aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/PostProcessor.py
blob: da95f1a87dbe63fc648e061aa5671bb3dba1d740 (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
import os
import subprocess
import sys
import time


from .utils import (
    compat_subprocess_get_DEVNULL,
    encodeFilename,
    PostProcessingError,
    shell_quote,
    subtitles_filename,
)


class PostProcessor(object):
    """Post Processor class.

    PostProcessor objects can be added to downloaders with their
    add_post_processor() method. When the downloader has finished a
    successful download, it will take its internal chain of PostProcessors
    and start calling the run() method on each one of them, first with
    an initial argument and then with the returned value of the previous
    PostProcessor.

    The chain will be stopped if one of them ever returns None or the end
    of the chain is reached.

    PostProcessor objects follow a "mutual registration" process similar
    to InfoExtractor objects.
    """

    _downloader = None

    def __init__(self, downloader=None):
        self._downloader = downloader

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

    def run(self, information):
        """Run the PostProcessor.

        The "information" argument is a dictionary like the ones
        composed by InfoExtractors. The only difference is that this
        one has an extra field called "filepath" that points to the
        downloaded file.

        This method returns a tuple, the first element of which describes
        whether the original file should be kept (i.e. not deleted - None for
        no preference), and the second of which is the updated information.

        In addition, this method may raise a PostProcessingError
        exception if post processing fails.
        """
        return None, information # by default, keep file and do nothing

class FFmpegPostProcessorError(PostProcessingError):
    pass

class AudioConversionError(PostProcessingError):
    pass


class FFmpegPostProcessor(PostProcessor):
    def __init__(self,downloader=None):
        PostProcessor.__init__(self, downloader)
        self._exes = self.detect_executables()

    @staticmethod
    def detect_executables():
        def executable(exe):
            try:
                subprocess.Popen([exe, '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
            except OSError:
                return False
            return exe
        programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
        return dict((program, executable(program)) for program in programs)

    def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
        if not self._exes['ffmpeg'] and not self._exes['avconv']:
            raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')

        files_cmd = []
        for path in input_paths:
            files_cmd.extend(['-i', encodeFilename(path)])
        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
               + opts +
               [encodeFilename(self._ffmpeg_filename_argument(out_path))])

        if self._downloader.params.get('verbose', False):
            self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd))
        p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
        stdout,stderr = p.communicate()
        if p.returncode != 0:
            stderr = stderr.decode('utf-8', 'replace')
            msg = stderr.strip().split('\n')[-1]
            raise FFmpegPostProcessorError(msg)

    def run_ffmpeg(self, path, out_path, opts):
        self.run_ffmpeg_multiple_files([path], out_path, opts)

    def _ffmpeg_filename_argument(self, fn):
        # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
        if fn.startswith(u'-'):
            return u'./' + fn
        return fn


class FFmpegExtractAudioPP(FFmpegPostProcessor):
    def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, nopostoverwrites=False):
        FFmpegPostProcessor.__init__(self, downloader)
        if preferredcodec is None:
            preferredcodec = 'best'
        self._preferredcodec = preferredcodec
        self._preferredquality = preferredquality
        self._nopostoverwrites = nopostoverwrites

    def get_audio_codec(self, path):
        if not self._exes['ffprobe'] and not self._exes['avprobe']:
            raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')
        try:
            cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
            handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
            output = handle.communicate()[0]
            if handle.wait() != 0:
                return None
        except (IOError, OSError):
            return None
        audio_codec = None
        for line in output.decode('ascii', 'ignore').split('\n'):
            if line.startswith('codec_name='):
                audio_codec = line.split('=')[1].strip()
            elif line.strip() == 'codec_type=audio' and audio_codec is not None:
                return audio_codec
        return None

    def run_ffmpeg(self, path, out_path, codec, more_opts):
        if not self._exes['ffmpeg'] and not self._exes['avconv']:
            raise AudioConversionError('ffmpeg or avconv not found. Please install one.')
        if codec is None:
            acodec_opts = []
        else:
            acodec_opts = ['-acodec', codec]
        opts = ['-vn'] + acodec_opts + more_opts
        try:
            FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
        except FFmpegPostProcessorError as err:
            raise AudioConversionError(err.msg)

    def run(self, information):
        path = information['filepath']

        filecodec = self.get_audio_codec(path)
        if filecodec is None:
            raise PostProcessingError(u'WARNING: unable to obtain file audio codec with ffprobe')

