2 # -*- coding: utf-8 -*-
4 from __future__ import absolute_import
25 compat_urllib_request,
41 UnavailableVideoError,
45 from .extractor import get_info_extractor, gen_extractors
46 from .FileDownloader import FileDownloader
49 class YoutubeDL(object):
52 YoutubeDL objects are the ones responsible of downloading the
53 actual video file and writing it to disk if the user has requested
54 it, among some other tasks. In most cases there should be one per
55 program. As, given a video URL, the downloader doesn't know how to
56 extract all the needed information, task that InfoExtractors do, it
57 has to pass the URL to one of them.
59 For this, YoutubeDL objects have a method that allows
60 InfoExtractors to be registered in a given order. When it is passed
61 a URL, the YoutubeDL object handles it to the first InfoExtractor it
62 finds that reports being able to handle it. The InfoExtractor extracts
63 all the information about the video or videos the URL refers to, and
64 YoutubeDL process the extracted information, possibly using a File
65 Downloader to download the video.
67 YoutubeDL objects accept a lot of parameters. In order not to saturate
68 the object constructor with arguments, it receives a dictionary of
69 options instead. These options are available through the params
70 attribute for the InfoExtractors to use. The YoutubeDL also
71 registers itself as the downloader in charge for the InfoExtractors
72 that are added to it, so this is a "mutual registration".
76 username: Username for authentication purposes.
77 password: Password for authentication purposes.
78 videopassword: Password for acces a video.
79 usenetrc: Use netrc for authentication instead.
80 verbose: Print additional info to stdout.
81 quiet: Do not print messages to stdout.
82 forceurl: Force printing final URL.
83 forcetitle: Force printing title.
84 forceid: Force printing ID.
85 forcethumbnail: Force printing thumbnail URL.
86 forcedescription: Force printing description.
87 forcefilename: Force printing final filename.
88 forcejson: Force printing info_dict as JSON.
89 simulate: Do not download the video files.
90 format: Video format code.
91 format_limit: Highest quality format to try.
92 outtmpl: Template for output names.
93 restrictfilenames: Do not allow "&" and spaces in file names
94 ignoreerrors: Do not stop on download errors.
95 nooverwrites: Prevent overwriting files.
96 playliststart: Playlist item to start at.
97 playlistend: Playlist item to end at.
98 matchtitle: Download only matching titles.
99 rejecttitle: Reject downloads for matching titles.
100 logtostderr: Log messages to stderr instead of stdout.
101 writedescription: Write the video description to a .description file
102 writeinfojson: Write the video description to a .info.json file
103 writeannotations: Write the video annotations to a .annotations.xml file
104 writethumbnail: Write the thumbnail image to a file
105 writesubtitles: Write the video subtitles to a file
106 writeautomaticsub: Write the automatic subtitles to a file
107 allsubtitles: Downloads all the subtitles of the video
108 (requires writesubtitles or writeautomaticsub)
109 listsubtitles: Lists all available subtitles for the video
110 subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt)
111 subtitleslangs: List of languages of the subtitles to download
112 keepvideo: Keep the video file after post-processing
113 daterange: A DateRange object, download only if the upload_date is in the range.
114 skip_download: Skip the actual download of the video file
115 cachedir: Location of the cache files in the filesystem.
116 None to disable filesystem cache.
117 noplaylist: Download single video instead of a playlist if in doubt.
118 age_limit: An integer representing the user's age in years.
119 Unsuitable videos for the given age are skipped.
120 downloadarchive: File name of a file where all downloads are recorded.
121 Videos already present in the file are not downloaded
124 The following parameters are not used by YoutubeDL itself, they are used by
126 nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
127 noresizebuffer, retries, continuedl, noprogress, consoletitle
133 _download_retcode = None
134 _num_downloads = None
137 def __init__(self, params):
138 """Create a FileDownloader object with the given options."""
140 self._ies_instances = {}
142 self._progress_hooks = []
143 self._download_retcode = 0
144 self._num_downloads = 0
145 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
147 if (sys.version_info >= (3,) and sys.platform != 'win32' and
148 sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
149 and not params['restrictfilenames']):
150 # On Python 3, the Unicode filesystem API will throw errors (#1474)
152 u'Assuming --restrict-filenames since file system encoding '
153 u'cannot encode all charactes. '
154 u'Set the LC_ALL environment variable to fix this.')
