aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/common.py
blob: 271bf85968690f00e25252294b51aa0e4cdecb15 (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
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
from __future__ import unicode_literals

import base64
import datetime
import hashlib
import json
import netrc
import os
import re
import socket
import sys
import time
import xml.etree.ElementTree

from ..compat import (
    compat_cookiejar,
    compat_HTTPError,
    compat_http_client,
    compat_urllib_error,
    compat_urllib_parse_urlparse,
    compat_urlparse,
    compat_str,
)
from ..utils import (
    NO_DEFAULT,
    age_restricted,
    bug_reports_message,
    clean_html,
    compiled_regex_type,
    determine_ext,
    ExtractorError,
    fix_xml_ampersands,
    float_or_none,
    int_or_none,
    RegexNotFoundError,
    sanitize_filename,
    unescapeHTML,
)


class InfoExtractor(object):
    """Information Extractor class.

    Information extractors are the classes that, given a URL, extract
    information about the video (or videos) the URL refers to. This
    information includes the real video URL, the video title, author and
    others. The information is stored in a dictionary which is then
    passed to the YoutubeDL. The YoutubeDL processes this
    information possibly downloading the video to the file system, among
    other possible outcomes.

    The type field determines the type of the result.
    By far the most common value (and the default if _type is missing) is
    "video", which indicates a single video.

    For a video, the dictionaries must include the following fields:

    id:             Video identifier.
    title:          Video title, unescaped.

    Additionally, it must contain either a formats entry or a url one:

    formats:        A list of dictionaries for each format available, ordered
                    from worst to best quality.

                    Potential fields:
                    * url        Mandatory. The URL of the video file
                    * ext        Will be calculated from url if missing
                    * format     A human-readable description of the format
                                 ("mp4 container with h264/opus").
                                 Calculated from the format_id, width, height.
                                 and format_note fields if missing.
                    * format_id  A short description of the format
                                 ("mp4_h264_opus" or "19").
                                Technically optional, but strongly recommended.
                    * format_note Additional info about the format
                                 ("3D" or "DASH video")
                    * width      Width of the video, if known
                    * height     Height of the video, if known
                    * resolution Textual description of width and height
                    * tbr        Average bitrate of audio and video in KBit/s
                    * abr        Average audio bitrate in KBit/s
                    * acodec     Name of the audio codec in use
                    * asr        Audio sampling rate in Hertz
                    * vbr        Average video bitrate in KBit/s
                    * fps        Frame rate
                    * vcodec     Name of the video codec in use
                    * container  Name of the container format
                    * filesize   The number of bytes, if known in advance
                    * filesize_approx  An estimate for the number of bytes
                    * player_url SWF Player URL (used for rtmpdump).
                    * protocol   The protocol that will be used for the actual
                                 download, lower-case.
                                 "http", "https", "rtsp", "rtmp", "rtmpe",
                                 "m3u8", or "m3u8_native".
                    * preference Order number of this format. If this field is
                                 present and not None, the formats get sorted
                                 by this field, regardless of all other values.
                                 -1 for default (order by other properties),
                                 -2 or smaller for less than default.
                                 < -1000 to hide the format (if there is
                                    another one which is strictly better)
                    * language_preference  Is this in the correct requested
                                 language?
                                 10 if it's what the URL is about,
                                 -1 for default (don't know),
                                 -10 otherwise, other values reserved for now.
                    * quality    Order number of the video quality of this
                                 format, irrespective of the file format.
                                 -1 for default (order by other properties),
                                 -2 or smaller for less than default.
                    * source_preference  Order number for this video source
                                  (quality takes higher priority)
                                 -1 for default (order by other properties),
                                 -2 or smaller for less than default.
                    * http_headers  A dictionary of additional HTTP headers
                                 to add to the request.
                    * stretched_ratio  If given and not 1, indicates that the
                                 video's pixels are not square.
                                 width : height ratio as float.
                    * no_resume  The server does not support resuming the
                                 (HTTP or RTMP) download. Boolean.

    url:            Final video URL.
    ext:            Video filename extension.
    format:         The video format, defaults to ext (used for --get-format)
    player_url:     SWF Player URL (used for rtmpdump).