        more_opts = []
        if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
            if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
                # Lossless, but in another container
                acodec = 'copy'
                extension = 'm4a'
                more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
            elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
                # Lossless if possible
                acodec = 'copy'
                extension = filecodec
                if filecodec == 'aac':
                    more_opts = ['-f', 'adts']
                if filecodec == 'vorbis':
                    extension = 'ogg'
            else:
                # MP3 otherwise.
                acodec = 'libmp3lame'
                extension = 'mp3'
                more_opts = []
                if self._preferredquality is not None:
                    if int(self._preferredquality) < 10:
                        more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
                    else:
                        more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
        else:
            # We convert the audio (lossy)
            acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
            extension = self._preferredcodec
            more_opts = []
            if self._preferredquality is not None:
                # The opus codec doesn't support the -aq option
                if int(self._preferredquality) < 10 and extension != 'opus':
                    more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
                else:
                    more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
            if self._preferredcodec == 'aac':
                more_opts += ['-f', 'adts']
            if self._preferredcodec == 'm4a':
                more_opts += [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
            if self._preferredcodec == 'vorbis':
                extension = 'ogg'
            if self._preferredcodec == 'wav':
                extension = 'wav'
                more_opts += ['-f', 'wav']

        prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
        new_path = prefix + sep + extension

        # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
        if new_path == path:
            self._nopostoverwrites = True

        try:
            if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
                self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
            else:
                self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
                self.run_ffmpeg(path, new_path, acodec, more_opts)
        except:
            etype,e,tb = sys.exc_info()
            if isinstance(e, AudioConversionError):
                msg = u'audio conversion failed: ' + e.msg
            else:
                msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
            raise PostProcessingError(msg)

        # Try to update the date time for extracted audio file.
        if information.get('filetime') is not None:
            try:
                os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
            except:
                self._downloader.report_warning(u'Cannot update utime of audio file')

        information['filepath'] = new_path
        return self._nopostoverwrites,information


class FFmpegVideoConvertor(FFmpegPostProcessor):
    def __init__(self, downloader=None,preferedformat=None):
        super(FFmpegVideoConvertor, self).__init__(downloader)
        self._preferedformat=preferedformat

    def run(self, information):
        path = information['filepath']
        prefix, sep, ext = path.rpartition(u'.')
        outpath = prefix + sep + self._preferedformat
        if information['ext'] == self._preferedformat:
            self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
            return True,information
        self._downloader.to_screen(u'['+'ffmpeg'+'] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) +outpath)
        self.run_ffmpeg(path, outpath, [])
        information['filepath'] = outpath
        information['format'] = self._preferedformat
        information['ext'] = self._preferedformat
        return False,information


