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|swf)/(?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'),
53 'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
54 'md5': '074b95bdee76b9e3654137aee9c79dfe',
58 'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
59 'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
60 'thumbnail': r
're:^https?:.*\.(?:jpg|png)$',
62 'timestamp': 1493651285,
63 'upload_date': '20170501',
64 'uploader': 'Deadline',
65 'uploader_id': 'x1xm8ri',
70 'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
71 'md5': '2137c41a8e78554bb09225b8eb322406',
75 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
76 'description': 'Several come bundled with the Steam Controller.',
77 'thumbnail': r
're:^https?:.*\.(?:jpg|png)$',
79 'timestamp': 1425657362,
80 'upload_date': '20150306',
82 'uploader_id': 'xijv66',
89 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
91 'title': 'Roar (Official)',
94 'uploader': 'Katy Perry',
95 'upload_date': '20130905',
98 'skip_download': True,
100 'skip': 'VEVO is only available in some countries',
102 # age-restricted video
103 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
104 'md5': '0d667a7b9cebecc3c89ee93099c4159d',
108 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
109 'uploader': 'HotWaves1012',
112 'skip': 'video gone',
114 # geo-restricted, player v5
115 'url': 'http://www.dailymotion.com/video/xhza0o',
116 'only_matching': True,
119 'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
120 'only_matching': True,
122 'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
123 'only_matching': True,
125 'url': 'http://www.dailymotion.com/swf/x3ss1m_funny-magic-trick-barry-and-stuart_fun',
126 'only_matching': True,
130 def _extract_urls(webpage
):
131 # Look for embedded Dailymotion player
132 matches
= re
.findall(
133 r
'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^
>]+value
=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
134 return list(map(lambda m: unescapeHTML(m[1]), matches))
136 def _real_extract(self, url):
137 video_id = self._match_id(url)
139 webpage = self._download_webpage_no_ff(
140 'https://www.dailymotion.com/video/%s' % video_id, video_id)
142 age_limit = self._rta_search(webpage)
144 description = self._og_search_description(webpage) or self._html_search_meta(
145 'description', webpage, 'description')
147 view_count_str = self._search_regex(
148 (r'<meta[^>]+itemprop="interactionCount
"[^>]+content="UserPlays
:([\s\d
,.]+)"',
149 r'video_views_count[^>]+>\s+([\s\d\,.]+)'),
150 webpage, 'view count', default=None)
152 view_count_str = re.sub(r'\s', '', view_count_str)
153 view_count = str_to_int(view_count_str)
154 comment_count = int_or_none(self._search_regex(
155 r'<meta[^>]+itemprop="interactionCount
"[^>]+content="UserComments
:(\d
+)"',
156 webpage, 'comment count', default=None))
158 player_v5 = self._search_regex(
159 [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826
160 r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
161 r'buildPlayer\(({.+?})\);',
162 r'var\s+config\s*=\s*({.+?});',
163 # New layout regex (see https://github.com/rg3/youtube-dl/issues/13580)
164 r'__PLAYER_CONFIG__\s*=\s*({.+?});'],
165 webpage, 'player v5', default=None)
167 player = self._parse_json(player_v5, video_id)
168 metadata = player['metadata']
170 self._check_error(metadata)
173 for quality, media_list in metadata['qualities'].items():
174 for media in media_list:
175 media_url = media.get('url')
178 type_ = media.get('type')
179 if type_ == 'application/vnd.lumberjack.manifest':
181 ext = mimetype2ext(type_) or determine_ext(media_url)
183 formats.extend(self._extract_m3u8_formats(
184 media_url, video_id, 'mp4', preference=-1,
185 m3u8_id='hls', fatal=False))
187 formats.extend(self._extract_f4m_formats(
188 media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
192 'format_id': 'http-%s' % quality,
195 m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
198 'width': int(m.group('width')),
199 'height': int(m.group('height')),
202 self._sort_formats(formats)
204 title = metadata['title']
205 duration = int_or_none(metadata.get('duration'))
206 timestamp = int_or_none(metadata.get('created_time'))
207 thumbnail = metadata.get('poster_url')
208 uploader = metadata.get('owner', {}).get('screenname')
209 uploader_id = metadata.get('owner', {}).get('id')
212 subtitles_data = metadata.get('subtitles', {}).get('data', {})
213 if subtitles_data and isinstance(subtitles_data, dict):
214 for subtitle_lang, subtitle in subtitles_data.items():
215 subtitles[subtitle_lang] = [{
216 'ext': determine_ext(subtitle_url),
218 } for subtitle_url in subtitle.get('urls', [])]
223 'description': description,
224 'thumbnail': thumbnail,
225 'duration': duration,
226 'timestamp': timestamp,
227 'uploader': uploader,
228 'uploader_id': uploader_id,
229 'age_limit': age_limit,
230 'view_count': view_count,
231 'comment_count': comment_count,
233 'subtitles': subtitles,
237 vevo_id = self._search_regex(
238 r'<link rel="video_src
" href="[^
"]*?vevo\.com[^"]*?video
=(?P
<id>[\w
]*)',
239 webpage, 'vevo embed
', default=None)
241 return self.url_result('vevo
:%s' % vevo_id, 'Vevo
')
243 # fallback old player
244 embed_page = self._download_webpage_no_ff(
245 'https
://www
.dailymotion
.com
/embed
/video
/%s' % video_id,
246 video_id, 'Downloading embed page
')
248 timestamp = parse_iso8601(self._html_search_meta(
249 'video
:release_date
', webpage, 'upload date
'))
251 info = self._parse_json(
253 r'var info
= ({.*?
