]>
Commit | Line | Data |
---|---|---|
1 | #!/usr/bin/env python | |
2 | # -*- coding: utf-8 -*- | |
3 | ||
4 | from __future__ import unicode_literals | |
5 | ||
6 | __license__ = 'Public Domain' | |
7 | ||
8 | import codecs | |
9 | import io | |
10 | import os | |
11 | import random | |
12 | import shlex | |
13 | import sys | |
14 | ||
15 | ||
16 | from .options import ( | |
17 | parseOpts, | |
18 | ) | |
19 | from .compat import ( | |
20 | compat_expanduser, | |
21 | compat_getpass, | |
22 | compat_print, | |
23 | workaround_optparse_bug9161, | |
24 | ) | |
25 | from .utils import ( | |
26 | DateRange, | |
27 | decodeOption, | |
28 | DEFAULT_OUTTMPL, | |
29 | DownloadError, | |
30 | match_filter_func, | |
31 | MaxDownloadsReached, | |
32 | preferredencoding, | |
33 | read_batch_urls, | |
34 | SameFileError, | |
35 | setproctitle, | |
36 | std_headers, | |
37 | write_string, | |
38 | ) | |
39 | from .update import update_self | |
40 | from .downloader import ( | |
41 | FileDownloader, | |
42 | ) | |
43 | from .extractor import gen_extractors, list_extractors | |
44 | from .YoutubeDL import YoutubeDL | |
45 | ||
46 | ||
47 | def _real_main(argv=None): | |
48 | # Compatibility fixes for Windows | |
49 | if sys.platform == 'win32': | |
50 | # https://github.com/rg3/youtube-dl/issues/820 | |
51 | codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None) | |
52 | ||
53 | workaround_optparse_bug9161() | |
54 | ||
55 | setproctitle('youtube-dl') | |
56 | ||
57 | parser, opts, args = parseOpts(argv) | |
58 | ||
59 | # Set user agent | |
60 | if opts.user_agent is not None: | |
61 | std_headers['User-Agent'] = opts.user_agent | |
62 | ||
63 | # Set referer | |
64 | if opts.referer is not None: | |
65 | std_headers['Referer'] = opts.referer | |
66 | ||
67 | # Custom HTTP headers | |
68 | if opts.headers is not None: | |
69 | for h in opts.headers: | |
70 | if h.find(':', 1) < 0: | |
71 | parser.error('wrong header formatting, it should be key:value, not "%s"' % h) | |
72 | key, value = h.split(':', 2) | |
73 | if opts.verbose: | |
74 | write_string('[debug] Adding header from command line option %s:%s\n' % (key, value)) | |
75 | std_headers[key] = value | |
76 | ||
77 | # Dump user agent | |
78 | if opts.dump_user_agent: | |
79 | compat_print(std_headers['User-Agent']) | |
80 | sys.exit(0) | |
81 | ||
82 | # Batch file verification | |
83 | batch_urls = [] | |
84 | if opts.batchfile is not None: | |
85 | try: | |
86 | if opts.batchfile == '-': | |
87 | batchfd = sys.stdin | |
88 | else: | |
89 | batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore') | |
90 | batch_urls = read_batch_urls(batchfd) | |
91 | if opts.verbose: | |
92 | write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n') | |
93 | except IOError: | |
94 | sys.exit('ERROR: batch file could not be read') | |
95 | all_urls = batch_urls + args | |
96 | all_urls = [url.strip() for url in all_urls] | |
97 | _enc = preferredencoding() | |
98 | all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls] | |
99 | ||
100 | if opts.list_extractors: | |
101 | for ie in list_extractors(opts.age_limit): | |
102 | compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) | |
103 | matchedUrls = [url for url in all_urls if ie.suitable(url)] | |
104 | for mu in matchedUrls: | |
105 | compat_print(' ' + mu) | |
106 | sys.exit(0) | |
107 | if opts.list_extractor_descriptions: | |
108 | for ie in list_extractors(opts.age_limit): | |
109 | if not ie._WORKING: | |
110 | continue | |
111 | desc = getattr(ie, 'IE_DESC', ie.IE_NAME) | |
112 | if desc is False: | |
113 | continue | |
114 | if hasattr(ie, 'SEARCH_KEY'): | |
115 | _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow') | |
116 | _COUNTS = ('', '5', '10', 'all') | |
117 | desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) | |
118 | compat_print(desc) | |
119 | sys.exit(0) | |
120 | ||
121 | # Conflicting, missing and erroneous options | |
122 | if opts.usenetrc and (opts.username is not None or opts.password is not None): | |
123 | parser.error('using .netrc conflicts with giving username/password') | |
124 | if opts.password is not None and opts.username is None: | |
125 | parser.error('account username missing\n') | |