    The following fields are optional:

    alt_title:      A secondary title of the video.
    display_id      An alternative identifier for the video, not necessarily
                    unique, but available before title. Typically, id is
                    something like "4234987", title "Dancing naked mole rats",
                    and display_id "dancing-naked-mole-rats"
    thumbnails:     A list of dictionaries, with the following entries:
                        * "id" (optional, string) - Thumbnail format ID
                        * "url"
                        * "preference" (optional, int) - quality of the image
                        * "width" (optional, int)
                        * "height" (optional, int)
                        * "resolution" (optional, string "{width}x{height"},
                                        deprecated)
    thumbnail:      Full URL to a video thumbnail image.
    description:    Full video description.
    uploader:       Full name of the video uploader.
    creator:        The main artist who created the video.
    timestamp:      UNIX timestamp of the moment the video became available.
    upload_date:    Video upload date (YYYYMMDD).
                    If not explicitly set, calculated from timestamp.
    uploader_id:    Nickname or id of the video uploader.
    location:       Physical location where the video was filmed.
    subtitles:      The available subtitles as a dictionary in the format
                    {language: subformats}. "subformats" is a list sorted from
                    lower to higher preference, each element is a dictionary
                    with the "ext" entry and one of:
                        * "data": The subtitles file contents
                        * "url": A url pointing to the subtitles file
    automatic_captions: Like 'subtitles', used by the YoutubeIE for
                    automatically generated captions
    duration:       Length of the video in seconds, as an integer.
    view_count:     How many users have watched the video on the platform.
    like_count:     Number of positive ratings of the video
    dislike_count:  Number of negative ratings of the video
    average_rating: Average rating give by users, the scale used depends on the webpage
    comment_count:  Number of comments on the video
    comments:       A list of comments, each with one or more of the following
                    properties (all but one of text or html optional):
                        * "author" - human-readable name of the comment author
                        * "author_id" - user ID of the comment author
                        * "id" - Comment ID
                        * "html" - Comment as HTML
                        * "text" - Plain text of the comment
                        * "timestamp" - UNIX timestamp of comment
                        * "parent" - ID of the comment this one is replying to.
                                     Set to "root" to indicate that this is a
                                     comment to the original video.
    age_limit:      Age restriction for the video, as an integer (years)
    webpage_url:    The url to the video webpage, if given to youtube-dl it
                    should allow to get the same result again. (It will be set
                    by YoutubeDL if it's missing)
    categories:     A list of categories that the video falls in, for example
                    ["Sports", "Berlin"]
    is_live:        True, False, or None (=unknown). Whether this video is a
                    live stream that goes on instead of a fixed-length video.

    Unless mentioned otherwise, the fields should be Unicode strings.

    Unless mentioned otherwise, None is equivalent to absence of information.


    _type "playlist" indicates multiple videos.
    There must be a key "entries", which is a list, an iterable, or a PagedList
    object, each element of which is a valid dictionary by this specification.

    Additionally, playlists can have "title" and "id" attributes with the same
    semantics as videos (see above).


    _type "multi_video" indicates that there are multiple videos that
    form a single show, for examples multiple acts of an opera or TV episode.
    It must have an entries key like a playlist and contain all the keys
    required for a video at the same time.


    _type "url" indicates that the video must be extracted from another
    location, possibly by a different extractor. Its only required key is:
    "url" - the next URL to extract.
    The key "ie_key" can be set to the class name (minus the trailing "IE",
    e.g. "Youtube") if the extractor class is known in advance.
    Additionally, the dictionary may have any properties of the resolved entity
    known in advance, for example "title" if the title of the referred video is
    known ahead of time.


    _type "url_transparent" entities have the same specification as "url", but
    indicate that the given additional information is more precise than the one
    associated with the resolved URL.
    This is useful when a site employs a video service that hosts the video and
    its technical metadata, but that video service does not embed a useful
    title, description etc.


    Subclasses of this one should re-define the _real_initialize() and
    _real_extract() methods and define a _VALID_URL regexp.
    Probably, they should also be added to the list of extractors.

    Finally, the _WORKING attribute should be set to False for broken IEs
    in order to warn the users and skip the tests.
    """

    _ready = False
    _downloader = None
    _WORKING = True

    def __init__(self, downloader=None):
        """Constructor. Receives an optional downloader."""
        self._ready = False
        self.set_downloader(downloader)

    @classmethod
    def suitable(cls, url):
        """Receives a URL and returns True if suitable for this IE."""