class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
    _lang_map = {
        'aa': 'aar',
        'ab': 'abk',
        'ae': 'ave',
        'af': 'afr',
        'ak': 'aka',
        'am': 'amh',
        'an': 'arg',
        'ar': 'ara',
        'as': 'asm',
        'av': 'ava',
        'ay': 'aym',
        'az': 'aze',
        'ba': 'bak',
        'be': 'bel',
        'bg': 'bul',
        'bh': 'bih',
        'bi': 'bis',
        'bm': 'bam',
        'bn': 'ben',
        'bo': 'bod',
        'br': 'bre',
        'bs': 'bos',
        'ca': 'cat',
        'ce': 'che',
        'ch': 'cha',
        'co': 'cos',
        'cr': 'cre',
        'cs': 'ces',
        'cu': 'chu',
        'cv': 'chv',
        'cy': 'cym',
        'da': 'dan',
        'de': 'deu',
        'dv': 'div',
        'dz': 'dzo',
        'ee': 'ewe',
        'el': 'ell',
        'en': 'eng',
        'eo': 'epo',
        'es': 'spa',
        'et': 'est',
        'eu': 'eus',
        'fa': 'fas',
        'ff': 'ful',
        'fi': 'fin',
        'fj': 'fij',
        'fo': 'fao',
        'fr': 'fra',
        'fy': 'fry',
        'ga': 'gle',
        'gd': 'gla',
        'gl': 'glg',
        'gn': 'grn',
        'gu': 'guj',
        'gv': 'glv',
        'ha': 'hau',
        'he': 'heb',
        'hi': 'hin',
        'ho': 'hmo',
        'hr': 'hrv',
        'ht': 'hat',
        'hu': 'hun',
        'hy': 'hye',
        'hz': 'her',
        'ia': 'ina',
        'id': 'ind',
        'ie': 'ile',
        'ig': 'ibo',
        'ii': 'iii',
        'ik': 'ipk',
        'io': 'ido',
        'is': 'isl',
        'it': 'ita',
        'iu': 'iku',
        'ja': 'jpn',
        'jv': 'jav',
        'ka': 'kat',
        'kg': 'kon',
        'ki': 'kik',
        'kj': 'kua',
        'kk': 'kaz',
        'kl': 'kal',
        'km': 'khm',
        'kn': 'kan',
        'ko': 'kor',
        'kr': 'kau',
        'ks': 'kas',
        'ku': 'kur',
        'kv': 'kom',
        'kw': 'cor',
        'ky': 'kir',
        'la': 'lat',
        'lb': 'ltz',
        'lg': 'lug',
        'li': 'lim',
        'ln': 'lin',
        'lo': 'lao',
        'lt': 'lit',
        'lu': 'lub',
        'lv': 'lav',
        'mg': 'mlg',
        'mh': 'mah',
        'mi': 'mri',
        'mk': 'mkd',
        'ml': 'mal',
        'mn': 'mon',
        'mr': 'mar',
        'ms': 'msa',
        'mt': 'mlt',
        'my': 'mya',
        'na': 'nau',
        'nb': 'nob',
        'nd': 'nde',
        'ne': 'nep',
        'ng': 'ndo',
        'nl': 'nld',
        'nn': 'nno',
        'no': 'nor',
        'nr': 'nbl',
        'nv': 'nav',
        'ny': 'nya',
        'oc': 'oci',
        'oj': 'oji',
        'om': 'orm',
        'or': 'ori',
        'os': 'oss',
        'pa': 'pan',
        'pi': 'pli',
        'pl': 'pol',
        'ps': 'pus',
        'pt': 'por',
        'qu': 'que',
        'rm': 'roh',
        'rn': 'run',
        'ro': 'ron',
        'ru': 'rus',
        'rw': 'kin',
        'sa': 'san',
        'sc': 'srd',
        'sd': 'snd',
        'se': 'sme',
        'sg': 'sag',
        'si': 'sin',
        'sk': 'slk',
        'sl': 'slv',
        'sm': 'smo',
        'sn': 'sna',
        'so': 'som',
        'sq': 'sqi',
        'sr': 'srp',
        'ss': 'ssw',
        'st': 'sot',
        'su': 'sun',
        'sv': 'swe',
        'sw': 'swa',
        'ta': 'tam',
        'te': 'tel',
        'tg': 'tgk',
        'th': 'tha',
        'ti': 'tir',
        'tk': 'tuk',
        'tl': 'tgl',
        'tn': 'tsn',
        'to': 'ton',
        'tr': 'tur',
        'ts': 'tso',
        'tt': 'tat',
        'tw': 'twi',
        'ty': 'tah',
        'ug': 'uig',
        'uk': 'ukr',
        'ur': 'urd',
        'uz': 'uzb',
        've': 'ven',
        'vi': 'vie',
        'vo': 'vol',
        'wa': 'wln',
        'wo': 'wol',
        'xh': 'xho',
        'yi': 'yid',
        'yo': 'yor',
        'za': 'zha',
        'zh': 'zho',
        'zu': 'zul',
    }

    def __init__(self, downloader=None, subtitlesformat='srt'):
        super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
        self._subformat = subtitlesformat

    @classmethod
    def _conver_lang_code(cls, code):
        """Convert language code from ISO 639-1 to ISO 639-2/T"""
        return cls._lang_map.get(code[:2])

    def run(self, information):
        if information['ext'] != u'mp4':
            self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
            return True, information
        if not information.get('subtitles'):
            self._downloader.to_screen(u'[ffmpeg] There aren\'t any subtitles to embed') 
            return True, information

        sub_langs = [key for key in information['subtitles']]
        filename = information['filepath']
        input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]

        opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
        for (i, lang) in enumerate(sub_langs):
            opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
            lang_code = self._conver_lang_code(lang)
            if lang_code is not None:
                opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
        opts.extend(['-f', 'mp4'])

        temp_filename = filename + u'.temp'
        self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
        self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
        os.remove(encodeFilename(filename))
        os.rename(encodeFilename(temp_filename), encodeFilename(filename))

        return True, information


class FFmpegMetadataPP(FFmpegPostProcessor):
    def run(self, info):
        metadata = {}
        if info.get('title') is not None:
            metadata['title'] = info['title']
        if info.get('upload_date') is not None:
            metadata['date'] = info['upload_date']
        if info.get('uploader') is not None:
            metadata['artist'] = info['uploader']
        elif info.get('uploader_id') is not None:
            metadata['artist'] = info['uploader_id']

        if not metadata:
            self._downloader.to_screen(u'[ffmpeg] There isn\'t any metadata to add')
            return True, info

        filename = info['filepath']
        ext = os.path.splitext(filename)[1][1:]
        temp_filename = filename + u'.temp'

        options = ['-c', 'copy']
        for (name, value) in metadata.items():
            options.extend(['-metadata', '%s=%s' % (name, value)])
        options.extend(['-f', ext])

        self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
        self.run_ffmpeg(filename, temp_filename, options)
        os.remove(encodeFilename(filename))
        os.rename(encodeFilename(temp_filename), encodeFilename(filename))
        return True, info


class XAttrMetadataPP(PostProcessor):