155 params['restrictfilenames'] = True
158 self.fd = FileDownloader(self, self.params)
160 if '%(stitle)s' in self.params['outtmpl']:
161 self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
163 def add_info_extractor(self, ie):
164 """Add an InfoExtractor object to the end of the list."""
166 self._ies_instances[ie.ie_key()] = ie
167 ie.set_downloader(self)
169 def get_info_extractor(self, ie_key):
171 Get an instance of an IE with name ie_key, it will try to get one from
172 the _ies list, if there's no instance it will create a new one and add
173 it to the extractor list.
175 ie = self._ies_instances.get(ie_key)
177 ie = get_info_extractor(ie_key)()
178 self.add_info_extractor(ie)
181 def add_default_info_extractors(self):
183 Add the InfoExtractors returned by gen_extractors to the end of the list
185 for ie in gen_extractors():
186 self.add_info_extractor(ie)
188 def add_post_processor(self, pp):
189 """Add a PostProcessor object to the end of the chain."""
191 pp.set_downloader(self)
193 def to_screen(self, message, skip_eol=False):
194 """Print message to stdout if not in quiet mode."""
195 if not self.params.get('quiet', False):
196 terminator = [u'\n', u''][skip_eol]
197 output = message + terminator
198 write_string(output, self._screen_file)
200 def to_stderr(self, message):
201 """Print message to stderr."""
202 assert type(message) == type(u'')
203 output = message + u'\n'
204 if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
205 output = output.encode(preferredencoding())
206 sys.stderr.write(output)
208 def to_console_title(self, message):
209 if not self.params.get('consoletitle', False):
211 if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
212 # c_wchar_p() might not be necessary if `message` is
213 # already of type unicode()
214 ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
215 elif 'TERM' in os.environ:
216 write_string(u'\033]0;%s\007' % message, self._screen_file)
218 def save_console_title(self):
219 if not self.params.get('consoletitle', False):
221 if 'TERM' in os.environ:
222 # Save the title on stack
223 write_string(u'\033[22;0t', self._screen_file)
225 def restore_console_title(self):
226 if not self.params.get('consoletitle', False):
228 if 'TERM' in os.environ:
229 # Restore the title from stack
230 write_string(u'\033[23;0t', self._screen_file)
233 self.save_console_title()
236 def __exit__(self, *args):
237 self.restore_console_title()
239 def fixed_template(self):
240 """Checks if the output template is fixed."""
241 return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
243 def trouble(self, message=None, tb=None):
244 """Determine action to take when a download problem appears.
246 Depending on if the downloader has been configured to ignore
247 download errors or not, this method may throw an exception or
248 not when errors are found, after printing the message.
250 tb, if given, is additional traceback information.
252 if message is not None:
253 self.to_stderr(message)
254 if self.params.get('verbose'):
256 if sys.exc_info()[0]: # if .trouble has been called from an except block
258 if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
259 tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
260 tb += compat_str(traceback.format_exc())
262 tb_data = traceback.format_list(traceback.extract_stack())
263 tb = u''.join(tb_data)
265 if not self.params.get('ignoreerrors', False):
266 if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
267 exc_info = sys.exc_info()[1].exc_info
269 exc_info = sys.exc_info()
270 raise DownloadError(message, exc_info)
271 self._download_retcode = 1
273 def report_warning(self, message):
275 Print the message to stderr, it will be prefixed with 'WARNING:'
276 If stderr is a tty file the 'WARNING:' will be colored
278 if sys.stderr.isatty() and os.name != 'nt':
279 _msg_header = u'\033[0;33mWARNING:\033[0m'
281 _msg_header = u'WARNING:'
282 warning_message = u'%s %s' % (_msg_header, message)
283 self.to_stderr(warning_message)
285 def report_error(self, message, tb=None):
287 Do the same as trouble, but prefixes the message with 'ERROR:', colored
288 in red if stderr is a tty file.
290 if sys.stderr.isatty() and os.name != 'nt':
291 _msg_header = u'\033[0;31mERROR:\033[0m'
293 _msg_header = u'ERROR:'
294 error_message = u'%s %s' % (_msg_header, message)
295 self.trouble(error_message, tb)
297 def report_writedescription(self, descfn):
298 """ Report that the description file is being written """
299 self.to_screen(u'[info] Writing video description to: ' + descfn)
301 def report_writesubtitles(self, sub_filename):
302 """ Report that the subtitles file is being written """
303 self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
305 def report_writeinfojson(self, infofn):
306 """ Report that the metadata file has been written """
307 self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
309 def report_writeannotations(self, annofn):
310 """ Report that the annotations file has been written. """
311 self.to_screen(u'[info] Writing video annotations to: ' + annofn)
313 def report_file_already_downloaded(self, file_name):
314 """Report file has already been fully downloaded."""
