You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

481 lines
20 KiB

11 years ago
11 years ago
11 years ago
11 years ago
11 years ago
11 years ago
11 years ago
11 years ago
11 years ago
10 years ago
  1. #!/usr/bin/env python
  2. # coding: utf-8
  3. from __future__ import unicode_literals
  4. __license__ = 'Public Domain'
  5. import codecs
  6. import io
  7. import os
  8. import random
  9. import sys
  10. from .options import (
  11. parseOpts,
  12. )
  13. from .compat import (
  14. compat_getpass,
  15. compat_shlex_split,
  16. workaround_optparse_bug9161,
  17. )
  18. from .utils import (
  19. DateRange,
  20. decodeOption,
  21. DEFAULT_OUTTMPL,
  22. DownloadError,
  23. expand_path,
  24. match_filter_func,
  25. MaxDownloadsReached,
  26. preferredencoding,
  27. read_batch_urls,
  28. SameFileError,
  29. setproctitle,
  30. std_headers,
  31. write_string,
  32. render_table,
  33. )
  34. from .update import update_self
  35. from .downloader import (
  36. FileDownloader,
  37. )
  38. from .extractor import gen_extractors, list_extractors
  39. from .extractor.adobepass import MSO_INFO
  40. from .YoutubeDL import YoutubeDL
  41. def _real_main(argv=None):
  42. # Compatibility fixes for Windows
  43. if sys.platform == 'win32':
  44. # https://github.com/ytdl-org/youtube-dl/issues/820
  45. codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  46. workaround_optparse_bug9161()
  47. setproctitle('youtube-dl')
  48. parser, opts, args = parseOpts(argv)
  49. # Set user agent
  50. if opts.user_agent is not None:
  51. std_headers['User-Agent'] = opts.user_agent
  52. # Set referer
  53. if opts.referer is not None:
  54. std_headers['Referer'] = opts.referer
  55. # Custom HTTP headers
  56. if opts.headers is not None:
  57. for h in opts.headers:
  58. if ':' not in h:
  59. parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
  60. key, value = h.split(':', 1)
  61. if opts.verbose:
  62. write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
  63. std_headers[key] = value
  64. # Dump user agent
  65. if opts.dump_user_agent:
  66. write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
  67. sys.exit(0)
  68. # Batch file verification
  69. batch_urls = []
  70. if opts.batchfile is not None:
  71. try:
  72. if opts.batchfile == '-':
  73. batchfd = sys.stdin
  74. else:
  75. batchfd = io.open(
  76. expand_path(opts.batchfile),
  77. 'r', encoding='utf-8', errors='ignore')
  78. batch_urls = read_batch_urls(batchfd)
  79. if opts.verbose:
  80. write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  81. except IOError:
  82. sys.exit('ERROR: batch file could not be read')
  83. all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
  84. _enc = preferredencoding()
  85. all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
  86. if opts.list_extractors:
  87. for ie in list_extractors(opts.age_limit):
  88. write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
  89. matchedUrls = [url for url in all_urls if ie.suitable(url)]
  90. for mu in matchedUrls:
  91. write_string(' ' + mu + '\n', out=sys.stdout)
  92. sys.exit(0)
  93. if opts.list_extractor_descriptions:
  94. for ie in list_extractors(opts.age_limit):
  95. if not ie._WORKING:
  96. continue
  97. desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
  98. if desc is False:
  99. continue
  100. if hasattr(ie, 'SEARCH_KEY'):
  101. _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
  102. _COUNTS = ('', '5', '10', 'all')
  103. desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
  104. write_string(desc + '\n', out=sys.stdout)
  105. sys.exit(0)
  106. if opts.ap_list_mso:
  107. table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
  108. write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
  109. sys.exit(0)
  110. # Conflicting, missing and erroneous options
  111. if opts.usenetrc and (opts.username is not None or opts.password is not None):
  112. parser.error('using .netrc conflicts with giving username/password')
  113. if opts.password is not None and opts.username is None:
  114. parser.error('account username missing\n')
  115. if opts.ap_password is not None and opts.ap_username is None:
  116. parser.error('TV Provider account username missing\n')
  117. if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
  118. parser.error('using output template conflicts with using title, video ID or auto number')
  119. if opts.autonumber_size is not None:
  120. if opts.autonumber_size <= 0:
  121. parser.error('auto number size must be positive')
  122. if opts.autonumber_start is not None:
  123. if opts.autonumber_start < 0:
  124. parser.error('auto number start must be positive or 0')
  125. if opts.usetitle and opts.useid:
  126. parser.error('using title conflicts with using video ID')
  127. if opts.username is not None and opts.password is None:
  128. opts.password = compat_getpass('Type account password and press [Return]: ')
  129. if opts.ap_username is not None and opts.ap_password is None:
  130. opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
  131. if opts.ratelimit is not None:
  132. numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
  133. if numeric_limit is None:
  134. parser.error('invalid rate limit specified')
  135. opts.ratelimit = numeric_limit
  136. if opts.min_filesize is not None:
  137. numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
  138. if numeric_limit is None:
  139. parser.error('invalid min_filesize specified')
  140. opts.min_filesize = numeric_limit
  141. if opts.max_filesize is not None:
  142. numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
  143. if numeric_limit is None:
  144. parser.error('invalid max_filesize specified')
  145. opts.max_filesize = numeric_limit
  146. if opts.sleep_interval is not None:
  147. if opts.sleep_interval < 0:
  148. parser.error('sleep interval must be positive or 0')
  149. if opts.max_sleep_interval is not None:
  150. if opts.max_sleep_interval < 0:
  151. parser.error('max sleep interval must be positive or 0')
  152. if opts.max_sleep_interval < opts.sleep_interval:
  153. parser.error('max sleep interval must be greater than or equal to min sleep interval')
  154. else:
  155. opts.max_sleep_interval = opts.sleep_interval
  156. if opts.ap_mso and opts.ap_mso not in MSO_INFO:
  157. parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
  158. def parse_retries(retries):
  159. if retries in ('inf', 'infinite'):
  160. parsed_retries = float('inf')
  161. else:
  162. try:
  163. parsed_retries = int(retries)
  164. except (TypeError, ValueError):
  165. parser.error('invalid retry count specified')
  166. return parsed_retries
  167. if opts.retries is not None:
  168. opts.retries = parse_retries(opts.retries)
  169. if opts.fragment_retries is not None:
  170. opts.fragment_retries = parse_retries(opts.fragment_retries)
  171. if opts.buffersize is not None:
  172. numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
  173. if numeric_buffersize is None:
  174. parser.error('invalid buffer size specified')
  175. opts.buffersize = numeric_buffersize
  176. if opts.http_chunk_size is not None:
  177. numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
  178. if not numeric_chunksize:
  179. parser.error('invalid http chunk size specified')
  180. opts.http_chunk_size = numeric_chunksize
  181. if opts.playliststart <= 0:
  182. raise ValueError('Playlist start must be positive')
  183. if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
  184. raise ValueError('Playlist end must be greater than playlist start')
  185. if opts.extractaudio:
  186. if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
  187. parser.error('invalid audio format specified')
  188. if opts.audioquality:
  189. opts.audioquality = opts.audioquality.strip('k').strip('K')
  190. if not opts.audioquality.isdigit():
  191. parser.error('invalid audio quality specified')
  192. if opts.recodevideo is not None:
  193. if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
  194. parser.error('invalid video recode format specified')
  195. if opts.convertsubtitles is not None:
  196. if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
  197. parser.error('invalid subtitle format specified')
  198. if opts.date is not None:
  199. date = DateRange.day(opts.date)
  200. else:
  201. date = DateRange(opts.dateafter, opts.datebefore)
  202. # Do not download videos when there are audio-only formats
  203. if opts.extractaudio and not opts.keepvideo and opts.format is None:
  204. opts.format = 'bestaudio/best'
  205. # --all-sub automatically sets --write-sub if --write-auto-sub is not given
  206. # this was the old behaviour if only --all-sub was given.
  207. if opts.allsubtitles and not opts.writeautomaticsub:
  208. opts.writesubtitles = True
  209. outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
  210. (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
  211. (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
  212. (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
  213. (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
  214. (opts.useid and '%(id)s.%(ext)s') or
  215. (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
  216. DEFAULT_OUTTMPL)
  217. if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
  218. parser.error('Cannot download a video and extract audio into the same'
  219. ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
  220. ' template'.format(outtmpl))
  221. 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
  222. any_printing = opts.print_json
  223. download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
  224. # PostProcessors
  225. postprocessors = []
  226. if opts.metafromtitle:
  227. postprocessors.append({
  228. 'key': 'MetadataFromTitle',
  229. 'titleformat': opts.metafromtitle
  230. })
  231. if opts.extractaudio:
  232. postprocessors.append({
  233. 'key': 'FFmpegExtractAudio',
  234. 'preferredcodec': opts.audioformat,
  235. 'preferredquality': opts.audioquality,
  236. 'nopostoverwrites': opts.nopostoverwrites,
  237. })
  238. if opts.recodevideo:
  239. postprocessors.append({
  240. 'key': 'FFmpegVideoConvertor',
  241. 'preferedformat': opts.recodevideo,
  242. })
  243. # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
  244. # FFmpegExtractAudioPP as containers before conversion may not support
  245. # metadata (3gp, webm, etc.)