        # This does not use has/getattr intentionally - we want to know whether
        # we have cached the regexp for *this* class, whereas getattr would also
        # match the superclass
        if '_VALID_URL_RE' not in cls.__dict__:
            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
        return cls._VALID_URL_RE.match(url) is not None

    @classmethod
    def _match_id(cls, url):
        if '_VALID_URL_RE' not in cls.__dict__:
            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
        m = cls._VALID_URL_RE.match(url)
        assert m
        return m.group('id')

    @classmethod
    def working(cls):
        """Getter method for _WORKING."""
        return cls._WORKING

    def initialize(self):
        """Initializes an instance (authentication, etc)."""
        if not self._ready:
            self._real_initialize()
            self._ready = True

    def extract(self, url):
        """Extracts URL information and returns it in list of dicts."""
        try:
            self.initialize()
            return self._real_extract(url)
        except ExtractorError:
            raise
        except compat_http_client.IncompleteRead as e:
            raise ExtractorError('A network error has occured.', cause=e, expected=True)
        except (KeyError, StopIteration) as e:
            raise ExtractorError('An extractor error has occured.', cause=e)

    def set_downloader(self, downloader):
        """Sets the downloader for this IE."""
        self._downloader = downloader

    def _real_initialize(self):
        """Real initialization process. Redefine in subclasses."""
        pass

    def _real_extract(self, url):
        """Real extraction process. Redefine in subclasses."""
        pass

    @classmethod
    def ie_key(cls):
        """A string for getting the InfoExtractor with get_info_extractor"""
        return cls.__name__[:-2]

    @property
    def IE_NAME(self):
        return type(self).__name__[:-2]

    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
        """ Returns the response handle """
        if note is None:
            self.report_download_webpage(video_id)
        elif note is not False:
            if video_id is None:
                self.to_screen('%s' % (note,))
            else:
                self.to_screen('%s: %s' % (video_id, note))
        try:
            return self._downloader.urlopen(url_or_request)
        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
            if errnote is False:
                return False
            if errnote is None:
                errnote = 'Unable to download webpage'
            errmsg = '%s: %s' % (errnote, compat_str(err))
            if fatal:
                raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
            else:
                self._downloader.report_warning(errmsg)
                return False

    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
        """ Returns a tuple (page content as string, URL handle) """
        # Strip hashes from the URL (#1038)
        if isinstance(url_or_request, (compat_str, str)):
            url_or_request = url_or_request.partition('#')[0]

        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
        if urlh is False:
            assert not fatal
            return False
        content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding)
        return (content, urlh)

    @staticmethod
    def _guess_encoding_from_content(content_type, webpage_bytes):
        m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
        if m:
            encoding = m.group(1)
        else:
            m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
                          webpage_bytes[:1024])
            if m:
                encoding = m.group(1).decode('ascii')
            elif webpage_bytes.startswith(b'\xff\xfe'):
                encoding = 'utf-16'
            else:
                encoding = 'utf-8'

        return encoding

    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
        content_type = urlh.headers.get('Content-Type', '')
        webpage_bytes = urlh.read()
        if prefix is not None:
            webpage_bytes = prefix + webpage_bytes
        if not encoding:
            encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
        if self._downloader.params.get('dump_intermediate_pages', False):
            try:
                url = url_or_request.get_full_url()
            except AttributeError:
                url = url_or_request
            self.to_screen('Dumping request to ' + url)
            dump = base64.b64encode(webpage_bytes).decode('ascii')
            self._downloader.to_screen(dump)
        if self._downloader.params.get('write_pages', False):
            try:
                url = url_or_request.get_full_url()
            except AttributeError:
                url = url_or_request
            basen = '%s_%s' % (video_id, url)
            if len(basen) > 240:
                h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
                basen = basen[:240 - len(h)] + h
            raw_filename = basen + '.dump'
            filename = sanitize_filename(raw_filename, restricted=True)
            self.to_screen('Saving request to ' + filename)
            # Working around MAX_PATH limitation on Windows (see
            # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
            if os.name == 'nt':
                absfilepath = os.path.abspath(filename)
                if len(absfilepath) > 259:
                    filename = '\\\\?\\' + absfilepath
            with open(filename, 'wb') as outf:
                outf.write(webpage_bytes)

        try:
            content = webpage_bytes.decode(encoding, 'replace')
        except LookupError:
            content = webpage_bytes.decode('utf-8', 'replace')

        if ('<title>Access to this site is blocked</title>' in content and
                'Websense' in content[:512]):
            msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
            blocked_iframe = self._html_search_regex(
                r'<iframe src="([^"]+)"', content,
                'Websense information URL', default=None)
            if blocked_iframe:
                msg += ' Visit %s for more details' % blocked_iframe
            raise ExtractorError(msg, expected=True)
        if '<title>The URL you requested has been blocked</title>' in content[:512]:
            msg = (
                'Access to this webpage has been blocked by Indian censorship. '
                'Use a VPN or proxy server (with --proxy) to route around it.')
            block_msg = self._html_search_regex(
                r'</h1><p>(.*?)</p>',
                content, 'block message', default=None)
            if block_msg:
                msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
            raise ExtractorError(msg, expected=True)

