aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/generic.py
blob: c1e53382181fc035dc87475fd51b6249ed79dab3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
# encoding: utf-8

from __future__ import unicode_literals

import os
import re

from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
    compat_urllib_error,
    compat_urllib_parse,
    compat_urllib_request,
    compat_urlparse,
    compat_xml_parse_error,

    ExtractorError,
    HEADRequest,
    parse_xml,
    smuggle_url,
    unescapeHTML,
    unified_strdate,
    url_basename,
)
from .brightcove import BrightcoveIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
from .smotri import SmotriIE


class GenericIE(InfoExtractor):
    IE_DESC = 'Generic downloader that works on some sites'
    _VALID_URL = r'.*'
    IE_NAME = 'generic'
    _TESTS = [
        {
            'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
            'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
            'info_dict': {
                'id': '13601338388002',
                'ext': 'mp4',
                'uploader': 'www.hodiho.fr',
                'title': 'R\u00e9gis plante sa Jeep',
            }
        },
        # bandcamp page with custom domain
        {
            'add_ie': ['Bandcamp'],
            'url': 'http://bronyrock.com/track/the-pony-mash',
            'info_dict': {
                'id': '3235767654',
                'ext': 'mp3',
                'title': 'The Pony Mash',
                'uploader': 'M_Pallante',
            },
            'skip': 'There is a limit of 200 free downloads / month for the test song',
        },
        # embedded brightcove video
        # it also tests brightcove videos that need to set the 'Referer' in the
        # http requests
        {
            'add_ie': ['Brightcove'],
            'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
            'info_dict': {
                'id': '2765128793001',
                'ext': 'mp4',
                'title': 'Le cours de bourse : l’analyse technique',
                'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
                'uploader': 'BFM BUSINESS',
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            # https://github.com/rg3/youtube-dl/issues/2253
            'url': 'http://bcove.me/i6nfkrc3',
            'md5': '0ba9446db037002366bab3b3eb30c88c',
            'info_dict': {
                'id': '3101154703001',
                'ext': 'mp4',
                'title': 'Still no power',
                'uploader': 'thestar.com',
                'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
            },
            'add_ie': ['Brightcove'],
        },
        {
            'url': 'http://www.championat.com/video/football/v/87/87499.html',
            'md5': 'fb973ecf6e4a78a67453647444222983',
            'info_dict': {
                'id': '3414141473001',
                'ext': 'mp4',
                'title': 'Видео. Удаление Дзагоева (ЦСКА)',
                'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
                'uploader': 'Championat',
            },
        },
        # Direct link to a video
        {
            'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
            'md5': '67d406c2bcb6af27fa886f31aa934bbe',
            'info_dict': {
                'id': 'trailer',
                'ext': 'mp4',
                'title': 'trailer',
                'upload_date': '20100513',
            }
        },
        # ooyala video
        {
            'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
            'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
            'info_dict': {
                'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
                'ext': 'mp4',
                'title': '2cc213299525360.mov',  # that's what we get
            },
        },
        # google redirect
        {
            'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
            'info_dict': {
                'id': 'cmQHVoWB5FY',
                'ext': 'mp4',
                'upload_date': '20130224',
                'uploader_id': 'TheVerge',
                'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
                'uploader': 'The Verge',
                'title': 'First Firefox OS phones side-by-side',
            },
            'params': {
                'skip_download': False,
            }
        },
        # embed.ly video
        {
            'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
            'info_dict': {
                'id': '9ODmcdjQcHQ',
                'ext': 'mp4',
                'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
                'upload_date': '20140225',
                'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
                'uploader': 'Tested',
                'uploader_id': 'testedcom',
            },
            # No need to test YoutubeIE here
            'params': {
                'skip_download': True,
            },
        },
        # funnyordie embed
        {
            'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
            'md5': '7cf780be104d40fea7bae52eed4a470e',
            'info_dict': {
                'id': '18e820ec3f',
                'ext': 'mp4',
                'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
                'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
            },
        },
        # RUTV embed
        {
            'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
            'info_dict': {
                'id': '776940',
                'ext': 'mp4',
                'title': 'Охотское море стало целиком российским',
                'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
            },
            'params': {
                # m3u8 download
                'skip_download': True,
            },
        },
        # Embedded TED video
        {
            'url': 'http://en.support.wordpress.com/videos/ted-talks/',
            'md5': 'deeeabcc1085eb2ba205474e7235a3d5',
            'info_dict': {
                'id': '981',
                'ext': 'mp4',
                'title': 'My web playroom',
                'uploader': 'Ze Frank',
                'description': 'md5:ddb2a40ecd6b6a147e400e535874947b',
            }
        },
        # Embeded Ustream video
        {
            'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
            'md5': '27b99cdb639c9b12a79bca876a073417',
            'info_dict': {
                'id': '45734260',
                'ext': 'flv',
                'uploader': 'AU SPA:  The NSA and Privacy',
                'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
            }
        },
        # nowvideo embed hidden behind percent encoding
        {
            'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
            'md5': '2baf4ddd70f697d94b1c18cf796d5107',
            'info_dict': {
                'id': '06e53103ca9aa',
                'ext': 'flv',
                'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
                'description': 'No description',
            },
        },
        # arte embed
        {
            'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
            'md5': '7653032cbb25bf6c80d80f217055fa43',
            'info_dict': {
                'id': '048195-004_PLUS7-F',
                'ext': 'flv',
                'title': 'X:enius',
                'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
                'upload_date': '20140320',
            },
            'params': {
                'skip_download': 'Requires rtmpdump'
            }
        },
        # smotri embed
        {
            'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml',
            'md5': 'ec40048448e9284c9a1de77bb188108b',
            'info_dict': {
                'id': 'v27008541fad',
                'ext': 'mp4',
                'title': 'Крым и Севастополь вошли в состав России',
                'description': 'md5:fae01b61f68984c7bd2fa741e11c3175',
                'duration': 900,
                'upload_date': '20140318',
                'uploader': 'rbctv_2012_4',
                'uploader_id': 'rbctv_2012_4',
            },
        },
        # Condé Nast embed
        {
            'url': 'http://www.wired.com/2014/04/honda-asimo/',
            'md5': 'ba0dfe966fa007657bd1443ee672db0f',
            'info_dict': {
                'id': '53501be369702d3275860000',
                'ext': 'mp4',
                'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
            }
        },
        # Dailymotion embed
        {
            'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
            'md5': '441aeeb82eb72c422c7f14ec533999cd',
            'info_dict': {
                'id': 'k2mm4bCdJ6CQ2i7c8o2',
                'ext': 'mp4',
                'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
                'uploader': 'Spi0n',
            },
            'add_ie': ['Dailymotion'],
        },
        # YouTube embed via <data-embed-url="">
        {
            'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
            'md5': 'c267b1ab6d736057d64babaa37e07a66',
            'info_dict': {
                'id': 'Ybd-qmqYYpA',
                'ext': 'mp4',
                'title': 'Asphalt 8: Airborne -  Chinese Great Wall - Android Game Trailer',
                'uploader': 'gameloftandroid',
                'uploader_id': 'gameloftandroid',
                'upload_date': '20140321',
                'description': 'md5:9c6dca5dd75b7131ce482ccf080749d6'
            }
        }
    ]