126 | if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid): | |
127 | parser.error('using output template conflicts with using title, video ID or auto number') | |
128 | if opts.usetitle and opts.useid: | |
129 | parser.error('using title conflicts with using video ID') | |
130 | if opts.username is not None and opts.password is None: | |
131 | opts.password = compat_getpass('Type account password and press [Return]: ') | |
132 | if opts.ratelimit is not None: | |
133 | numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) | |
134 | if numeric_limit is None: | |
135 | parser.error('invalid rate limit specified') | |
136 | opts.ratelimit = numeric_limit | |
137 | if opts.min_filesize is not None: | |
138 | numeric_limit = FileDownloader.parse_bytes(opts.min_filesize) | |
139 | if numeric_limit is None: | |
140 | parser.error('invalid min_filesize specified') | |
141 | opts.min_filesize = numeric_limit | |
142 | if opts.max_filesize is not None: | |
143 | numeric_limit = FileDownloader.parse_bytes(opts.max_filesize) | |
144 | if numeric_limit is None: | |
145 | parser.error('invalid max_filesize specified') | |
146 | opts.max_filesize = numeric_limit | |
147 | if opts.retries is not None: | |
148 | if opts.retries in ('inf', 'infinite'): | |
149 | opts_retries = float('inf') | |
150 | else: | |
151 | try: | |
152 | opts_retries = int(opts.retries) | |
153 | except (TypeError, ValueError): | |
154 | parser.error('invalid retry count specified') | |
155 | if opts.buffersize is not None: | |
156 | numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) | |
157 | if numeric_buffersize is None: | |
158 | parser.error('invalid buffer size specified') | |
159 | opts.buffersize = numeric_buffersize | |
160 | if opts.playliststart <= 0: | |
161 | raise ValueError('Playlist start must be positive') | |
162 | if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart: | |
163 | raise ValueError('Playlist end must be greater than playlist start') | |
164 | if opts.extractaudio: | |
165 | if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']: | |
166 | parser.error('invalid audio format specified') | |
167 | if opts.audioquality: | |
168 | opts.audioquality = opts.audioquality.strip('k').strip('K') | |
169 | if not opts.audioquality.isdigit(): | |
170 | parser.error('invalid audio quality specified') | |
171 | if opts.recodevideo is not None: | |
172 | if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: | |
173 | parser.error('invalid video recode format specified') | |
174 | if opts.convertsubtitles is not None: | |
175 | if opts.convertsubtitles not in ['srt', 'vtt', 'ass']: | |
176 | parser.error('invalid subtitle format specified') | |
177 | ||
178 | if opts.date is not None: | |
179 | date = DateRange.day(opts.date) | |
180 | else: | |
181 | date = DateRange(opts.dateafter, opts.datebefore) | |
182 | ||
183 | # Do not download videos when there are audio-only formats | |
184 | if opts.extractaudio and not opts.keepvideo and opts.format is None: | |
185 | opts.format = 'bestaudio/best' | |
186 | ||
187 | # --all-sub automatically sets --write-sub if --write-auto-sub is not given | |
188 | # this was the old behaviour if only --all-sub was given. | |
189 | if opts.allsubtitles and not opts.writeautomaticsub: | |
190 | opts.writesubtitles = True | |
191 | ||
192 | outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or | |
193 | (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or | |
194 | (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or | |
195 | (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or | |
196 | (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or | |
197 | (opts.useid and '%(id)s.%(ext)s') or | |
198 | (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or | |
199 | DEFAULT_OUTTMPL) | |
200 | if not os.path.splitext(outtmpl)[1] and opts.extractaudio: | |
201 | parser.error('Cannot download a video and extract audio into the same' | |
202 | ' file! Use "{0}.%(ext)s" instead of "{0}" as the output' | |
203 | ' template'.format(outtmpl)) | |
204 | ||
205 | any_getting = 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 or opts.dump_single_json | |
206 | any_printing = opts.print_json | |
