54 'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
55 'md5': '2137c41a8e78554bb09225b8eb322406',
59 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
60 'description': 'Several come bundled with the Steam Controller.',
61 'thumbnail': 're:^https?:.*\.(?:jpg|png)$',
63 'timestamp': 1425657362,
64 'upload_date': '20150306',
66 'uploader_id': 'xijv66',
74 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
76 'title': 'Roar (Official)',
79 'uploader': 'Katy Perry',
80 'upload_date': '20130905',
83 'skip_download': True,
85 'skip': 'VEVO is only available in some countries',
87 # age-restricted video
89 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
90 'md5': '0d667a7b9cebecc3c89ee93099c4159d',
94 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
95 'uploader': 'HotWaves1012',
99 # geo-restricted, player v5
101 'url': 'http://www.dailymotion.com/video/xhza0o',
102 'only_matching': True,
106 'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
107 'only_matching': True,
110 'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
111 'only_matching': True,
115 def _real_extract(self, url):
116 video_id = self._match_id(url)
118 webpage = self._download_webpage_no_ff(
119 'https://www.dailymotion.com/video/%s' % video_id, video_id)
121 age_limit = self._rta_search(webpage)
123 description = self._og_search_description(webpage) or self._html_search_meta(
124 'description', webpage, 'description')
126 view_count_str = self._search_regex(
127 (r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"',
128 r'video_views_count[^>]+>\s+([\s\d\,.]+)'),
129 webpage, 'view count', fatal=False)
131 view_count_str = re.sub(r'\s', '', view_count_str)
132 view_count = str_to_int(view_count_str)
133 comment_count = int_or_none(self._search_regex(
134 r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
135 webpage, 'comment count', fatal=False))
137 player_v5 = self._search_regex(
138 [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826
139 r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
140 r'buildPlayer\(({.+?})\);'],
141 webpage, 'player v5', default=None)
143 player = self._parse_json(player_v5, video_id)
144 metadata = player['metadata']
146 self._check_error(metadata)
149 for quality, media_list in metadata['qualities'].items():
150 for media in media_list:
151 media_url = media.get('url')
154 type_ = media.get('type')
155 if type_ == 'application/vnd.lumberjack.manifest':
157 ext = mimetype2ext(type_) or determine_ext(media_url)
159 formats.extend(self._extract_m3u8_formats(
160 media_url, video_id, 'mp4', preference=-1,
161 m3u8_id='hls', fatal=False))
163 formats.extend(self._extract_f4m_formats(
164 media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
168 'format_id': 'http-%s' % quality,
171 m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
174 'width': int(m.group('width')),
175 'height': int(m.group('height')),
178 self._sort_formats(formats)
180 title = metadata['title']
181 duration = int_or_none(metadata.get('duration'))
182 timestamp = int_or_none(metadata.get('created_time'))
183 thumbnail = metadata.get('poster_url')
184 uploader = metadata.get('owner', {}).get('screenname')
185 uploader_id = metadata.get('owner', {}).get('id')
188 subtitles_data = metadata.get('subtitles', {}).get('data', {})
189 if subtitles_data and isinstance(subtitles_data, dict):
190 for subtitle_lang, subtitle in subtitles_data.items():
191 subtitles[subtitle_lang] = [{
192 'ext': determine_ext(subtitle_url),
194 } for subtitle_url in subtitle.get('urls', [])]
199 'description': description,
200 'thumbnail': thumbnail,
201 'duration': duration,
202 'timestamp': timestamp,
203 'uploader': uploader,
204 'uploader_id': uploader_id,
205 'age_limit': age_limit,
206 'view_count': view_count,
207 'comment_count': comment_count,
209 'subtitles': subtitles,
213 vevo_id = self._search_regex(
214 r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
215 webpage, 'vevo embed', default=None)
217 return self.url_result('vevo:%s' % vevo_id, 'Vevo')
219 # fallback old player
220 embed_page = self._download_webpage_no_ff(
221 'https://www.dailymotion.com/embed/video/%s' % video_id,
222 video_id, 'Downloading embed page')
224 timestamp = parse_iso8601(self._html_search_meta(
225 'video:release_date', webpage, 'upload date'))
227 info = self._parse_json(
229 r'var info = ({.*?}),$', embed_page,
230 'video info', flags=re.MULTILINE),
233 self._check_error(info)
236 for (key, format_id) in self._FORMATS:
237 video_url = info.get(key)
238 if video_url is not None:
239 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
240 if m_size is not None:
241 width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
243 width, height = None, None
247 'format_id': format_id,
251 self._sort_formats(formats)
254 video_subtitles = self.extract_subtitles(video_id, webpage)
256 title = self._og_search_title(webpage, default=None)
258 title = self._html_search_regex(
259 r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
265 'uploader': info['owner.screenname'],
266 'timestamp': timestamp,
268 'description': description,
269 'subtitles': video_subtitles,
270 'thumbnail': info['thumbnail_url'],
271 'age_limit': age_limit,
272 'view_count': view_count,
273 'duration': info['duration']
276 def _check_error(self, info):
277 if info.get('error') is not None:
278 raise ExtractorError(
279 '%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
281 def _get_subtitles(self, video_id, webpage):
283 sub_list = self._download_webpage(
284 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
285 video_id, note=False)
286 except ExtractorError as err:
287 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
289 info = json.loads(sub_list)
290 if (info['total'] > 0):
291 sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list'])
293 self._downloader.report_warning('video doesn\'t have subtitles')
297 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
298 IE_NAME = 'dailymotion:playlist'
299 _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
300 _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
301 _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
303 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
306 'id': 'xv4bw_nqtv_sport',
308 'playlist_mincount': 20,
311 def _extract_entries(self, id):
313 processed_urls = set()
314 for pagenum in itertools.count(1):
315 page_url = self._PAGE_TEMPLATE % (id, pagenum)
316 webpage, urlh = self._download_webpage_handle_no_ff(
317 page_url, id, 'Downloading page %s' % pagenum)
318 if urlh.geturl() in processed_urls:
319 self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
320 page_url, urlh.geturl()), id)
323 processed_urls.add(urlh.geturl())
325 for video_id in re.findall(r'data-xid="(.+?)"', webpage):
326 if video_id not in video_ids:
327 yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
328 video_ids.add(video_id)
330 if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
333 def _real_extract(self, url):
334 mobj = re.match(self._VALID_URL, url)
335 playlist_id = mobj.group('id')
336 webpage = self._download_webpage(url, playlist_id)
341 'title': self._og_search_title(webpage),
342 'entries': self._extract_entries(playlist_id),
346 class DailymotionUserIE(DailymotionPlaylistIE):
347 IE_NAME = 'dailymotion:user'
348 _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
349 _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
351 'url': 'https://www.dailymotion.com/user/nqtv',
354 'title': 'RĂ©mi Gaillard',
356 'playlist_mincount': 100,
358 'url': 'http://www.dailymotion.com/user/UnderProject',
360 'id': 'UnderProject',
361 'title': 'UnderProject',
363 'playlist_mincount': 1800,
364 'expected_warnings': [
365 'Stopped at duplicated page',
367 'skip': 'Takes too long time',
370 def _real_extract(self, url):
371 mobj = re.match(self._VALID_URL, url)
372 user = mobj.group('user')
373 webpage = self._download_webpage(
374 'https://www.dailymotion.com/user/%s' % user, user)
375 full_user = unescapeHTML(self._html_search_regex(
376 r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
383 'entries': self._extract_entries(user),
387 class DailymotionCloudIE(DailymotionBaseInfoExtractor):
388 _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
389 _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
390 _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
393 # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
394 # Tested at FranceTvInfo_2
395 'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
396 'only_matching': True,
398 # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
399 'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
400 'only_matching': True,
404 def _extract_dmcloud_url(cls, webpage):
405 mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage)
410 r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL,
415 def _real_extract(self, url):
416 video_id = self._match_id(url)
418 webpage = self._download_webpage_no_ff(url, video_id)
420 title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
422 video_info = self._parse_json(self._search_regex(
423 r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
425 # TODO: parse ios_url, which is in fact a manifest
426 video_url = video_info['mp4_url']
432 'thumbnail': video_info.get('thumbnail_url'),