aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/__init__.py
blob: c4e1d32db1825dcd1f539344828d2cfde9aecb9e (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
#!/usr/bin/env python
# -*- coding: utf-8 -*-

__authors__  = (
    'Ricardo Garcia Gonzalez',
    'Danny Colligan',
    'Benjamin Johnson',
    'Vasyl\' Vavrychuk',
    'Witold Baryluk',
    'Paweł Paprota',
    'Gergely Imreh',
    'Rogério Brito',
    'Philipp Hagemeister',
    'Sören Schulze',
    'Kevin Ngo',
    'Ori Avtalion',
    'shizeeg',
    'Filippo Valsorda',
    'Christian Albrecht',
    'Dave Vasilevsky',
    'Jaime Marquínez Ferrándiz',
    'Jeff Crouse',
    'Osama Khalid',
    'Michael Walter',
    'M. Yasoob Ullah Khalid',
    'Julien Fraichard',
    'Johny Mo Swag',
    'Axel Noack',
    'Albert Kim',
    'Pierre Rudloff',
    'Huarong Huo',
    'Ismael Mejía',
    'Steffan \'Ruirize\' James',
    'Andras Elso',
    'Jelle van der Waa',
    'Marcin Cieślak',
    'Anton Larionov',
    'Takuya Tsuchida',
    'Sergey M.',
    'Michael Orlitzky',
    'Chris Gahan',
    'Saimadhav Heblikar',
    'Mike Col',
    'Oleg Prutz',
    'pulpe',
    'Andreas Schmitz',
    'Michael Kaiser',
    'Niklas Laxström',
    'David Triendl',
    'Anthony Weems',
    'David Wagner',
    'Juan C. Olivares',
    'Mattias Harrysson',
    'phaer',
    'Sainyam Kapoor',
    'Nicolas Évrard',
    'Jason Normore',
    'Hoje Lee',
    'Adam Thalhammer',
    'Georg Jähnig',
    'Ralf Haring',
    'Koki Takahashi',
    'Ariset Llerena',
    'Adam Malcontenti-Wilson',
    'Tobias Bell',
    'Naglis Jonaitis',
    'Charles Chen',
    'Hassaan Ali',
    'Dobrosław Żybort',
    'David Fabijan',
    'Sebastian Haas',
    'Alexander Kirk',
    'Erik Johnson',
    'Keith Beckman',
    'Ole Ernst',
    'Aaron McDaniel (mcd1992)',
    'Magnus Kolstad',
    'Hari Padmanaban',
    'Carlos Ramos',
    '5moufl',
    'lenaten',
)

__license__ = 'Public Domain'

import codecs
import io
import os
import random
import sys


from .options import (
    parseOpts,
)
from .utils import (
    compat_getpass,
    compat_print,
    DateRange,
    DEFAULT_OUTTMPL,
    decodeOption,
    DownloadError,
    MaxDownloadsReached,
    preferredencoding,
    read_batch_urls,
    SameFileError,
    setproctitle,
    std_headers,
    write_string,
)
from .update import update_self
from .downloader import (
    FileDownloader,
)
from .extractor import gen_extractors
from .YoutubeDL import YoutubeDL
from .postprocessor import (
    AtomicParsleyPP,
    FFmpegAudioFixPP,
    FFmpegMetadataPP,
    FFmpegVideoConvertor,
    FFmpegExtractAudioPP,
    FFmpegEmbedSubtitlePP,
    XAttrMetadataPP,
    ExecAfterDownloadPP,
)


def _real_main(argv=None):
    # Compatibility fixes for Windows
    if sys.platform == 'win32':
        # https://github.com/rg3/youtube-dl/issues/820
        codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)

    setproctitle(u'youtube-dl')

    parser, opts, args = parseOpts(argv)

    # Set user agent
    if opts.user_agent is not None:
        std_headers['User-Agent'] = opts.user_agent

    # Set referer
    if opts.referer is not None:
        std_headers['Referer'] = opts.referer

    # Custom HTTP headers
    if opts.headers is not None:
        for h in opts.headers:
            if h.find(':', 1) < 0:
                parser.error(u'wrong header formatting, it should be key:value, not "%s"'%h)
            key, value = h.split(':', 2)
            if opts.verbose:
                write_string(u'[debug] Adding header from command line option %s:%s\n'%(key, value))
            std_headers[key] = value