316 self.to_screen(u'[download] %s has already been downloaded' % file_name)
317 except UnicodeEncodeError:
318 self.to_screen(u'[download] The file has already been downloaded')
320 def increment_downloads(self):
321 """Increment the ordinal that assigns a number to each file."""
322 self._num_downloads += 1
324 def prepare_filename(self, info_dict):
325 """Generate the output filename."""
327 template_dict = dict(info_dict)
329 template_dict['epoch'] = int(time.time())
330 autonumber_size = self.params.get('autonumber_size')
331 if autonumber_size is None:
333 autonumber_templ = u'%0' + str(autonumber_size) + u'd'
334 template_dict['autonumber'] = autonumber_templ % self._num_downloads
335 if template_dict.get('playlist_index') is not None:
336 template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index']
338 sanitize = lambda k, v: sanitize_filename(
339 u'NA' if v is None else compat_str(v),
340 restricted=self.params.get('restrictfilenames'),
342 template_dict = dict((k, sanitize(k, v))
343 for k, v in template_dict.items())
345 tmpl = os.path.expanduser(self.params['outtmpl'])
346 filename = tmpl % template_dict
348 except KeyError as err:
349 self.report_error(u'Erroneous output template')
351 except ValueError as err:
352 self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')')
355 def _match_entry(self, info_dict):
356 """ Returns None iff the file should be downloaded """
358 if 'title' in info_dict:
359 # This can happen when we're just evaluating the playlist
360 title = info_dict['title']
361 matchtitle = self.params.get('matchtitle', False)
363 if not re.search(matchtitle, title, re.IGNORECASE):
364 return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
365 rejecttitle = self.params.get('rejecttitle', False)
367 if re.search(rejecttitle, title, re.IGNORECASE):
368 return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
369 date = info_dict.get('upload_date', None)
371 dateRange = self.params.get('daterange', DateRange())
372 if date not in dateRange:
373 return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
374 age_limit = self.params.get('age_limit')
375 if age_limit is not None:
376 if age_limit < info_dict.get('age_limit', 0):
377 return u'Skipping "' + title + '" because it is age restricted'
378 if self.in_download_archive(info_dict):
379 return (u'%s has already been recorded in archive'
380 % info_dict.get('title', info_dict.get('id', u'video')))
384 def add_extra_info(info_dict, extra_info):
385 '''Set the keys from extra_info in info dict if they are missing'''
386 for key, value in extra_info.items():
387 info_dict.setdefault(key, value)
389 def extract_info(self, url, download=True, ie_key=None, extra_info={}):
391 Returns a list with a dictionary for each video we find.
392 If 'download', also downloads the videos.
393 extra_info is a dict containing the extra values to add to each result
397 ies = [self.get_info_extractor(ie_key)]
402 if not ie.suitable(url):
406 self.report_warning(u'The program functionality for this site has been marked as broken, '
407 u'and will probably not work.')
410 ie_result = ie.extract(url)
411 if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
413 if isinstance(ie_result, list):
414 # Backwards compatibility: old IE result format
416 '_type': 'compat_list',
417 'entries': ie_result,
419 self.add_extra_info(ie_result,
421 'extractor': ie.IE_NAME,
423 'extractor_key': ie.ie_key(),
425 return self.process_ie_result(ie_result, download, extra_info)
426 except ExtractorError as de: # An error we somewhat expected
427 self.report_error(compat_str(de), de.format_traceback())
429 except Exception as e:
430 if self.params.get('ignoreerrors', False):
431 self.report_error(compat_str(e), tb=compat_str(traceback.format_exc()))
436 self.report_error(u'no suitable InfoExtractor: %s' % url)
438 def process_ie_result(self, ie_result, download=True, extra_info={}):
440 Take the result of the ie(may be modified) and resolve all unresolved
441 references (URLs, playlist items).