207 | download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive | |
208 | ||
209 | # PostProcessors | |
210 | postprocessors = [] | |
211 | # Add the metadata pp first, the other pps will copy it | |
212 | if opts.metafromtitle: | |
213 | postprocessors.append({ | |
214 | 'key': 'MetadataFromTitle', | |
215 | 'titleformat': opts.metafromtitle | |
216 | }) | |
217 | if opts.addmetadata: | |
218 | postprocessors.append({'key': 'FFmpegMetadata'}) | |
219 | if opts.extractaudio: | |
220 | postprocessors.append({ | |
221 | 'key': 'FFmpegExtractAudio', | |
222 | 'preferredcodec': opts.audioformat, | |
223 | 'preferredquality': opts.audioquality, | |
224 | 'nopostoverwrites': opts.nopostoverwrites, | |
225 | }) | |
226 | if opts.recodevideo: | |
227 | postprocessors.append({ | |
228 | 'key': 'FFmpegVideoConvertor', | |
229 | 'preferedformat': opts.recodevideo, | |
230 | }) | |
231 | if opts.convertsubtitles: | |
232 | postprocessors.append({ | |
233 | 'key': 'FFmpegSubtitlesConvertor', | |
234 | 'format': opts.convertsubtitles, | |
235 | }) | |
236 | if opts.embedsubtitles: | |
237 | postprocessors.append({ | |
238 | 'key': 'FFmpegEmbedSubtitle', | |
239 | }) | |
240 | if opts.xattrs: | |
241 | postprocessors.append({'key': 'XAttrMetadata'}) | |
242 | if opts.embedthumbnail: | |
243 | postprocessors.append({'key': 'EmbedThumbnail'}) | |
244 | # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. | |
245 | # So if the user is able to remove the file before your postprocessor runs it might cause a few problems. | |
246 | if opts.exec_cmd: | |
247 | postprocessors.append({ | |
248 | 'key': 'ExecAfterDownload', | |
249 | 'verboseOutput': opts.verbose, | |
250 | 'exec_cmd': opts.exec_cmd, | |
251 | }) | |
252 | if opts.xattr_set_filesize: | |
253 | try: | |
254 | import xattr | |
255 | xattr # Confuse flake8 | |
256 | except ImportError: | |
257 | parser.error('setting filesize xattr requested but python-xattr is not available') | |
258 | external_downloader_args = None | |
259 | if opts.external_downloader_args: | |
260 | external_downloader_args = shlex.split(opts.external_downloader_args) | |
261 | match_filter = ( | |
262 | None if opts.match_filter is None | |
263 | else match_filter_func(opts.match_filter)) | |
264 | ||
265 | ydl_opts = { | |
266 | 'usenetrc': opts.usenetrc, | |
267 | 'username': opts.username, | |
268 | 'password': opts.password, | |
269 | 'twofactor': opts.twofactor, | |
270 | 'videopassword': opts.videopassword, | |
271 | 'quiet': (opts.quiet or any_getting or any_printing), | |
272 | 'no_warnings': opts.no_warnings, | |
273 | 'forceurl': opts.geturl, | |
274 | 'forcetitle': opts.gettitle, | |
275 | 'forceid': opts.getid, | |
276 | 'forcethumbnail': opts.getthumbnail, | |
277 | 'forcedescription': opts.getdescription, | |
278 | 'forceduration': opts.getduration, | |
279 | 'forcefilename': opts.getfilename, | |
280 | 'forceformat': opts.getformat, | |
281 | 'forcejson': opts.dumpjson or opts.print_json, | |
282 | 'dump_single_json': opts.dump_single_json, | |
283 | 'simulate': opts.simulate or any_getting, | |
284 | 'skip_download': opts.skip_download, | |
285 | 'format': opts.format, | |
286 | 'listformats': opts.listformats, | |
287 | 'outtmpl': outtmpl, | |
288 | 'autonumber_size': opts.autonumber_size, | |
289 | 'restrictfilenames': opts.restrictfilenames, | |
290 | 'ignoreerrors': opts.ignoreerrors, | |
291 | 'ratelimit': opts.ratelimit, | |
292 | 'nooverwrites': opts.nooverwrites, | |
293 | 'retries': opts_retries, | |
294 | 'buffersize': opts.buffersize, | |
295 | 'noresizebuffer': opts.noresizebuffer, | |
296 | 'continuedl': opts.continue_dl, | |
297 | 'noprogress': opts.noprogress, | |
298 | 'progress_with_newline': opts.progress_with_newline, | |
299 | 'playliststart': opts.playliststart, | |
300 | 'playlistend': opts.playlistend, | |
301 | 'playlistreverse': opts.playlist_reverse, | |
302 | 'noplaylist': opts.noplaylist, | |
303 | 'logtostderr': opts.outtmpl == '-', | |
304 | 'consoletitle': opts.consoletitle, | |
305 | 'nopart': opts.nopart, | |
306 | 'updatetime': opts.updatetime, | |
307 | 'writedescription': opts.writedescription, | |
308 | 'writeannotations': opts.writeannotations, | |