        return content

    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
        """ Returns the data of the page as a string """
        success = False
        try_count = 0
        while success is False:
            try:
                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
                success = True
            except compat_http_client.IncompleteRead as e:
                try_count += 1
                if try_count >= tries:
                    raise e
                self._sleep(timeout, video_id)
        if res is False:
            return res
        else:
            content, _ = res
            return content

    def _download_xml(self, url_or_request, video_id,
                      note='Downloading XML', errnote='Unable to download XML',
                      transform_source=None, fatal=True, encoding=None):
        """Return the xml as an xml.etree.ElementTree.Element"""
        xml_string = self._download_webpage(
            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
        if xml_string is False:
            return xml_string
        if transform_source:
            xml_string = transform_source(xml_string)
        return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))

    def _download_json(self, url_or_request, video_id,
                       note='Downloading JSON metadata',
                       errnote='Unable to download JSON metadata',
                       transform_source=None,
                       fatal=True, encoding=None):
        json_string = self._download_webpage(
            url_or_request, video_id, note, errnote, fatal=fatal,
            encoding=encoding)
        if (not fatal) and json_string is False:
            return None
        return self._parse_json(
            json_string, video_id, transform_source=transform_source, fatal=fatal)

    def _parse_json(self, json_string, video_id, transform_source=None, fatal=True):
        if transform_source:
            json_string = transform_source(json_string)
        try:
            return json.loads(json_string)
        except ValueError as ve:
            errmsg = '%s: Failed to parse JSON ' % video_id
            if fatal:
                raise ExtractorError(errmsg, cause=ve)
            else:
                self.report_warning(errmsg + str(ve))

    def report_warning(self, msg, video_id=None):
        idstr = '' if video_id is None else '%s: ' % video_id
        self._downloader.report_warning(
            '[%s] %s%s' % (self.IE_NAME, idstr, msg))

    def to_screen(self, msg):
        """Print msg to screen, prefixing it with '[ie_name]'"""
        self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg))

    def report_extraction(self, id_or_name):
        """Report information extraction."""
        self.to_screen('%s: Extracting information' % id_or_name)

    def report_download_webpage(self, video_id):
        """Report webpage download."""
        self.to_screen('%s: Downloading webpage' % video_id)

    def report_age_confirmation(self):
        """Report attempt to confirm age."""
        self.to_screen('Confirming age')

    def report_login(self):
        """Report attempt to log in."""
        self.to_screen('Logging in')

    # Methods for following #608
    @staticmethod
    def url_result(url, ie=None, video_id=None, video_title=None):
        """Returns a url that points to a page that should be processed"""
        # TODO: ie should be the class used for getting the info
        video_info = {'_type': 'url',
                      'url': url,
                      'ie_key': ie}
        if video_id is not None:
            video_info['id'] = video_id
        if video_title is not None:
            video_info['title'] = video_title
        return video_info

    @staticmethod
    def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
        """Returns a playlist"""
        video_info = {'_type': 'playlist',
                      'entries': entries}
        if playlist_id:
            video_info['id'] = playlist_id
        if playlist_title:
            video_info['title'] = playlist_title
        if playlist_description:
            video_info['description'] = playlist_description
        return video_info

    def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
        """
        Perform a regex search on the given string, using a single or a list of
        patterns returning the first matching group.
        In case of failure return a default value or raise a WARNING or a
        RegexNotFoundError, depending on fatal, specifying the field name.
        """
        if isinstance(pattern, (str, compat_str, compiled_regex_type)):
            mobj = re.search(pattern, string, flags)
        else:
            for p in pattern:
                mobj = re.search(p, string, flags)
                if mobj:
                    break

        if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty():
            _name = '\033[0;34m%s\033[0m' % name
        else:
            _name = name

        if mobj:
            if group is None:
                # return the first matching group
                return next(g for g in mobj.groups() if g is not None)
            else:
                return mobj.group(group)
        elif default is not NO_DEFAULT:
            return default
        elif fatal:
            raise RegexNotFoundError('Unable to extract %s' % _name)
        else:
            self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
            return None

    def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
        """
        Like _search_regex, but strips HTML tags and unescapes entities.
        """
        res = self._search_regex(pattern, string, name, default, fatal, flags, group)
        if res:
            return clean_html(res).strip()
        else:
            return res

    def _get_login_info(self):
        """
        Get the login info as (username, password)
        It will look in the netrc file using the _NETRC_MACHINE value
        If there's no info available, return (None, None)
        """
        if self._downloader is None:
            return (None, None)

        username = None
        password = None
        downloader_params = self._downloader.params