443 It will also download the videos if 'download'.
444 Returns the resolved ie_result.
447 result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
448 if result_type == 'video':
449 self.add_extra_info(ie_result, extra_info)
450 return self.process_video_result(ie_result, download=download)
451 elif result_type == 'url':
452 # We have to add extra_info to the results because it may be
453 # contained in a playlist
454 return self.extract_info(ie_result['url'],
456 ie_key=ie_result.get('ie_key'),
457 extra_info=extra_info)
458 elif result_type == 'playlist':
460 # We process each entry in the playlist
461 playlist = ie_result.get('title', None) or ie_result.get('id', None)
462 self.to_screen(u'[download] Downloading playlist: %s' % playlist)
464 playlist_results = []
466 n_all_entries = len(ie_result['entries'])
467 playliststart = self.params.get('playliststart', 1) - 1
468 playlistend = self.params.get('playlistend', -1)
470 if playlistend == -1:
471 entries = ie_result['entries'][playliststart:]
473 entries = ie_result['entries'][playliststart:playlistend]
475 n_entries = len(entries)
477 self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
478 (ie_result['extractor'], playlist, n_all_entries, n_entries))
480 for i, entry in enumerate(entries, 1):
481 self.to_screen(u'[download] Downloading video #%s of %s' % (i, n_entries))
483 'playlist': playlist,
484 'playlist_index': i + playliststart,
485 'extractor': ie_result['extractor'],
486 'webpage_url': ie_result['webpage_url'],
487 'extractor_key': ie_result['extractor_key'],
490 reason = self._match_entry(entry)
491 if reason is not None:
492 self.to_screen(u'[download] ' + reason)
495 entry_result = self.process_ie_result(entry,
498 playlist_results.append(entry_result)
499 ie_result['entries'] = playlist_results
501 elif result_type == 'compat_list':
503 self.add_extra_info(r,
505 'extractor': ie_result['extractor'],
506 'webpage_url': ie_result['webpage_url'],
507 'extractor_key': ie_result['extractor_key'],
510 ie_result['entries'] = [
511 self.process_ie_result(_fixup(r), download, extra_info)
512 for r in ie_result['entries']
516 raise Exception('Invalid result type: %s' % result_type)
518 def select_format(self, format_spec, available_formats):
519 if format_spec == 'best' or format_spec is None:
520 return available_formats[-1]
521 elif format_spec == 'worst':
522 return available_formats[0]
524 extensions = [u'mp4', u'flv', u'webm', u'3gp']
525 if format_spec in extensions:
526 filter_f = lambda f: f['ext'] == format_spec
528 filter_f = lambda f: f['format_id'] == format_spec
529 matches = list(filter(filter_f, available_formats))
534 def process_video_result(self, info_dict, download=True):
535 assert info_dict.get('_type', 'video') == 'video'
537 if 'playlist' not in info_dict:
538 # It isn't part of a playlist
539 info_dict['playlist'] = None
540 info_dict['playlist_index'] = None
542 # This extractors handle format selection themselves
543 if info_dict['extractor'] in [u'youtube', u'Youku']:
545 self.process_info(info_dict)
548 # We now pick which formats have to be downloaded
549 if info_dict.get('formats') is None:
550 # There's only one format available
551 formats = [info_dict]
553 formats = info_dict['formats']
555 # We check that all the formats have the format and format_id fields
556 for (i, format) in enumerate(formats):
557 if format.get('format_id') is None:
558 format['format_id'] = compat_str(i)
559 if format.get('format') is None:
560 format['format'] = u'{id} - {res}{note}'.format(
561 id=format['format_id'],
562 res=self.format_resolution(format),
563 note=u' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '',
565 # Automatically determine file extension if missing
566 if 'ext' not in format:
567 format['ext'] = determine_ext(format['url'])
569 if self.params.get('listformats', None):
570 self.list_formats(info_dict)
573 format_limit = self.params.get('format_limit', None)
575 formats = list(takewhile_inclusive(
576 lambda f: f['format_id'] != format_limit, formats
578 if self.params.get('prefer_free_formats'):
579 def _free_formats_key(f):
581 ext_ord = [u'flv', u'mp4', u'webm'].index(f['ext'])
584 # We only compare the extension if they have the same height and width
585 return (f.get('height'), f.get('width'), ext_ord)
586 formats = sorted(formats, key=_free_formats_key)
588 req_format = self.params.get('format', 'best')
589 if req_format is None:
591 formats_to_download = []
592 # The -1 is for supporting YoutubeIE
593 if req_format in ('-1', 'all'):
594 formats_to_download = formats
596 # We can accept formats requestd in the format: 34/5/best, we pick
597 # the first that is available, starting from left
598 req_formats = req_format.split('/')
599 for rf in req_formats:
600 selected_format = self.select_format(rf, formats)
601 if selected_format is not None:
602 formats_to_download = [selected_format]
604 if not formats_to_download:
605 raise ExtractorError(u'requested format not available',
609 if len(formats_to_download) > 1:
610 self.to_screen(u'[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download)))
611 for format in formats_to_download:
612 new_info = dict(info_dict)
613 new_info.update(format)
614 self.process_info(new_info)
615 # We update the info dict with the best quality format (backwards compatibility)
616 info_dict.update(formats_to_download[-1])
619 def process_info(self, info_dict):
620 """Process a single resolved IE result."""