    #
    # More info about extended attributes for media:
    #   http://freedesktop.org/wiki/CommonExtendedAttributes/
    #   http://www.freedesktop.org/wiki/PhreedomDraft/
    #   http://dublincore.org/documents/usageguide/elements.shtml
    #
    # TODO:
    #  * capture youtube keywords and put them in 'user.dublincore.subject' (comma-separated)
    #  * figure out which xattrs can be used for 'duration', 'thumbnail', 'resolution'
    #

    def run(self, info):
        """ Set extended attributes on downloaded file (if xattr support is found). """

        from .utils import hyphenate_date

        # This mess below finds the best xattr tool for the job and creates a
        # "write_xattr" function.
        try:
            # try the pyxattr module...
            import xattr
            def write_xattr(path, key, value):
                return xattr.setxattr(path, key, value)

        except ImportError:

            if os.name == 'posix':
                def which(bin):
                    for dir in os.environ["PATH"].split(":"):
                        path = os.path.join(dir, bin)
                        if os.path.exists(path):
                            return path

                user_has_setfattr = which("setfattr")
                user_has_xattr    = which("xattr")

                if user_has_setfattr or user_has_xattr:

                    def write_xattr(path, key, value):
                        import errno
                        potential_errors = {
                            # setfattr: /tmp/blah: Operation not supported
                            "Operation not supported": errno.EOPNOTSUPP,
                            # setfattr: ~/blah: No such file or directory
                            # xattr: No such file: ~/blah
                            "No such file": errno.ENOENT,
                        }

                        if user_has_setfattr:
                            cmd = ['setfattr', '-n', key, '-v', value, path]
                        elif user_has_xattr:
                            cmd = ['xattr', '-w', key, value, path]

                        try:
                            output = subprocess.check_output(cmd, stderr=subprocess.STDOUT)
                        except subprocess.CalledProcessError as e:
                            errorstr = e.output.strip().decode()
                            for potential_errorstr, potential_errno in potential_errors.items():
                                if errorstr.find(potential_errorstr) > -1:
                                    e = OSError(potential_errno, potential_errorstr)
                                    e.__cause__ = None
                                    raise e
                            raise # Reraise unhandled error

                else:
                    # On Unix, and can't find pyxattr, setfattr, or xattr.
                    if sys.platform.startswith('linux'):
                        self._downloader.report_error("Couldn't find a tool to set the xattrs. Install either the python 'pyxattr' or 'xattr' modules, or the GNU 'attr' package (which contains the 'setfattr' tool).")
                    elif sys.platform == 'darwin':
                        self._downloader.report_error("Couldn't find a tool to set the xattrs. Install either the python 'xattr' module, or the 'xattr' binary.")
            else:
                # Write xattrs to NTFS Alternate Data Streams: http://en.wikipedia.org/wiki/NTFS#Alternate_data_streams_.28ADS.29
                def write_xattr(path, key, value):
                    assert(key.find(":") < 0)
                    assert(path.find(":") < 0)
                    assert(os.path.exists(path))

                    f = open(path+":"+key, "w")
                    f.write(value)
                    f.close()

        # Write the metadata to the file's xattrs
        self._downloader.to_screen('[metadata] Writing metadata to file\'s xattrs...')

        filename = info['filepath']

        try:
            xattr_mapping = {
                'user.xdg.referrer.url':       'webpage_url',
                # 'user.xdg.comment':            'description',
                'user.dublincore.title':       'title',
                'user.dublincore.date':        'upload_date',
                'user.dublincore.description': 'description',
                'user.dublincore.contributor': 'uploader',
                'user.dublincore.format':      'format',
            }

            for xattrname, infoname in xattr_mapping.items():

                value = info.get(infoname)

                if value:
                    if infoname == "upload_date":
                        value = hyphenate_date(value)

                    write_xattr(filename, xattrname, value)

            return True, info

        except OSError:
            self._downloader.report_error("This filesystem doesn't support extended attributes. (You may have to enable them in your /etc/fstab)")
            return False, info