    def report_download_webpage(self, video_id):
        """Report webpage download."""
        if not self._downloader.params.get('test', False):
            self._downloader.report_warning('Falling back on generic information extractor.')
        super(GenericIE, self).report_download_webpage(video_id)

    def report_following_redirect(self, new_url):
        """Report information extraction."""
        self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)

    def _send_head(self, url):
        """Check if it is a redirect, like url shorteners, in case return the new url."""

        class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
            """
            Subclass the HTTPRedirectHandler to make it use our
            HEADRequest also on the redirected URL
            """
            def redirect_request(self, req, fp, code, msg, headers, newurl):
                if code in (301, 302, 303, 307):
                    newurl = newurl.replace(' ', '%20')
                    newheaders = dict((k,v) for k,v in req.headers.items()
                                      if k.lower() not in ("content-length", "content-type"))
                    try:
                        # This function was deprecated in python 3.3 and removed in 3.4
                        origin_req_host = req.get_origin_req_host()
                    except AttributeError:
                        origin_req_host = req.origin_req_host
                    return HEADRequest(newurl,
                                       headers=newheaders,
                                       origin_req_host=origin_req_host,
                                       unverifiable=True)
                else:
                    raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)

        class HTTPMethodFallback(compat_urllib_request.BaseHandler):
            """
            Fallback to GET if HEAD is not allowed (405 HTTP error)
            """
            def http_error_405(self, req, fp, code, msg, headers):
                fp.read()
                fp.close()

                newheaders = dict((k,v) for k,v in req.headers.items()
                                  if k.lower() not in ("content-length", "content-type"))
                return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
                                                 headers=newheaders,
                                                 origin_req_host=req.get_origin_req_host(),
                                                 unverifiable=True))