}),$
', embed_page,
254 'video info
', flags=re.MULTILINE),
257 self._check_error(info)
260 for (key, format_id) in self._FORMATS:
261 video_url = info.get(key)
262 if video_url is not None:
263 m_size = re.search(r'H264
-(\d
+)x(\d
+)', video_url)
264 if m_size is not None:
265 width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
267 width, height = None, None
271 'format_id
': format_id,
275 self._sort_formats(formats)
278 video_subtitles = self.extract_subtitles(video_id, webpage)
280 title = self._og_search_title(webpage, default=None)
282 title = self._html_search_regex(
283 r'(?s
)<span\s
+id="video_title"[^
>]*>(.*?
)</span
>', webpage,
289 'uploader
': info['owner
.screenname
'],
290 'timestamp
': timestamp,
292 'description
': description,
293 'subtitles
': video_subtitles,
294 'thumbnail
': info['thumbnail_url
'],
295 'age_limit
': age_limit,
296 'view_count
': view_count,
297 'duration
': info['duration
']
300 def _check_error(self, info):
301 error = info.get('error
')
302 if info.get('error
') is not None:
303 title = error['title
']
304 # See https://developer.dailymotion.com/api#access-error
305 if error.get('code
') == 'DM007
':
306 self.raise_geo_restricted(msg=title)
307 raise ExtractorError(
308 '%s said
: %s' % (self.IE_NAME, title), expected=True)
310 def _get_subtitles(self, video_id, webpage):
312 sub_list = self._download_webpage(
313 'https
://api
.dailymotion
.com
/video
/%s/subtitles?fields
=id,language
,url
' % video_id,
314 video_id, note=False)
315 except ExtractorError as err:
316 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
318 info = json.loads(sub_list)
319 if (info['total
'] > 0):
320 sub_lang_list = dict((l['language
'], [{'url
': l['url
'], 'ext
': 'srt
'}]) for l in info['list'])
322 self._downloader.report_warning('video doesn
\'t have subtitles
')
326 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
327 IE_NAME = 'dailymotion
:playlist
'
328 _VALID_URL = r'(?
:https?
://)?
(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}/playlist
/(?P
<id>[^
/?
#&]+)'
329 _MORE_PAGES_INDICATOR
= r
'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
330 _PAGE_TEMPLATE
= 'https://www.dailymotion.com/playlist/%s/%s'
332 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
335 'id': 'xv4bw_nqtv_sport',
337 'playlist_mincount': 20,
340 def _extract_entries(self
, id):
342 processed_urls
= set()
343 for pagenum
in itertools
.count(1):
344 page_url
= self
._PAGE
_TEMPLATE
% (id, pagenum
)
345 webpage
, urlh
= self
._download
_webpage
_handle
_no
_ff
(
346 page_url
, id, 'Downloading page %s' % pagenum
)
347 if urlh
.geturl() in processed_urls
:
348 self
.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
349 page_url
, urlh
.geturl()), id)
352 processed_urls
.add(urlh
.geturl())
354 for video_id
in re
.findall(r
'data-xid="(.+?)"', webpage
):
355 if video_id
not in video_ids
:
356 yield self
.url_result(
357 'http://www.dailymotion.com/video/%s' % video_id
,
358 DailymotionIE
.ie_key(), video_id
)
359 video_ids
.add(video_id
)
361 if re
.search(self
._MORE
_PAGES
_INDICATOR
, webpage
) is None:
364 def _real_extract(self
, url
):
365 mobj
= re
.match(self
._VALID
_URL
, url
)
366 playlist_id
= mobj
.group('id')
367 webpage
= self
._download
_webpage
(url
, playlist_id
)
372 'title': self
._og
_search
_title
(webpage
),
373 'entries': self
._extract
_entries
(playlist_id
),
377 class DailymotionUserIE(DailymotionPlaylistIE
):
378 IE_NAME
= 'dailymotion:user'
379 _VALID_URL
= r
'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
380 _PAGE_TEMPLATE
= 'http://www.dailymotion.com/user/%s/%s'
382 'url': 'https://www.dailymotion.com/user/nqtv',
385 'title': 'Rémi Gaillard',
387 'playlist_mincount': 100,
389 'url': 'http://www.dailymotion.com/user/UnderProject',
391 'id': 'UnderProject',
392 'title': 'UnderProject',
394 'playlist_mincount': 1800,
395 'expected_warnings': [
396 'Stopped at duplicated page',
398 'skip': 'Takes too long time',
401 def _real_extract(self
, url
):
402 mobj
= re
.match(self
._VALID
_URL
, url
)
403 user
= mobj
.group('user')
404 webpage
= self
._download
_webpage
(
405 'https://www.dailymotion.com/user/%s' % user
, user
)
406 full_user
= unescapeHTML(self
._html
_search
_regex
(
407 r
'<a class="nav-image" title="([^"]+)" href="/%s">' % re
.escape(user
),
414 'entries': self
._extract
_entries
(user
),