        # Attempt to use provided username and password or .netrc data
        if downloader_params.get('username', None) is not None:
            username = downloader_params['username']
            password = downloader_params['password']
        elif downloader_params.get('usenetrc', False):
            try:
                info = netrc.netrc().authenticators(self._NETRC_MACHINE)
                if info is not None:
                    username = info[0]
                    password = info[2]
                else:
                    raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
            except (IOError, netrc.NetrcParseError) as err:
                self._downloader.report_warning('parsing .netrc: %s' % compat_str(err))

        return (username, password)

    def _get_tfa_info(self):
        """
        Get the two-factor authentication info
        TODO - asking the user will be required for sms/phone verify
        currently just uses the command line option
        If there's no info available, return None
        """
        if self._downloader is None:
            return None
        downloader_params = self._downloader.params

        if downloader_params.get('twofactor', None) is not None:
            return downloader_params['twofactor']

        return None

    # Helper functions for extracting OpenGraph info
    @staticmethod
    def _og_regexes(prop):
        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
        property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
        template = r'<meta[^>]+?%s[^>]+?%s'
        return [
            template % (property_re, content_re),
            template % (content_re, property_re),
        ]

    def _og_search_property(self, prop, html, name=None, **kargs):
        if name is None:
            name = 'OpenGraph %s' % prop
        escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
        if escaped is None:
            return None
        return unescapeHTML(escaped)

    def _og_search_thumbnail(self, html, **kargs):
        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)

    def _og_search_description(self, html, **kargs):
        return self._og_search_property('description', html, fatal=False, **kargs)

    def _og_search_title(self, html, **kargs):
        return self._og_search_property('title', html, **kargs)

    def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
        regexes = self._og_regexes('video') + self._og_regexes('video:url')
        if secure:
            regexes = self._og_regexes('video:secure_url') + regexes
        return self._html_search_regex(regexes, html, name, **kargs)

    def _og_search_url(self, html, **kargs):
        return self._og_search_property('url', html, **kargs)

    def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
        if display_name is None:
            display_name = name
        return self._html_search_regex(
            r'''(?isx)<meta
                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
            html, display_name, fatal=fatal, group='content', **kwargs)

    def _dc_search_uploader(self, html):
        return self._html_search_meta('dc.creator', html, 'uploader')

    def _rta_search(self, html):
        # See http://www.rtalabel.org/index.php?content=howtofaq#single
        if re.search(r'(?ix)<meta\s+name="rating"\s+'
                     r'     content="RTA-5042-1996-1400-1577-RTA"',
                     html):
            return 18
        return 0

    def _media_rating_search(self, html):
        # See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/
        rating = self._html_search_meta('rating', html)

        if not rating:
            return None

        RATING_TABLE = {
            'safe for kids': 0,
            'general': 8,
            '14 years': 14,
            'mature': 17,
            'restricted': 19,
        }
        return RATING_TABLE.get(rating.lower(), None)

    def _family_friendly_search(self, html):
        # See http://schema.org/VideoObject
        family_friendly = self._html_search_meta('isFamilyFriendly', html)

        if not family_friendly:
            return None

        RATING_TABLE = {
            '1': 0,
            'true': 0,
            '0': 18,
            'false': 18,
        }
        return RATING_TABLE.get(family_friendly.lower(), None)

    def _twitter_search_player(self, html):
        return self._html_search_meta('twitter:player', html,
                                      'twitter card player')

    @staticmethod
    def _hidden_inputs(html):
        return dict([
            (input.group('name'), input.group('value')) for input in re.finditer(
                r'''(?x)
                    <input\s+
                        type=(?P<q_hidden>["\'])hidden(?P=q_hidden)\s+
                        name=(?P<q_name>["\'])(?P<name>.+?)(?P=q_name)\s+
                        (?:id=(?P<q_id>["\']).+?(?P=q_id)\s+)?
                        value=(?P<q_value>["\'])(?P<value>.*?)(?P=q_value)
                ''', html)
        ])

    def _form_hidden_inputs(self, form_id, html):
        form = self._search_regex(
            r'(?s)<form[^>]+?id=(["\'])%s\1[^>]*>(?P<form>.+?)</form>' % form_id,
            html, '%s form' % form_id, group='form')
        return self._hidden_inputs(form)