        # Build our opener
        opener = compat_urllib_request.OpenerDirector()
        for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
                        HTTPMethodFallback, HEADRedirectHandler,
                        compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
            opener.add_handler(handler())

        response = opener.open(HEADRequest(url))
        if response is None:
            raise ExtractorError('Invalid URL protocol')
        return response

    def _extract_rss(self, url, video_id, doc):
        playlist_title = doc.find('./channel/title').text
        playlist_desc_el = doc.find('./channel/description')
        playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text

        entries = [{
            '_type': 'url',
            'url': e.find('link').text,
            'title': e.find('title').text,
        } for e in doc.findall('./channel/item')]

        return {
            '_type': 'playlist',
            'id': url,
            'title': playlist_title,
            'description': playlist_desc,
            'entries': entries,
        }

    def _real_extract(self, url):
        if url.startswith('//'):
            return {
                '_type': 'url',
                'url': self.http_scheme() + url,
            }

        parsed_url = compat_urlparse.urlparse(url)
        if not parsed_url.scheme:
            default_search = self._downloader.params.get('default_search')
            if default_search is None:
                default_search = 'auto_warning'

            if default_search in ('auto', 'auto_warning'):
                if '/' in url:
                    self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
                    return self.url_result('http://' + url)
                else:
                    if default_search == 'auto_warning':
                        self._downloader.report_warning(
                            'Falling back to youtube search for  %s . Set --default-search to "auto" to suppress this warning.' % url)
                    return self.url_result('ytsearch:' + url)
            else:
                assert ':' in default_search
                return self.url_result(default_search + url)
        video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]

        self.to_screen('%s: Requesting header' % video_id)

        try:
            response = self._send_head(url)

            # Check for redirect
            new_url = response.geturl()
            if url != new_url:
                self.report_following_redirect(new_url)
                return self.url_result(new_url)

            # Check for direct link to a video
            content_type = response.headers.get('Content-Type', '')
            m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
            if m:
                upload_date = response.headers.get('Last-Modified')
                if upload_date:
                    upload_date = unified_strdate(upload_date)
                return {
                    'id': video_id,
                    'title': os.path.splitext(url_basename(url))[0],
                    'formats': [{
                        'format_id': m.group('format_id'),
                        'url': url,
                        'vcodec': 'none' if m.group('type') == 'audio' else None
                    }],
                    'upload_date': upload_date,
                }

        except compat_urllib_error.HTTPError:
            # This may be a stupid server that doesn't like HEAD, our UA, or so
            pass

        try:
            webpage = self._download_webpage(url, video_id)
        except ValueError:
            # since this is the last-resort InfoExtractor, if
            # this error is thrown, it'll be thrown here
            raise ExtractorError('Failed to download URL: %s' % url)

        self.report_extraction(video_id)

        # Is it an RSS feed?
        try:
            doc = parse_xml(webpage)
            if doc.tag == 'rss':
                return self._extract_rss(url, video_id, doc)
        except compat_xml_parse_error:
            pass

        # Sometimes embedded video player is hidden behind percent encoding
        # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
        # Unescaping the whole page allows to handle those cases in a generic way
        webpage = compat_urllib_parse.unquote(webpage)

        # it's tempting to parse this further, but you would
        # have to take into account all the variations like
        #   Video Title - Site Name
        #   Site Name | Video Title
        #   Video Title - Tagline | Site Name
        # and so on and so forth; it's just not practical
        video_title = self._html_search_regex(
            r'(?s)<title>(.*?)</title>', webpage, 'video title',
            default='video')

        # video uploader is domain name
        video_uploader = self._search_regex(
            r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')

        # Look for BrightCove:
        bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
        if bc_urls:
            self.to_screen('Brightcove video detected.')
            entries = [{
                '_type': 'url',
                'url': smuggle_url(bc_url, {'Referer': url}),
                'ie_key': 'Brightcove'
            } for bc_url in bc_urls]

            return {
                '_type': 'playlist',
                'title': video_title,
                'id': video_id,
                'entries': entries,
            }

        # Look for embedded (iframe) Vimeo player
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
        if mobj:
            player_url = unescapeHTML(mobj.group('url'))
            surl = smuggle_url(player_url, {'Referer': url})
            return self.url_result(surl, 'Vimeo')

        # Look for embedded (swf embed) Vimeo player
        mobj = re.search(
            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
        if mobj:
            return self.url_result(mobj.group(1), 'Vimeo')

        # Look for embedded YouTube player
        matches = re.findall(r'''(?x)
            (?:<iframe[^>]+?src=|data-video-url=|embedSWF\(\s*)
            (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
                (?:embed|v)/.+?)
            \1''', webpage)
        if matches:
            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
                     for tuppl in matches]
            return self.playlist_result(
                urlrs, playlist_id=video_id, playlist_title=video_title)

        # Look for embedded Dailymotion player
        matches = re.findall(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
        if matches:
            urlrs = [self.url_result(unescapeHTML(tuppl[1]))
                     for tuppl in matches]
            return self.playlist_result(
                urlrs, playlist_id=video_id, playlist_title=video_title)

        # Look for embedded Wistia player
        match = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
        if match:
            return {
                '_type': 'url_transparent',
                'url': unescapeHTML(match.group('url')),
                'ie_key': 'Wistia',
                'uploader': video_uploader,
                'title': video_title,
                'id': video_id,
            }