  246. # And this post-processor should be placed before other metadata
  247. # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
  248. # extra metadata. By default ffmpeg preserves metadata applicable for both
  249. # source and target containers. From this point the container won't change,
  250. # so metadata can be added here.
  251. if opts.addmetadata:
  252. postprocessors.append({'key': 'FFmpegMetadata'})
  253. if opts.convertsubtitles:
  254. postprocessors.append({
  255. 'key': 'FFmpegSubtitlesConvertor',
  256. 'format': opts.convertsubtitles,
  257. })
  258. if opts.embedsubtitles:
  259. postprocessors.append({
  260. 'key': 'FFmpegEmbedSubtitle',
  261. })
  262. if opts.embedthumbnail:
  263. already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
  264. postprocessors.append({
  265. 'key': 'EmbedThumbnail',
  266. 'already_have_thumbnail': already_have_thumbnail
  267. })
  268. if not already_have_thumbnail:
  269. opts.writethumbnail = True
  270. # XAttrMetadataPP should be run after post-processors that may change file
  271. # contents
  272. if opts.xattrs:
  273. postprocessors.append({'key': 'XAttrMetadata'})
  274. # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
  275. # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
  276. if opts.exec_cmd:
  277. postprocessors.append({
  278. 'key': 'ExecAfterDownload',
  279. 'exec_cmd': opts.exec_cmd,
  280. })
  281. external_downloader_args = None
  282. if opts.external_downloader_args:
  283. external_downloader_args = compat_shlex_split(opts.external_downloader_args)
  284. postprocessor_args = None
  285. if opts.postprocessor_args:
  286. postprocessor_args = compat_shlex_split(opts.postprocessor_args)
  287. match_filter = (
  288. None if opts.match_filter is None
  289. else match_filter_func(opts.match_filter))
  290. ydl_opts = {
  291. 'usenetrc': opts.usenetrc,
  292. 'username': opts.username,
  293. 'password': opts.password,
  294. 'twofactor': opts.twofactor,
  295. 'videopassword': opts.videopassword,
  296. 'ap_mso': opts.ap_mso,
  297. 'ap_username': opts.ap_username,
  298. 'ap_password': opts.ap_password,
  299. 'quiet': (opts.quiet or any_getting or any_printing),
  300. 'no_warnings': opts.no_warnings,
  301. 'forceurl': opts.geturl,
  302. 'forcetitle': opts.gettitle,
  303. 'forceid': opts.getid,
  304. 'forcethumbnail': opts.getthumbnail,
  305. 'forcedescription': opts.getdescription,
  306. 'forceduration': opts.getduration,
  307. 'forcefilename': opts.getfilename,
  308. 'forceformat': opts.getformat,
  309. 'forcejson': opts.dumpjson or opts.print_json,
  310. 'dump_single_json': opts.dump_single_json,
  311. 'simulate': opts.simulate or any_getting,
  312. 'skip_download': opts.skip_download,
  313. 'format': opts.format,
  314. 'listformats': opts.listformats,
  315. 'outtmpl': outtmpl,
  316. 'autonumber_size': opts.autonumber_size,
  317. 'autonumber_start': opts.autonumber_start,
  318. 'restrictfilenames': opts.restrictfilenames,
  319. 'ignoreerrors': opts.ignoreerrors,
  320. 'force_generic_extractor': opts.force_generic_extractor,
  321. 'ratelimit': opts.ratelimit,
  322. 'nooverwrites': opts.nooverwrites,
  323. 'retries': opts.retries,
  324. 'fragment_retries': opts.fragment_retries,
  325. 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
  326. 'keep_fragments': opts.keep_fragments,
  327. 'buffersize': opts.buffersize,
  328. 'noresizebuffer': opts.noresizebuffer,
  329. 'http_chunk_size': opts.http_chunk_size,
  330. 'continuedl': opts.continue_dl,
  331. 'noprogress': opts.noprogress,
  332. 'progress_with_newline': opts.progress_with_newline,
  333. 'playliststart': opts.playliststart,
  334. 'playlistend': opts.playlistend,
  335. 'playlistreverse': opts.playlist_reverse,
  336. 'playlistrandom': opts.playlist_random,
  337. 'noplaylist': opts.noplaylist,
  338. 'logtostderr': opts.outtmpl == '-',
  339. 'consoletitle': opts.consoletitle,
  340. 'nopart': opts.nopart,
  341. 'updatetime': opts.updatetime,
  342. 'writedescription': opts.writedescription,
  343. 'writeannotations': opts.writeannotations,
  344. 'writeinfojson': opts.writeinfojson,
  345. 'writethumbnail': opts.writethumbnail,
  346. 'write_all_thumbnails': opts.write_all_thumbnails,
