2 from __future__ import unicode_literals
8 from .common import InfoExtractor
10 from ..compat import (
12 compat_urllib_request,
25 class DailymotionBaseInfoExtractor(InfoExtractor):
27 def _build_request(url):
28 """Build a request with the family filter disabled"""
29 request = compat_urllib_request.Request(url)
30 request.add_header('Cookie', 'family_filter=off; ff=off')
33 def _download_webpage_handle_no_ff(self, url, *args, **kwargs):
34 request = self._build_request(url)
35 return self._download_webpage_handle(request, *args, **kwargs)
37 def _download_webpage_no_ff(self, url, *args, **kwargs):
38 request = self._build_request(url)
39 return self._download_webpage(request, *args, **kwargs)
42 class DailymotionIE(DailymotionBaseInfoExtractor):
43 _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
44 IE_NAME = 'dailymotion'
47 ('stream_h264_ld_url', 'ld'),
48 ('stream_h264_url', 'standard'),
49 ('stream_h264_hq_url', 'hq'),
50 ('stream_h264_hd_url', 'hd'),
51 ('stream_h264_hd1080_url', 'hd180'),
56 'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
57 'md5': '2137c41a8e78554bb09225b8eb322406',
61 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
62 'description': 'Several come bundled with the Steam Controller.',
63 'thumbnail': 're:^https?:.*\.(?:jpg|png)$',
65 'timestamp': 1425657362,
66 'upload_date': '20150306',
68 'uploader_id': 'xijv66',
76 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
78 'title': 'Roar (Official)',
81 'uploader': 'Katy Perry',
82 'upload_date': '20130905',
85 'skip_download': True,
87 'skip': 'VEVO is only available in some countries',
89 # age-restricted video
91 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
92 'md5': '0d667a7b9cebecc3c89ee93099c4159d',
96 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
97 'uploader': 'HotWaves1012',
103 def _real_extract(self, url):
104 video_id = self._match_id(url)
106 webpage = self._download_webpage_no_ff(
107 'https://www.dailymotion.com/video/%s' % video_id, video_id)
109 age_limit = self._rta_search(webpage)
111 description = self._og_search_description(webpage) or self._html_search_meta(
112 'description', webpage, 'description')
114 view_count = str_to_int(self._search_regex(
115 [r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"',
116 r'video_views_count[^>]+>\s+([\d\.,]+)'],
117 webpage, 'view count', fatal=False))
118 comment_count = int_or_none(self._search_regex(
119 r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
120 webpage, 'comment count', fatal=False))
122 player_v5 = self._search_regex(
123 r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
124 webpage, 'player v5', default=None)
126 player = self._parse_json(player_v5, video_id)
127 metadata = player['metadata']
129 for quality, media_list in metadata['qualities'].items():
130 for media in media_list:
131 media_url = media.get('url')
134 type_ = media.get('type')
135 if type_ == 'application/vnd.lumberjack.manifest':
137 if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8':
138 formats.extend(self._extract_m3u8_formats(
139 media_url, video_id, 'mp4', m3u8_id='hls'))
143 'format_id': quality,
145 m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
148 'width': int(m.group('width')),
149 'height': int(m.group('height')),
152 self._sort_formats(formats)
154 title = metadata['title']
155 duration = int_or_none(metadata.get('duration'))
156 timestamp = int_or_none(metadata.get('created_time'))
157 thumbnail = metadata.get('poster_url')
158 uploader = metadata.get('owner', {}).get('screenname')
159 uploader_id = metadata.get('owner', {}).get('id')
162 for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items():
163 subtitles[subtitle_lang] = [{
164 'ext': determine_ext(subtitle_url),
166 } for subtitle_url in subtitle.get('urls', [])]
171 'description': description,
172 'thumbnail': thumbnail,
173 'duration': duration,
174 'timestamp': timestamp,
175 'uploader': uploader,
176 'uploader_id': uploader_id,
177 'age_limit': age_limit,
178 'view_count': view_count,
179 'comment_count': comment_count,
181 'subtitles': subtitles,
185 vevo_id = self._search_regex(
186 r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
187 webpage, 'vevo embed', default=None)
189 return self.url_result('vevo:%s' % vevo_id, 'Vevo')
191 # fallback old player
192 embed_page = self._download_webpage_no_ff(
193 'https://www.dailymotion.com/embed/video/%s' % video_id,
194 video_id, 'Downloading embed page')
196 timestamp = parse_iso8601(self._html_search_meta(
197 'video:release_date', webpage, 'upload date'))
199 info = self._parse_json(
201 r'var info = ({.*?}),$', embed_page,
202 'video info', flags=re.MULTILINE),
205 if info.get('error') is not None:
206 msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
