import os
import subprocess
import time
+import re
from .common import AudioConversionError, PostProcessor
shell_quote,
subtitles_filename,
dfxp2srt,
+ ISO639Utils,
+ replace_extension,
)
+EXT_TO_OUT_FORMATS = {
+ 'aac': 'adts',
+ 'flac': 'flac',
+ 'm4a': 'ipod',
+ 'mka': 'matroska',
+ 'mkv': 'matroska',
+ 'mpg': 'mpeg',
+ 'ogv': 'ogg',
+ 'ts': 'mpegts',
+ 'wma': 'asf',
+ 'wmv': 'asf',
+}
+ACODECS = {
+ 'mp3': 'libmp3lame',
+ 'aac': 'aac',
+ 'flac': 'flac',
+ 'm4a': 'aac',
+ 'opus': 'libopus',
+ 'vorbis': 'libvorbis',
+ 'wav': None,
+}
+
+
class FFmpegPostProcessorError(PostProcessingError):
pass
def _determine_executables(self):
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
- prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False)
+ prefer_ffmpeg = False
self.basename = None
self.probe_basename = None
self._paths = None
self._versions = None
if self._downloader:
+ prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False)
location = self._downloader.params.get('ffmpeg_location')
if location is not None:
if not os.path.exists(location):
def probe_executable(self):
return self._paths[self.probe_basename]
+ def get_audio_codec(self, path):
+ if not self.probe_available:
+ raise PostProcessingError('ffprobe or avprobe not found. Please install one.')
+ try:
+ cmd = [
+ encodeFilename(self.probe_executable, True),
+ encodeArgument('-show_streams'),
+ encodeFilename(self._ffmpeg_filename_argument(path), True)]
+ if self._downloader.params.get('verbose', False):
+ self._downloader.to_screen('[debug] %s command line: %s' % (self.basename, shell_quote(cmd)))
+ handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE, stdin=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_multiple_files(self, input_paths, out_path, opts):
self.check_version()
oldest_mtime = min(
os.stat(encodeFilename(path)).st_mtime for path in input_paths)
+ opts += self._configuration_args()
+
files_cmd = []
for path in input_paths:
- files_cmd.extend([encodeArgument('-i'), encodeFilename(path, True)])
+ files_cmd.extend([
+ encodeArgument('-i'),
+ encodeFilename(self._ffmpeg_filename_argument(path), True)
+ ])
cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] +
files_cmd +
[encodeArgument(o) for o in 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('-'):
- return './' + fn
- return fn
+ # Always use 'file:' because the filename may contain ':' (ffmpeg
+ # interprets that as a protocol) or can start with '-' (-- is broken in
+ # ffmpeg, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details)
+ # Also leave '-' intact in order not to break streaming to stdout.
+ return 'file:' + fn if fn != '-' else fn
class FFmpegExtractAudioPP(FFmpegPostProcessor):
self._preferredquality = preferredquality
self._nopostoverwrites = nopostoverwrites
- def get_audio_codec(self, path):
-
- if not self.probe_available:
- raise PostProcessingError('ffprobe or avprobe not found. Please install one.')
- try:
- cmd = [
- encodeFilename(self.probe_executable, True),
- encodeArgument('-show_streams'),
- encodeFilename(self._ffmpeg_filename_argument(path), True)]
- if self._downloader.params.get('verbose', False):
- self._downloader.to_screen('[debug] %s command line: %s' % (self.basename, shell_quote(cmd)))
- handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE, stdin=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 codec is None:
acodec_opts = []
acodec = 'copy'
extension = 'm4a'
more_opts = ['-bsf:a', 'aac_adtstoasc']
- elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
+ elif filecodec in ['aac', 'flac', 'mp3', 'vorbis', 'opus']:
# Lossless if possible
acodec = 'copy'
extension = filecodec
else:
more_opts += ['-b:a', self._preferredquality + 'k']
else:
- # We convert the audio (lossy)
- acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
+ # We convert the audio (lossy if codec is lossy)
+ acodec = ACODECS[self._preferredcodec]
extension = self._preferredcodec
more_opts = []
if self._preferredquality is not None:
prefix, sep, ext = path.rpartition('.') # not os.path.splitext, since the latter does not work on unicode in all setups
new_path = prefix + sep + extension
+ information['filepath'] = new_path
+ information['ext'] = extension
+
# If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
if (new_path == path or
(self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
- self._downloader.to_screen('[youtube] Post-process file %s exists, skipping' % new_path)
+ self._downloader.to_screen('[ffmpeg] Post-process file %s exists, skipping' % new_path)
return [], information
try:
- self._downloader.to_screen('[' + self.basename + '] Destination: ' + new_path)
+ self._downloader.to_screen('[ffmpeg] Destination: ' + new_path)
self.run_ffmpeg(path, new_path, acodec, more_opts)
except AudioConversionError as e:
raise PostProcessingError(
new_path, time.time(), information['filetime'],
errnote='Cannot update utime of audio file')
- information['filepath'] = new_path
- information['ext'] = extension
-
return [path], information
def run(self, information):
path = information['filepath']
- prefix, sep, ext = path.rpartition('.')