    # Dump user agent
    if opts.dump_user_agent:
        compat_print(std_headers['User-Agent'])
        sys.exit(0)

    # Batch file verification
    batch_urls = []
    if opts.batchfile is not None:
        try:
            if opts.batchfile == '-':
                batchfd = sys.stdin
            else:
                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
            batch_urls = read_batch_urls(batchfd)
            if opts.verbose:
                write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
        except IOError:
            sys.exit(u'ERROR: batch file could not be read')
    all_urls = batch_urls + args
    all_urls = [url.strip() for url in all_urls]
    _enc = preferredencoding()
    all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]

    extractors = gen_extractors()

    if opts.list_extractors:
        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
            compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
            matchedUrls = [url for url in all_urls if ie.suitable(url)]
            for mu in matchedUrls:
                compat_print(u'  ' + mu)
        sys.exit(0)
    if opts.list_extractor_descriptions:
        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
            if not ie._WORKING:
                continue
            desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
            if desc is False:
                continue
            if hasattr(ie, 'SEARCH_KEY'):
                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny')
                _COUNTS = (u'', u'5', u'10', u'all')
                desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
            compat_print(desc)
        sys.exit(0)


    # Conflicting, missing and erroneous options
    if opts.usenetrc and (opts.username is not None or opts.password is not None):
        parser.error(u'using .netrc conflicts with giving username/password')
    if opts.password is not None and opts.username is None:
        parser.error(u'account username missing\n')
    if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
        parser.error(u'using output template conflicts with using title, video ID or auto number')
    if opts.usetitle and opts.useid:
        parser.error(u'using title conflicts with using video ID')
    if opts.username is not None and opts.password is None:
        opts.password = compat_getpass(u'Type account password and press [Return]: ')
    if opts.ratelimit is not None:
        numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
        if numeric_limit is None:
            parser.error(u'invalid rate limit specified')
        opts.ratelimit = numeric_limit
    if opts.min_filesize is not None:
        numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
        if numeric_limit is None:
            parser.error(u'invalid min_filesize specified')
        opts.min_filesize = numeric_limit
    if opts.max_filesize is not None:
        numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
        if numeric_limit is None:
            parser.error(u'invalid max_filesize specified')
        opts.max_filesize = numeric_limit
    if opts.retries is not None:
        try:
            opts.retries = int(opts.retries)
        except (TypeError, ValueError):
            parser.error(u'invalid retry count specified')
    if opts.buffersize is not None:
        numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
        if numeric_buffersize is None:
            parser.error(u'invalid buffer size specified')
        opts.buffersize = numeric_buffersize
    if opts.playliststart <= 0:
        raise ValueError(u'Playlist start must be positive')
    if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
        raise ValueError(u'Playlist end must be greater than playlist start')
    if opts.extractaudio:
        if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
            parser.error(u'invalid audio format specified')
    if opts.audioquality:
        opts.audioquality = opts.audioquality.strip('k').strip('K')
        if not opts.audioquality.isdigit():
            parser.error(u'invalid audio quality specified')
    if opts.recodevideo is not None:
        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
            parser.error(u'invalid video recode format specified')
    if opts.date is not None:
        date = DateRange.day(opts.date)
    else:
        date = DateRange(opts.dateafter, opts.datebefore)

    # Do not download videos when there are audio-only formats
    if opts.extractaudio and not opts.keepvideo and opts.format is None:
        opts.format = 'bestaudio/best'

    # --all-sub automatically sets --write-sub if --write-auto-sub is not given
    # this was the old behaviour if only --all-sub was given.
    if opts.allsubtitles and (opts.writeautomaticsub == False):
        opts.writesubtitles = True

    if sys.version_info < (3,):
        # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
        if opts.outtmpl is not None:
            opts.outtmpl = opts.outtmpl.decode(preferredencoding())
    outtmpl =((opts.outtmpl is not None and opts.outtmpl)
            or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
            or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
            or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
            or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
            or (opts.useid and u'%(id)s.%(ext)s')
            or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
            or DEFAULT_OUTTMPL)
    if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
        parser.error(u'Cannot download a video and extract audio into the same'
                     u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
                     u' template'.format(outtmpl))

    any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson
    download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive

    ydl_opts = {
        'usenetrc': opts.usenetrc,
        'username': opts.username,
        'password': opts.password,
        'twofactor': opts.twofactor,
        'videopassword': opts.videopassword,
        'quiet': (opts.quiet or any_printing),
        'no_warnings': opts.no_warnings,
        'forceurl': opts.geturl,
        'forcetitle': opts.gettitle,
        'forceid': opts.getid,
        'forcethumbnail': opts.getthumbnail,
        'forcedescription': opts.getdescription,
        'forceduration': opts.getduration,
        'forcefilename': opts.getfilename,
        'forceformat': opts.getformat,
        'forcejson': opts.dumpjson,
        'simulate': opts.simulate,
        'skip_download': (opts.skip_download or opts.simulate or any_printing),
        'format': opts.format,
        'format_limit': opts.format_limit,
        'listformats': opts.listformats,
        'outtmpl': outtmpl,
        'autonumber_size': opts.autonumber_size,
        'restrictfilenames': opts.restrictfilenames,
        'ignoreerrors': opts.ignoreerrors,
        'ratelimit': opts.ratelimit,
        'nooverwrites': opts.nooverwrites,
        'retries': opts.retries,
        'buffersize': opts.buffersize,
        'noresizebuffer': opts.noresizebuffer,
        'continuedl': opts.continue_dl,
        'noprogress': opts.noprogress,
        'progress_with_newline': opts.progress_with_newline,
        'playliststart': opts.playliststart,
        'playlistend': opts.playlistend,
        'noplaylist': opts.noplaylist,
        'logtostderr': opts.outtmpl == '-',
        'consoletitle': opts.consoletitle,
        'nopart': opts.nopart,
        'updatetime': opts.updatetime,
        'writedescription': opts.writedescription,
        'writeannotations': opts.writeannotations,
        'writeinfojson': opts.writeinfojson,
        'writethumbnail': opts.writethumbnail,
        'writesubtitles': opts.writesubtitles,
        'writeautomaticsub': opts.writeautomaticsub,
        'allsubtitles': opts.allsubtitles,
        'listsubtitles': opts.listsubtitles,
        'subtitlesformat': opts.subtitlesformat,
        'subtitleslangs': opts.subtitleslangs,
        'matchtitle': decodeOption(opts.matchtitle),
        'rejecttitle': decodeOption(opts.rejecttitle),
        'max_downloads': opts.max_downloads,
        'prefer_free_formats': opts.prefer_free_formats,
        'verbose': opts.verbose,
        'dump_intermediate_pages': opts.dump_intermediate_pages,
        'write_pages': opts.write_pages,
        'test': opts.test,
        'keepvideo': opts.keepvideo,
        'min_filesize': opts.min_filesize,
        'max_filesize': opts.max_filesize,
        'min_views': opts.min_views,
        'max_views': opts.max_views,
        'daterange': date,
        'cachedir': opts.cachedir,
        'youtube_print_sig_code': opts.youtube_print_sig_code,
        'age_limit': opts.age_limit,
        'download_archive': download_archive_fn,
        'cookiefile': opts.cookiefile,
        'nocheckcertificate': opts.no_check_certificate,
        'prefer_insecure': opts.prefer_insecure,
        'proxy': opts.proxy,
        'socket_timeout': opts.socket_timeout,
        'bidi_workaround': opts.bidi_workaround,
        'debug_printtraffic': opts.debug_printtraffic,
        'prefer_ffmpeg': opts.prefer_ffmpeg,
        'include_ads': opts.include_ads,
        'default_search': opts.default_search,
        'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
        'encoding': opts.encoding,
        'exec_cmd': opts.exec_cmd,
        'extract_flat': opts.extract_flat,
    }

    with YoutubeDL(ydl_opts) as ydl:
        ydl.print_debug_header()
        ydl.add_default_info_extractors()

        # PostProcessors
        # Add the metadata pp first, the other pps will copy it
        if opts.addmetadata:
            ydl.add_post_processor(FFmpegMetadataPP())
        if opts.extractaudio:
            ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
        if opts.recodevideo:
            ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
        if opts.embedsubtitles:
            ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
        if opts.xattrs:
            ydl.add_post_processor(XAttrMetadataPP())
        if opts.embedthumbnail:
            if not opts.addmetadata:
                ydl.add_post_processor(FFmpegAudioFixPP())
            ydl.add_post_processor(AtomicParsleyPP())


        # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
        # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
        if opts.exec_cmd:
            ydl.add_post_processor(ExecAfterDownloadPP(
                verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))

        # Update version
        if opts.update_self:
            update_self(ydl.to_screen, opts.verbose)

        # Remove cache dir
        if opts.rm_cachedir:
            ydl.cache.remove()

        # Maybe do nothing
        if (len(all_urls) < 1) and (opts.load_info_filename is None):
            if not (opts.update_self or opts.rm_cachedir):
                parser.error(u'you must provide at least one URL')
            else:
                sys.exit()

        try:
            if opts.load_info_filename is not None:
                retcode = ydl.download_with_info_file(opts.load_info_filename)
            else:
                retcode = ydl.download(all_urls)
        except MaxDownloadsReached:
            ydl.to_screen(u'--max-download limit reached, aborting.')
            retcode = 101

    sys.exit(retcode)


def main(argv=None):
    try:
        _real_main(argv)
    except DownloadError:
        sys.exit(1)
    except SameFileError:
        sys.exit(u'ERROR: fixed output name but more than one file to download')
    except KeyboardInterrupt:
        sys.exit(u'\nERROR: Interrupted by user')