622 assert info_dict.get('_type', 'video') == 'video'
623 #We increment the download the download count here to match the previous behaviour.
624 self.increment_downloads()
626 info_dict['fulltitle'] = info_dict['title']
627 if len(info_dict['title']) > 200:
628 info_dict['title'] = info_dict['title'][:197] + u'...'
630 # Keep for backwards compatibility
631 info_dict['stitle'] = info_dict['title']
633 if not 'format' in info_dict:
634 info_dict['format'] = info_dict['ext']
636 reason = self._match_entry(info_dict)
637 if reason is not None:
638 self.to_screen(u'[download] ' + reason)
641 max_downloads = self.params.get('max_downloads')
642 if max_downloads is not None:
643 if self._num_downloads > int(max_downloads):
644 raise MaxDownloadsReached()
646 filename = self.prepare_filename(info_dict)
649 if self.params.get('forcetitle', False):
650 compat_print(info_dict['fulltitle'])
651 if self.params.get('forceid', False):
652 compat_print(info_dict['id'])
653 if self.params.get('forceurl', False):
654 # For RTMP URLs, also include the playpath
655 compat_print(info_dict['url'] + info_dict.get('play_path', u''))
656 if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
657 compat_print(info_dict['thumbnail'])
658 if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
659 compat_print(info_dict['description'])
660 if self.params.get('forcefilename', False) and filename is not None:
661 compat_print(filename)
662 if self.params.get('forceformat', False):
663 compat_print(info_dict['format'])
664 if self.params.get('forcejson', False):
665 compat_print(json.dumps(info_dict))
667 # Do nothing else if in simulate mode
668 if self.params.get('simulate', False):
675 dn = os.path.dirname(encodeFilename(filename))
676 if dn != '' and not os.path.exists(dn):
678 except (OSError, IOError) as err:
679 self.report_error(u'unable to create directory ' + compat_str(err))
682 if self.params.get('writedescription', False):
684 descfn = filename + u'.description'
685 self.report_writedescription(descfn)
686 with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
687 descfile.write(info_dict['description'])
688 except (KeyError, TypeError):
689 self.report_warning(u'There\'s no description to write.')
690 except (OSError, IOError):
691 self.report_error(u'Cannot write description file ' + descfn)
694 if self.params.get('writeannotations', False):
696 annofn = filename + u'.annotations.xml'
697 self.report_writeannotations(annofn)
698 with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
699 annofile.write(info_dict['annotations'])
700 except (KeyError, TypeError):
701 self.report_warning(u'There are no annotations to write.')
702 except (OSError, IOError):
703 self.report_error(u'Cannot write annotations file: ' + annofn)
706 subtitles_are_requested = any([self.params.get('writesubtitles', False),
707 self.params.get('writeautomaticsub')])
709 if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
710 # subtitles download errors are already managed as troubles in relevant IE
711 # that way it will silently go on when used with unsupporting IE
712 subtitles = info_dict['subtitles']
713 sub_format = self.params.get('subtitlesformat', 'srt')
714 for sub_lang in subtitles.keys():
715 sub = subtitles[sub_lang]
719 sub_filename = subtitles_filename(filename, sub_lang, sub_format)
720 self.report_writesubtitles(sub_filename)
721 with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
723 except (OSError, IOError):
724 self.report_error(u'Cannot write subtitles file ' + descfn)
727 if self.params.get('writeinfojson', False):
728 infofn = os.path.splitext(filename)[0] + u'.info.json'
729 self.report_writeinfojson(infofn)
731 json_info_dict = dict((k, v) for k, v in info_dict.items() if not k in ['urlhandle'])
732 write_json_file(json_info_dict, encodeFilename(infofn))
733 except (OSError, IOError):
734 self.report_error(u'Cannot write metadata to JSON file ' + infofn)
737 if self.params.get('writethumbnail', False):
738 if info_dict.get('thumbnail') is not None:
739 thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
740 thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
741 self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
742 (info_dict['extractor'], info_dict['id']))
744 uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
745 with open(thumb_filename, 'wb') as thumbf:
746 shutil.copyfileobj(uf, thumbf)
747 self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
748 (info_dict['extractor'], info_dict['id'], thumb_filename))
749 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
750 self.report_warning(u'Unable to download thumbnail "%s": %s' %
751 (info_dict['thumbnail'], compat_str(err)))
753 if not self.params.get('skip_download', False):
754 if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
758 success = self.fd._do_download(filename, info_dict)
759 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
760 self.report_error(u'unable to download video data: %s' % str(err))
762 except (OSError, IOError) as err:
763 raise UnavailableVideoError(err)
764 except (ContentTooShortError, ) as err:
765 self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
770 self.post_process(filename, info_dict)
771 except (PostProcessingError) as err:
772 self.report_error(u'postprocessing: %s' % str(err))
775 self.record_download_archive(info_dict)
777 def download(self, url_list):
778 """Download a given list of URLs."""