- outpath = prefix + sep + self._preferedformat
if information['ext'] == self._preferedformat:
self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
return [], information
+ options = []
+ if self._preferedformat == 'avi':
+ options.extend(['-c:v', 'libxvid', '-vtag', 'XVID'])
+ prefix, sep, ext = path.rpartition('.')
+ outpath = prefix + sep + self._preferedformat
self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
- self.run_ffmpeg(path, outpath, [])
+ self.run_ffmpeg(path, outpath, options)
information['filepath'] = outpath
information['format'] = self._preferedformat
information['ext'] = self._preferedformat
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',
- }
-
- @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'] not in ['mp4', 'mkv']:
- self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 or mkv files')
+ if information['ext'] not in ('mp4', 'webm', 'mkv'):
+ self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4, webm or mkv files')
return [], information
subtitles = information.get('requested_subtitles')
if not subtitles:
self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to embed')
return [], information
- sub_langs = list(subtitles.keys())
filename = information['filepath']
- sub_filenames = [subtitles_filename(filename, lang, sub_info['ext']) for lang, sub_info in subtitles.items()]
+
+ ext = information['ext']
+ sub_langs = []
+ sub_filenames = []
+ webm_vtt_warn = False
+
+ for lang, sub_info in subtitles.items():
+ sub_ext = sub_info['ext']
+ if ext != 'webm' or ext == 'webm' and sub_ext == 'vtt':
+ sub_langs.append(lang)
+ sub_filenames.append(subtitles_filename(filename, lang, sub_ext))
+ else:
+ if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt':
+ webm_vtt_warn = True
+ self._downloader.to_screen('[ffmpeg] Only WebVTT subtitles can be embedded in webm files')
+
+ if not sub_langs:
+ return [], information
+
input_files = [filename] + sub_filenames
opts = [
opts += ['-c:s', 'mov_text']
for (i, lang) in enumerate(sub_langs):
opts.extend(['-map', '%d:0' % (i + 1)])
- lang_code = self._conver_lang_code(lang)
+ lang_code = ISO639Utils.short2long(lang)
if lang_code is not None:
opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
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('artist') is not None:
- metadata['artist'] = info['artist']
- elif info.get('uploader') is not None:
- metadata['artist'] = info['uploader']
- elif info.get('uploader_id') is not None:
- metadata['artist'] = info['uploader_id']
- if info.get('description') is not None:
- metadata['description'] = info['description']
- metadata['comment'] = info['description']
- if info.get('webpage_url') is not None:
- metadata['purl'] = info['webpage_url']
- if info.get('album') is not None:
- metadata['album'] = info['album']
+
+ def add(meta_list, info_list=None):
+ if not info_list:
+ info_list = meta_list
+ if not isinstance(meta_list, (list, tuple)):
+ meta_list = (meta_list,)
+ if not isinstance(info_list, (list, tuple)):
+ info_list = (info_list,)
+ for info_f in info_list:
+ if info.get(info_f) is not None:
+ for meta_f in meta_list:
+ metadata[meta_f] = info[info_f]
+ break
+
+ add('title', ('track', 'title'))
+ add('date', 'upload_date')
+ add(('description', 'comment'), 'description')
+ add('purl', 'webpage_url')
+ add('track', 'track_number')
+ add('artist', ('artist', 'creator', 'uploader', 'uploader_id'))
+ add('genre')
+ add('album')
+ add('album_artist')
+ add('disc', 'disc_number')
if not metadata:
self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
+ in_filenames = [filename]
+ options = []
if info['ext'] == 'm4a':