  347. 'writesubtitles': opts.writesubtitles,
  348. 'writeautomaticsub': opts.writeautomaticsub,
  349. 'allsubtitles': opts.allsubtitles,
  350. 'listsubtitles': opts.listsubtitles,
  351. 'subtitlesformat': opts.subtitlesformat,
  352. 'subtitleslangs': opts.subtitleslangs,
  353. 'matchtitle': decodeOption(opts.matchtitle),
  354. 'rejecttitle': decodeOption(opts.rejecttitle),
  355. 'max_downloads': opts.max_downloads,
  356. 'prefer_free_formats': opts.prefer_free_formats,
  357. 'verbose': opts.verbose,
  358. 'dump_intermediate_pages': opts.dump_intermediate_pages,
  359. 'write_pages': opts.write_pages,
  360. 'test': opts.test,
  361. 'keepvideo': opts.keepvideo,
  362. 'min_filesize': opts.min_filesize,
  363. 'max_filesize': opts.max_filesize,
  364. 'min_views': opts.min_views,
  365. 'max_views': opts.max_views,
  366. 'daterange': date,
  367. 'cachedir': opts.cachedir,
  368. 'youtube_print_sig_code': opts.youtube_print_sig_code,
  369. 'age_limit': opts.age_limit,
  370. 'download_archive': download_archive_fn,
  371. 'cookiefile': opts.cookiefile,
  372. 'nocheckcertificate': opts.no_check_certificate,
  373. 'prefer_insecure': opts.prefer_insecure,
  374. 'proxy': opts.proxy,
  375. 'socket_timeout': opts.socket_timeout,
  376. 'bidi_workaround': opts.bidi_workaround,
  377. 'debug_printtraffic': opts.debug_printtraffic,
  378. 'prefer_ffmpeg': opts.prefer_ffmpeg,
  379. 'include_ads': opts.include_ads,
  380. 'default_search': opts.default_search,
  381. 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
  382. 'encoding': opts.encoding,
  383. 'extract_flat': opts.extract_flat,
  384. 'mark_watched': opts.mark_watched,
  385. 'merge_output_format': opts.merge_output_format,
  386. 'postprocessors': postprocessors,
  387. 'fixup': opts.fixup,
  388. 'source_address': opts.source_address,
  389. 'call_home': opts.call_home,
  390. 'sleep_interval': opts.sleep_interval,
  391. 'max_sleep_interval': opts.max_sleep_interval,
  392. 'external_downloader': opts.external_downloader,
  393. 'list_thumbnails': opts.list_thumbnails,
  394. 'playlist_items': opts.playlist_items,
  395. 'xattr_set_filesize': opts.xattr_set_filesize,
  396. 'match_filter': match_filter,
  397. 'no_color': opts.no_color,
  398. 'ffmpeg_location': opts.ffmpeg_location,
  399. 'hls_prefer_native': opts.hls_prefer_native,
  400. 'hls_use_mpegts': opts.hls_use_mpegts,
  401. 'external_downloader_args': external_downloader_args,
  402. 'postprocessor_args': postprocessor_args,
  403. 'cn_verification_proxy': opts.cn_verification_proxy,
  404. 'geo_verification_proxy': opts.geo_verification_proxy,
  405. 'config_location': opts.config_location,
  406. 'geo_bypass': opts.geo_bypass,
  407. 'geo_bypass_country': opts.geo_bypass_country,
  408. 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
  409. # just for deprecation check
  410. 'autonumber': opts.autonumber if opts.autonumber is True else None,
  411. 'usetitle': opts.usetitle if opts.usetitle is True else None,
  412. }
  413. with YoutubeDL(ydl_opts) as ydl:
  414. # Update version
  415. if opts.update_self:
  416. update_self(ydl.to_screen, opts.verbose, ydl._opener)
  417. # Remove cache dir
  418. if opts.rm_cachedir:
  419. ydl.cache.remove()
  420. # Maybe do nothing
  421. if (len(all_urls) < 1) and (opts.load_info_filename is None):
  422. if opts.update_self or opts.rm_cachedir:
  423. sys.exit()
  424. ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
  425. parser.error(
  426. 'You must provide at least one URL.\n'
  427. 'Type youtube-dl --help to see a list of all options.')
  428. try:
  429. if opts.load_info_filename is not None:
  430. retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
  431. else:
  432. retcode = ydl.download(all_urls)
  433. except MaxDownloadsReached:
  434. ydl.to_screen('--max-download limit reached, aborting.')
  435. retcode = 101
  436. sys.exit(retcode)
  437. def main(argv=None):
  438. try:
  439. _real_main(argv)
  440. except DownloadError:
  441. sys.exit(1)
  442. except SameFileError:
  443. sys.exit('ERROR: fixed output name but more than one file to download')
  444. except KeyboardInterrupt:
  445. sys.exit('\nERROR: Interrupted by user')
  446. __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']