    def _sort_formats(self, formats, field_preference=None):
        if not formats:
            raise ExtractorError('No video formats found')

        def _formats_key(f):
            # TODO remove the following workaround
            from ..utils import determine_ext
            if not f.get('ext') and 'url' in f:
                f['ext'] = determine_ext(f['url'])

            if isinstance(field_preference, (list, tuple)):
                return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference)

            preference = f.get('preference')
            if preference is None:
                proto = f.get('protocol')
                if proto is None:
                    proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme

                preference = 0 if proto in ['http', 'https'] else -0.1
                if f.get('ext') in ['f4f', 'f4m']:  # Not yet supported
                    preference -= 0.5

            if f.get('vcodec') == 'none':  # audio only
                if self._downloader.params.get('prefer_free_formats'):
                    ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                else:
                    ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a']
                ext_preference = 0
                try:
                    audio_ext_preference = ORDER.index(f['ext'])
                except ValueError:
                    audio_ext_preference = -1
            else:
                if self._downloader.params.get('prefer_free_formats'):
                    ORDER = ['flv', 'mp4', 'webm']
                else:
                    ORDER = ['webm', 'flv', 'mp4']
                try:
                    ext_preference = ORDER.index(f['ext'])
                except ValueError:
                    ext_preference = -1
                audio_ext_preference = 0

            return (
                preference,
                f.get('language_preference') if f.get('language_preference') is not None else -1,
                f.get('quality') if f.get('quality') is not None else -1,
                f.get('tbr') if f.get('tbr') is not None else -1,
                f.get('filesize') if f.get('filesize') is not None else -1,
                f.get('vbr') if f.get('vbr') is not None else -1,
                f.get('height') if f.get('height') is not None else -1,
                f.get('width') if f.get('width') is not None else -1,
                ext_preference,
                f.get('abr') if f.get('abr') is not None else -1,
                audio_ext_preference,
                f.get('fps') if f.get('fps') is not None else -1,
                f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
                f.get('source_preference') if f.get('source_preference') is not None else -1,
                f.get('format_id') if f.get('format_id') is not None else '',
            )
        formats.sort(key=_formats_key)

    def _check_formats(self, formats, video_id):
        if formats:
            formats[:] = filter(
                lambda f: self._is_valid_url(
                    f['url'], video_id,
                    item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
                formats)

    def _is_valid_url(self, url, video_id, item='video'):
        url = self._proto_relative_url(url, scheme='http:')
        # For now assume non HTTP(S) URLs always valid
        if not (url.startswith('http://') or url.startswith('https://')):
            return True
        try:
            self._request_webpage(url, video_id, 'Checking %s URL' % item)
            return True
        except ExtractorError as e:
            if isinstance(e.cause, compat_HTTPError):
                self.to_screen(
                    '%s: %s URL is invalid, skipping' % (video_id, item))
                return False
            raise

    def http_scheme(self):
        """ Either "http:" or "https:", depending on the user's preferences """
        return (
            'http:'
            if self._downloader.params.get('prefer_insecure', False)
            else 'https:')

    def _proto_relative_url(self, url, scheme=None):
        if url is None:
            return url
        if url.startswith('//'):
            if scheme is None:
                scheme = self.http_scheme()
            return scheme + url
        else:
            return url

    def _sleep(self, timeout, video_id, msg_template=None):
        if msg_template is None:
            msg_template = '%(video_id)s: Waiting for %(timeout)s seconds'
        msg = msg_template % {'video_id': video_id, 'timeout': timeout}
        self.to_screen(msg)
        time.sleep(timeout)

    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
        manifest = self._download_xml(
            manifest_url, video_id, 'Downloading f4m manifest',
            'Unable to download f4m manifest',
            # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
            # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244)
            transform_source=lambda s: fix_xml_ampersands(s).strip())

        formats = []
        manifest_version = '1.0'
        media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
        if not media_nodes:
            manifest_version = '2.0'
            media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
        for i, media_el in enumerate(media_nodes):
            if manifest_version == '2.0':
                media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
                if not media_url:
                    continue
                manifest_url = (
                    media_url if media_url.startswith('http://') or media_url.startswith('https://')
                    else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
                # If media_url is itself a f4m manifest do the recursive extraction
                # since bitrates in parent manifest (this one) and media_url manifest
                # may differ leading to inability to resolve the format by requested
                # bitrate in f4m downloader
                if determine_ext(manifest_url) == 'f4m':
                    formats.extend(self._extract_f4m_formats(manifest_url, video_id, preference, f4m_id))
                    continue
            tbr = int_or_none(media_el.attrib.get('bitrate'))
            formats.append({
                'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
                'url': manifest_url,
                'ext': 'flv',
                'tbr': tbr,
                'width': int_or_none(media_el.attrib.get('width')),
                'height': int_or_none(media_el.attrib.get('height')),
                'preference': preference,
            })
        self._sort_formats(formats)