309 | 'writeinfojson': opts.writeinfojson, | |
310 | 'writethumbnail': opts.writethumbnail, | |
311 | 'write_all_thumbnails': opts.write_all_thumbnails, | |
312 | 'writesubtitles': opts.writesubtitles, | |
313 | 'writeautomaticsub': opts.writeautomaticsub, | |
314 | 'allsubtitles': opts.allsubtitles, | |
315 | 'listsubtitles': opts.listsubtitles, | |
316 | 'subtitlesformat': opts.subtitlesformat, | |
317 | 'subtitleslangs': opts.subtitleslangs, | |
318 | 'matchtitle': decodeOption(opts.matchtitle), | |
319 | 'rejecttitle': decodeOption(opts.rejecttitle), | |
320 | 'max_downloads': opts.max_downloads, | |
321 | 'prefer_free_formats': opts.prefer_free_formats, | |
322 | 'verbose': opts.verbose, | |
323 | 'dump_intermediate_pages': opts.dump_intermediate_pages, | |
324 | 'write_pages': opts.write_pages, | |
325 | 'test': opts.test, | |
326 | 'keepvideo': opts.keepvideo, | |
327 | 'min_filesize': opts.min_filesize, | |
328 | 'max_filesize': opts.max_filesize, | |
329 | 'min_views': opts.min_views, | |
330 | 'max_views': opts.max_views, | |
331 | 'daterange': date, | |
332 | 'cachedir': opts.cachedir, | |
333 | 'youtube_print_sig_code': opts.youtube_print_sig_code, | |
334 | 'age_limit': opts.age_limit, | |
335 | 'download_archive': download_archive_fn, | |
336 | 'cookiefile': opts.cookiefile, | |
337 | 'nocheckcertificate': opts.no_check_certificate, | |
338 | 'prefer_insecure': opts.prefer_insecure, | |
339 | 'proxy': opts.proxy, | |
340 | 'socket_timeout': opts.socket_timeout, | |
341 | 'bidi_workaround': opts.bidi_workaround, | |
342 | 'debug_printtraffic': opts.debug_printtraffic, | |
343 | 'prefer_ffmpeg': opts.prefer_ffmpeg, | |
344 | 'include_ads': opts.include_ads, | |
345 | 'default_search': opts.default_search, | |
346 | 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, | |
347 | 'encoding': opts.encoding, | |
348 | 'exec_cmd': opts.exec_cmd, | |
349 | 'extract_flat': opts.extract_flat, | |
350 | 'merge_output_format': opts.merge_output_format, | |
351 | 'postprocessors': postprocessors, | |
352 | 'fixup': opts.fixup, | |
353 | 'source_address': opts.source_address, | |
354 | 'call_home': opts.call_home, | |
355 | 'sleep_interval': opts.sleep_interval, | |
356 | 'external_downloader': opts.external_downloader, | |
357 | 'list_thumbnails': opts.list_thumbnails, | |
358 | 'playlist_items': opts.playlist_items, | |
359 | 'xattr_set_filesize': opts.xattr_set_filesize, | |
360 | 'match_filter': match_filter, | |
361 | 'no_color': opts.no_color, | |
362 | 'ffmpeg_location': opts.ffmpeg_location, | |
363 | 'hls_prefer_native': opts.hls_prefer_native, | |
364 | 'external_downloader_args': external_downloader_args, | |
365 | 'cn_verification_proxy': opts.cn_verification_proxy, | |
366 | } | |
367 | ||
368 | with YoutubeDL(ydl_opts) as ydl: | |
369 | # Update version | |
370 | if opts.update_self: | |
371 | update_self(ydl.to_screen, opts.verbose) | |
372 | ||
373 | # Remove cache dir | |
374 | if opts.rm_cachedir: | |
375 | ydl.cache.remove() | |
376 | ||
377 | # Maybe do nothing | |
378 | if (len(all_urls) < 1) and (opts.load_info_filename is None): | |
379 | if opts.update_self or opts.rm_cachedir: | |
380 | sys.exit() | |
381 | ||
382 | ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv) | |
383 | parser.error( | |
384 | 'You must provide at least one URL.\n' | |
385 | 'Type youtube-dl --help to see a list of all options.') | |
386 | ||
387 | try: | |
388 | if opts.load_info_filename is not None: | |
389 | retcode = ydl.download_with_info_file(opts.load_info_filename) | |
390 | else: | |
391 | retcode = ydl.download(all_urls) | |
392 | except MaxDownloadsReached: | |
393 | ydl.to_screen('--max-download limit reached, aborting.') | |
394 | retcode = 101 | |
395 | ||
396 | sys.exit(retcode) | |
397 | ||
398 | ||
399 | def main(argv=None): | |
400 | try: | |
401 | _real_main(argv) | |
402 | except DownloadError: | |
403 | sys.exit(1) | |
404 | except SameFileError: | |
405 | sys.exit('ERROR: fixed output name but more than one file to download') | |
406 | except KeyboardInterrupt: | |
407 | sys.exit('\nERROR: Interrupted by user') | |
408 | ||
409 | __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors'] |