- options = ['-vn', '-acodec', 'copy']
+ options.extend(['-vn', '-acodec', 'copy'])
else:
- options = ['-c', 'copy']
+ options.extend(['-c', 'copy'])
for (name, value) in metadata.items():
options.extend(['-metadata', '%s=%s' % (name, value)])
+ chapters = info.get('chapters', [])
+ if chapters:
+ metadata_filename = replace_extension(filename, 'meta')
+ with io.open(metadata_filename, 'wt', encoding='utf-8') as f:
+ def ffmpeg_escape(text):
+ return re.sub(r'(=|;|#|\\|\n)', r'\\\1', text)
+
+ metadata_file_content = ';FFMETADATA1\n'
+ for chapter in chapters:
+ metadata_file_content += '[CHAPTER]\nTIMEBASE=1/1000\n'
+ metadata_file_content += 'START=%d\n' % (chapter['start_time'] * 1000)
+ metadata_file_content += 'END=%d\n' % (chapter['end_time'] * 1000)
+ chapter_title = chapter.get('title')
+ if chapter_title:
+ metadata_file_content += 'title=%s\n' % ffmpeg_escape(chapter_title)
+ f.write(metadata_file_content)
+ in_filenames.append(metadata_filename)
+ options.extend(['-map_metadata', '1'])
+
self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
- self.run_ffmpeg(filename, temp_filename, options)
+ self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options)
+ if chapters:
+ os.remove(metadata_filename)
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return [], info
return [], info
+class FFmpegFixupM3u8PP(FFmpegPostProcessor):
+ def run(self, info):
+ filename = info['filepath']
+ if self.get_audio_codec(filename) == 'aac':
+ temp_filename = prepend_extension(filename, 'temp')
+
+ options = ['-c', 'copy', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
+ self._downloader.to_screen('[ffmpeg] Fixing malformed AAC bitstream in "%s"' % filename)
+ self.run_ffmpeg(filename, temp_filename, options)
+
+ os.remove(encodeFilename(filename))
+ os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+ return [], info
+
+
class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
def __init__(self, downloader=None, format=None):
super(FFmpegSubtitlesConvertorPP, self).__init__(downloader)
self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to convert')
return [], info
self._downloader.to_screen('[ffmpeg] Converting subtitles')
+ sub_filenames = []
for lang, sub in subs.items():
ext = sub['ext']
if ext == new_ext:
self._downloader.to_screen(
- '[ffmpeg] Subtitle file for %s is already in the requested'
- 'format' % new_ext)
+ '[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext)
continue
+ old_file = subtitles_filename(filename, lang, ext)
+ sub_filenames.append(old_file)
new_file = subtitles_filename(filename, lang, new_ext)
- if ext == 'dfxp' or ext == 'ttml':
+ if ext in ('dfxp', 'ttml', 'tt'):
self._downloader.report_warning(
'You have requested to convert dfxp (TTML) subtitles into another format, '
'which results in style information loss')
- dfxp_file = subtitles_filename(filename, lang, ext)
+ dfxp_file = old_file
srt_file = subtitles_filename(filename, lang, 'srt')
- with io.open(dfxp_file, 'rt', encoding='utf-8') as f:
+ with open(dfxp_file, 'rb') as f:
srt_data = dfxp2srt(f.read())
with io.open(srt_file, 'wt', encoding='utf-8') as f:
f.write(srt_data)
+ old_file = srt_file
- ext = 'srt'
subs[lang] = {
'ext': 'srt',
'data': srt_data
if new_ext == 'srt':
continue
+ else:
+ sub_filenames.append(srt_file)
- self.run_ffmpeg(
- subtitles_filename(filename, lang, ext),
- new_file, ['-f', new_format])
+ self.run_ffmpeg(old_file, new_file, ['-f', new_format])
with io.open(new_file, 'rt', encoding='utf-8') as f:
subs[lang] = {
- 'ext': ext,
+ 'ext': new_ext,
'data': f.read(),
}
- return [], info
+ return sub_filenames, info
Rapsys Git / youtubedl / blobdiff