207 raise ExtractorError(msg, expected=True)
210 for (key, format_id) in self._FORMATS:
211 video_url = info.get(key)
212 if video_url is not None:
213 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
214 if m_size is not None:
215 width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
217 width, height = None, None
221 'format_id': format_id,
225 self._sort_formats(formats)
228 video_subtitles = self.extract_subtitles(video_id, webpage)
230 title = self._og_search_title(webpage, default=None)
232 title = self._html_search_regex(
233 r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
239 'uploader': info['owner.screenname'],
240 'timestamp': timestamp,
242 'description': description,
243 'subtitles': video_subtitles,
244 'thumbnail': info['thumbnail_url'],
245 'age_limit': age_limit,
246 'view_count': view_count,
247 'duration': info['duration']
250 def _get_subtitles(self, video_id, webpage):
252 sub_list = self._download_webpage(
253 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
254 video_id, note=False)
255 except ExtractorError as err:
256 self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
258 info = json.loads(sub_list)
259 if (info['total'] > 0):
260 sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list'])
262 self._downloader.report_warning('video doesn\'t have subtitles')
266 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
267 IE_NAME = 'dailymotion:playlist'
268 _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
269 _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
270 _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
272 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
275 'id': 'xv4bw_nqtv_sport',
277 'playlist_mincount': 20,
280 def _extract_entries(self, id):
282 processed_urls = set()
283 for pagenum in itertools.count(1):
284 page_url = self._PAGE_TEMPLATE % (id, pagenum)
285 webpage, urlh = self._download_webpage_handle_no_ff(
286 page_url, id, 'Downloading page %s' % pagenum)
287 if urlh.geturl() in processed_urls:
288 self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
289 page_url, urlh.geturl()), id)
292 processed_urls.add(urlh.geturl())
294 video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
296 if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
298 return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
299 for video_id in orderedSet(video_ids)]
301 def _real_extract(self, url):
302 mobj = re.match(self._VALID_URL, url)
303 playlist_id = mobj.group('id')
304 webpage = self._download_webpage(url, playlist_id)
309 'title': self._og_search_title(webpage),
310 'entries': self._extract_entries(playlist_id),
314 class DailymotionUserIE(DailymotionPlaylistIE):
315 IE_NAME = 'dailymotion:user'
316 _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
317 _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
319 'url': 'https://www.dailymotion.com/user/nqtv',
322 'title': 'RĂ©mi Gaillard',
324 'playlist_mincount': 100,
326 'url': 'http://www.dailymotion.com/user/UnderProject',
328 'id': 'UnderProject',
329 'title': 'UnderProject',
331 'playlist_mincount': 1800,
332 'expected_warnings': [
333 'Stopped at duplicated page',
335 'skip': 'Takes too long time',
338 def _real_extract(self, url):
339 mobj = re.match(self._VALID_URL, url)
340 user = mobj.group('user')
341 webpage = self._download_webpage(
342 'https://www.dailymotion.com/user/%s' % user, user)
343 full_user = unescapeHTML(self._html_search_regex(
344 r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
351 'entries': self._extract_entries(user),
355 class DailymotionCloudIE(DailymotionBaseInfoExtractor):
356 _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
357 _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
358 _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
361 # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
362 # Tested at FranceTvInfo_2
363 'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
364 'only_matching': True,
366 # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
367 'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
368 'only_matching': True,
372 def _extract_dmcloud_url(self, webpage):
373 mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
378 r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
383 def _real_extract(self, url):
384 video_id = self._match_id(url)
386 webpage = self._download_webpage_no_ff(url, video_id)
388 title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
390 video_info = self._parse_json(self._search_regex(
391 r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
393 # TODO: parse ios_url, which is in fact a manifest
394 video_url = video_info['mp4_url']
400 'thumbnail': video_info.get('thumbnail_url'),