        return formats

    def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                              entry_protocol='m3u8', preference=None,
                              m3u8_id=None, note=None, errnote=None,
                              fatal=True):

        formats = [{
            'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
            'url': m3u8_url,
            'ext': ext,
            'protocol': 'm3u8',
            'preference': preference - 1 if preference else -1,
            'resolution': 'multiple',
            'format_note': 'Quality selection URL',
        }]

        format_url = lambda u: (
            u
            if re.match(r'^https?://', u)
            else compat_urlparse.urljoin(m3u8_url, u))

        m3u8_doc = self._download_webpage(
            m3u8_url, video_id,
            note=note or 'Downloading m3u8 information',
            errnote=errnote or 'Failed to download m3u8 information',
            fatal=fatal)
        if m3u8_doc is False:
            return m3u8_doc
        last_info = None
        last_media = None
        kv_rex = re.compile(
            r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
        for line in m3u8_doc.splitlines():
            if line.startswith('#EXT-X-STREAM-INF:'):
                last_info = {}
                for m in kv_rex.finditer(line):
                    v = m.group('val')
                    if v.startswith('"'):
                        v = v[1:-1]
                    last_info[m.group('key')] = v
            elif line.startswith('#EXT-X-MEDIA:'):
                last_media = {}
                for m in kv_rex.finditer(line):
                    v = m.group('val')
                    if v.startswith('"'):
                        v = v[1:-1]
                    last_media[m.group('key')] = v
            elif line.startswith('#') or not line.strip():
                continue
            else:
                if last_info is None:
                    formats.append({'url': format_url(line)})
                    continue
                tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
                format_id = []
                if m3u8_id:
                    format_id.append(m3u8_id)
                last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None
                format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
                f = {
                    'format_id': '-'.join(format_id),
                    'url': format_url(line.strip()),
                    'tbr': tbr,
                    'ext': ext,
                    'protocol': entry_protocol,
                    'preference': preference,
                }
                codecs = last_info.get('CODECS')
                if codecs:
                    # TODO: looks like video codec is not always necessarily goes first
                    va_codecs = codecs.split(',')
                    if va_codecs[0]:
                        f['vcodec'] = va_codecs[0].partition('.')[0]
                    if len(va_codecs) > 1 and va_codecs[1]:
                        f['acodec'] = va_codecs[1].partition('.')[0]
                resolution = last_info.get('RESOLUTION')
                if resolution:
                    width_str, height_str = resolution.split('x')
                    f['width'] = int(width_str)
                    f['height'] = int(height_str)
                if last_media is not None:
                    f['m3u8_media'] = last_media
                    last_media = None
                formats.append(f)
                last_info = {}
        self._sort_formats(formats)
        return formats

    # TODO: improve extraction
    def _extract_smil_formats(self, smil_url, video_id, fatal=True):
        smil = self._download_xml(
            smil_url, video_id, 'Downloading SMIL file',
            'Unable to download SMIL file', fatal=fatal)
        if smil is False:
            assert not fatal
            return []

        base = smil.find('./head/meta').get('base')

        formats = []
        rtmp_count = 0
        if smil.findall('./body/seq/video'):
            video = smil.findall('./body/seq/video')[0]
            fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
            formats.extend(fmts)
        else:
            for video in smil.findall('./body/switch/video'):
                fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
                formats.extend(fmts)

        self._sort_formats(formats)

        return formats

    def _parse_smil_video(self, video, video_id, base, rtmp_count):
        src = video.get('src')
        if not src:
            return ([], rtmp_count)
        bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
        width = int_or_none(video.get('width'))
        height = int_or_none(video.get('height'))
        proto = video.get('proto')
        if not proto:
            if base:
                if base.startswith('rtmp'):
                    proto = 'rtmp'
                elif base.startswith('http'):
                    proto = 'http'
        ext = video.get('ext')
        if proto == 'm3u8':
            return (self._extract_m3u8_formats(src, video_id, ext), rtmp_count)
        elif proto == 'rtmp':
            rtmp_count += 1
            streamer = video.get('streamer') or base
            return ([{
                'url': streamer,
                'play_path': src,
                'ext': 'flv',
                'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
                'tbr': bitrate,
                'width': width,
                'height': height,
            }], rtmp_count)
        elif proto.startswith('http'):
            return ([{
                'url': base + src,
                'ext': ext or 'flv',
                'tbr': bitrate,
                'width': width,
                'height': height,
            }], rtmp_count)