779 if len(url_list) > 1 and self.fixed_template():
780 raise SameFileError(self.params['outtmpl'])
784 #It also downloads the videos
785 videos = self.extract_info(url)
786 except UnavailableVideoError:
787 self.report_error(u'unable to download video')
788 except MaxDownloadsReached:
789 self.to_screen(u'[info] Maximum number of downloaded files reached.')
792 return self._download_retcode
794 def post_process(self, filename, ie_info):
795 """Run all the postprocessors on the given file."""
797 info['filepath'] = filename
801 keep_video_wish, new_info = pp.run(info)
802 if keep_video_wish is not None:
804 keep_video = keep_video_wish
805 elif keep_video is None:
806 # No clear decision yet, let IE decide
807 keep_video = keep_video_wish
808 except PostProcessingError as e:
809 self.report_error(e.msg)
810 if keep_video is False and not self.params.get('keepvideo', False):
812 self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename)
813 os.remove(encodeFilename(filename))
814 except (IOError, OSError):
815 self.report_warning(u'Unable to remove downloaded video file')
817 def in_download_archive(self, info_dict):
818 fn = self.params.get('download_archive')
821 extractor = info_dict.get('extractor_id')
822 if extractor is None:
823 if 'id' in info_dict:
824 extractor = info_dict.get('ie_key') # key in a playlist
825 if extractor is None:
826 return False # Incomplete video information
827 # Future-proof against any change in case
828 # and backwards compatibility with prior versions
829 extractor = extractor.lower()
830 vid_id = extractor + u' ' + info_dict['id']
832 with locked_file(fn, 'r', encoding='utf-8') as archive_file:
833 for line in archive_file:
834 if line.strip() == vid_id:
836 except IOError as ioe:
837 if ioe.errno != errno.ENOENT:
841 def record_download_archive(self, info_dict):
842 fn = self.params.get('download_archive')
845 vid_id = info_dict['extractor'] + u' ' + info_dict['id']
846 with locked_file(fn, 'a', encoding='utf-8') as archive_file:
847 archive_file.write(vid_id + u'\n')
850 def format_resolution(format, default='unknown'):
851 if format.get('_resolution') is not None:
852 return format['_resolution']
853 if format.get('height') is not None:
854 if format.get('width') is not None:
855 res = u'%sx%s' % (format['width'], format['height'])
857 res = u'%sp' % format['height']
862 def list_formats(self, info_dict):
863 def format_note(fdict):
864 if fdict.get('format_note') is not None:
865 return fdict['format_note']
867 if fdict.get('vcodec') is not None:
868 res += u'%-5s' % fdict['vcodec']
869 elif fdict.get('vbr') is not None:
871 if fdict.get('vbr') is not None:
872 res += u'@%4dk' % fdict['vbr']
873 if fdict.get('acodec') is not None:
876 res += u'%-5s' % fdict['acodec']
877 elif fdict.get('abr') is not None:
881 if fdict.get('abr') is not None:
882 res += u'@%3dk' % fdict['abr']
886 return (u'%-20s%-10s%-12s%s' % (
889 self.format_resolution(format),
894 formats = info_dict.get('formats', [info_dict])
895 formats_s = list(map(line, formats))
897 formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)'
898 formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
901 'format_id': u'format code', 'ext': u'extension',
902 '_resolution': u'resolution', 'format_note': u'note'})
903 self.to_screen(u'[info] Available formats for %s:\n%s\n%s' %
904 (info_dict['id'], header_line, u"\n".join(formats_s)))