        # Look for embedded blip.tv player
        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
        if mobj:
            return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV')
        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage)
        if mobj:
            return self.url_result(mobj.group(1), 'BlipTV')

        # Look for embedded condenast player
        matches = re.findall(
            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
            webpage)
        if matches:
            return {
                '_type': 'playlist',
                'entries': [{
                    '_type': 'url',
                    'ie_key': 'CondeNast',
                    'url': ma,
                } for ma in matches],
                'title': video_title,
                'id': video_id,
            }

        # Look for Bandcamp pages with custom domain
        mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
        if mobj is not None:
            burl = unescapeHTML(mobj.group(1))
            # Don't set the extractor because it can be a track url or an album
            return self.url_result(burl)

        # Look for embedded Vevo player
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'))

        # Look for Ooyala videos
        mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
             re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
        if mobj is not None:
            return OoyalaIE._build_url_result(mobj.group('ec'))

        # Look for Aparat videos
        mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
        if mobj is not None:
            return self.url_result(mobj.group(1), 'Aparat')

        # Look for MPORA videos
        mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
        if mobj is not None:
            return self.url_result(mobj.group(1), 'Mpora')

        # Look for embedded NovaMov-based player
        mobj = re.search(
            r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
                    (?P<url>http://(?:(?:embed|www)\.)?
                        (?:novamov\.com|
                           nowvideo\.(?:ch|sx|eu|at|ag|co)|
                           videoweed\.(?:es|com)|
                           movshare\.(?:net|sx|ag)|
                           divxstage\.(?:eu|net|ch|co|at|ag))
                        /embed\.php.+?)\1''', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'))

        # Look for embedded Facebook player
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'), 'Facebook')

        # Look for embedded VK player
        mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'), 'VK')

        # Look for embedded Huffington Post player
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'), 'HuffPost')

        # Look for embed.ly
        mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'))
        mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
        if mobj is not None:
            return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))

        # Look for funnyordie embed
        matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
        if matches:
            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
                     for eurl in matches]
            return self.playlist_result(
                urlrs, playlist_id=video_id, playlist_title=video_title)

        # Look for embedded RUTV player
        rutv_url = RUTVIE._extract_url(webpage)
        if rutv_url:
            return self.url_result(rutv_url, 'RUTV')

        # Look for embedded TED player
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'), 'TED')

        # Look for embedded Ustream videos
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'), 'Ustream')

        # Look for embedded arte.tv player
        mobj = re.search(
            r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
            webpage)
        if mobj is not None:
            return self.url_result(mobj.group('url'), 'ArteTVEmbed')

        # Look for embedded smotri.com player
        smotri_url = SmotriIE._extract_url(webpage)
        if smotri_url:
            return self.url_result(smotri_url, 'Smotri')

        # Look for embeded soundcloud player
        mobj = re.search(
            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
            webpage)
        if mobj is not None:
            url = unescapeHTML(mobj.group('url'))
            return self.url_result(url)

        # Start with something easy: JW Player in SWFObject
        found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
        if not found:
            # Look for gorilla-vid style embedding
            found = re.findall(r'''(?sx)
                (?:
                    jw_plugins|
                    JWPlayerOptions|
                    jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
                )
                .*?file\s*:\s*["\'](.*?)["\']''', webpage)
        if not found:
            # Broaden the search a little bit
            found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
        if not found:
            # Broaden the findall a little bit: JWPlayer JS loader
            found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
        if not found:
            # Try to find twitter cards info
            found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
        if not found:
            # We look for Open Graph info:
            # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
            m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
            # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
            if m_video_type is not None:
                found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
        if not found:
            # HTML5 video
            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
        if not found:
            found = re.search(
                r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
                webpage)
            if found:
                new_url = found.group(1)
                self.report_following_redirect(new_url)
                return {
                    '_type': 'url',
                    'url': new_url,
                }
        if not found:
            raise ExtractorError('Unsupported URL: %s' % url)

        entries = []
        for video_url in found:
            video_url = compat_urlparse.urljoin(url, video_url)
            video_id = compat_urllib_parse.unquote(os.path.basename(video_url))

            # Sometimes, jwplayer extraction will result in a YouTube URL
            if YoutubeIE.suitable(video_url):
                entries.append(self.url_result(video_url, 'Youtube'))
                continue

            # here's a fun little line of code for you:
            video_id = os.path.splitext(video_id)[0]

            entries.append({
                'id': video_id,
                'url': video_url,
                'uploader': video_uploader,
                'title': video_title,
            })

        if len(entries) == 1:
            return entries[0]
        else:
            for num, e in enumerate(entries, start=1):
                e['title'] = '%s (%d)' % (e['title'], num)
            return {
                '_type': 'playlist',
                'entries': entries,
            }