    def _live_title(self, name):
        """ Generate the title for a live video """
        now = datetime.datetime.now()
        now_str = now.strftime("%Y-%m-%d %H:%M")
        return name + ' ' + now_str

    def _int(self, v, name, fatal=False, **kwargs):
        res = int_or_none(v, **kwargs)
        if 'get_attr' in kwargs:
            print(getattr(v, kwargs['get_attr']))
        if res is None:
            msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
            if fatal:
                raise ExtractorError(msg)
            else:
                self._downloader.report_warning(msg)
        return res

    def _float(self, v, name, fatal=False, **kwargs):
        res = float_or_none(v, **kwargs)
        if res is None:
            msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
            if fatal:
                raise ExtractorError(msg)
            else:
                self._downloader.report_warning(msg)
        return res

    def _set_cookie(self, domain, name, value, expire_time=None):
        cookie = compat_cookiejar.Cookie(
            0, name, value, None, None, domain, None,
            None, '/', True, False, expire_time, '', None, None, None)
        self._downloader.cookiejar.set_cookie(cookie)

    def get_testcases(self, include_onlymatching=False):
        t = getattr(self, '_TEST', None)
        if t:
            assert not hasattr(self, '_TESTS'), \
                '%s has _TEST and _TESTS' % type(self).__name__
            tests = [t]
        else:
            tests = getattr(self, '_TESTS', [])
        for t in tests:
            if not include_onlymatching and t.get('only_matching', False):
                continue
            t['name'] = type(self).__name__[:-len('IE')]
            yield t

    def is_suitable(self, age_limit):
        """ Test whether the extractor is generally suitable for the given
        age limit (i.e. pornographic sites are not, all others usually are) """

        any_restricted = False
        for tc in self.get_testcases(include_onlymatching=False):
            if 'playlist' in tc:
                tc = tc['playlist'][0]
            is_restricted = age_restricted(
                tc.get('info_dict', {}).get('age_limit'), age_limit)
            if not is_restricted:
                return True
            any_restricted = any_restricted or is_restricted
        return not any_restricted

    def extract_subtitles(self, *args, **kwargs):
        if (self._downloader.params.get('writesubtitles', False) or
                self._downloader.params.get('listsubtitles')):
            return self._get_subtitles(*args, **kwargs)
        return {}

    def _get_subtitles(self, *args, **kwargs):
        raise NotImplementedError("This method must be implemented by subclasses")

    def extract_automatic_captions(self, *args, **kwargs):
        if (self._downloader.params.get('writeautomaticsub', False) or
                self._downloader.params.get('listsubtitles')):
            return self._get_automatic_captions(*args, **kwargs)
        return {}

    def _get_automatic_captions(self, *args, **kwargs):
        raise NotImplementedError("This method must be implemented by subclasses")


class SearchInfoExtractor(InfoExtractor):
    """
    Base class for paged search queries extractors.
    They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
    Instances should define _SEARCH_KEY and _MAX_RESULTS.
    """

    @classmethod
    def _make_valid_url(cls):
        return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY

    @classmethod
    def suitable(cls, url):
        return re.match(cls._make_valid_url(), url) is not None

    def _real_extract(self, query):
        mobj = re.match(self._make_valid_url(), query)
        if mobj is None:
            raise ExtractorError('Invalid search query "%s"' % query)

        prefix = mobj.group('prefix')
        query = mobj.group('query')
        if prefix == '':
            return self._get_n_results(query, 1)
        elif prefix == 'all':
            return self._get_n_results(query, self._MAX_RESULTS)
        else:
            n = int(prefix)
            if n <= 0:
                raise ExtractorError('invalid download number %s for query "%s"' % (n, query))
            elif n > self._MAX_RESULTS:
                self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
                n = self._MAX_RESULTS
            return self._get_n_results(query, n)

    def _get_n_results(self, query, n):
        """Get a specified number of results for a query"""
        raise NotImplementedError("This method must be implemented by subclasses")

    @property
    def SEARCH_KEY(self):
        return self._SEARCH_KEY