Skip to content

Handle auto-dubbed audio tracks #242

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
powellnorma wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Handle auto-dubbed audio tracks #242

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
102d92e
Handle auto-dubbed audio tracks
powellnorma Aug 24, 2025
0ef4046
Handle auto-dubbed audio tracks - 2
powellnorma Aug 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,6 +224,24 @@
'category': 'interface',
}),

## mine
('disable_dubbing', {
'label': 'Disable dubbing',
'type': bool,
'default': True,
'comment': '''Allows only original audio track''',
'category': 'interface',
}),
## mine
('allowed_dubbing_languages', {
'label': 'Allowed dubbing languages',
'type': str,
'default': 'English;Russian',
'comment': '''Allows dubbing for listed languages''',
'category': 'interface',
}),


('video_player', {
'type': int,
'default': 1,
Expand Down
116 changes: 72 additions & 44 deletions youtube/watch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,65 +104,93 @@ def get_video_sources(info, target_resolution):
audio_sources.sort(key=lambda source: source['audio_bitrate'])
uni_sources.sort(key=lambda src: src['quality'])

webm_audios = [a for a in audio_sources if a['ext'] == 'webm']
mp4_audios = [a for a in audio_sources if a['ext'] == 'mp4']

for quality_string, sources in video_only_sources.items():
# choose an audio source to go with it
# 0.5 is semiarbitrary empirical constant to spread audio sources
# between 144p and 1080p. Use something better eventually.
quality, fps = map(int, quality_string.split('p'))
target_audio_bitrate = quality*fps/30*0.5
pair_info = {
'quality_string': quality_string,
'quality': quality,
'height': sources[0]['height'],
'width': sources[0]['width'],
'fps': fps,
'videos': sources,
'audios': [],
}
for audio_choices in (webm_audios, mp4_audios):
if not audio_choices:
################################################################################## mine
# for multi tracks
res = {}
# group dicts by audio_track key
for item1 in audio_sources:
if item1['audio_track'] not in res:
res[item1['audio_track']] = []
res[item1['audio_track']].append(item1)

for k_lang, v_lang in res.items():
k_lang_ = "" if k_lang == 'undefined' else " " + k_lang

webm_audios = [a for a in v_lang if a['ext'] == 'webm']
mp4_audios = [a for a in v_lang if a['ext'] == 'mp4']

for quality_string, sources in video_only_sources.items():
# choose an audio source to go with it
# 0.5 is semiarbitrary empirical constant to spread audio sources
# between 144p and 1080p. Use something better eventually.
quality, fps = map(int, quality_string.split('p'))
target_audio_bitrate = quality*fps/30*0.5
pair_info = {
'quality_string': quality_string + k_lang_, # mine
'quality': quality,
'height': sources[0]['height'],
'width': sources[0]['width'],
'fps': fps,
'videos': sources,
'audios': [],
}
for audio_choices in (webm_audios, mp4_audios):
if not audio_choices:
continue
closest_audio_source = audio_choices[0]
best_err = target_audio_bitrate - audio_choices[0]['audio_bitrate']
best_err = abs(best_err)
for audio_source in audio_choices[1:]:
err = abs(audio_source['audio_bitrate'] - target_audio_bitrate)
# once err gets worse we have passed the closest one
if err > best_err:
break
best_err = err
closest_audio_source = audio_source
pair_info['audios'].append(closest_audio_source)

if not pair_info['audios']:
continue
closest_audio_source = audio_choices[0]
best_err = target_audio_bitrate - audio_choices[0]['audio_bitrate']
best_err = abs(best_err)
for audio_source in audio_choices[1:]:
err = abs(audio_source['audio_bitrate'] - target_audio_bitrate)
# once err gets worse we have passed the closest one
if err > best_err:
break
best_err = err
closest_audio_source = audio_source
pair_info['audios'].append(closest_audio_source)

if not pair_info['audios']:
continue

def video_rank(src):
''' Sort by settings preference. Use file size as tiebreaker '''
setting_name = 'codec_rank_' + codec_name(src['vcodec'])
return (settings.current_settings_dict[setting_name],
src['file_size'])
pair_info['videos'].sort(key=video_rank)
def video_rank(src):
''' Sort by settings preference. Use file size as tiebreaker '''
setting_name = 'codec_rank_' + codec_name(src['vcodec'])
return (settings.current_settings_dict[setting_name],
src['file_size'])
pair_info['videos'].sort(key=video_rank)

pair_sources.append(pair_info)
pair_sources.append(pair_info)

pair_sources.sort(key=lambda src: src['quality_string'])
pair_sources.sort(key=lambda src: src['quality'])

# if file_size is none for some videos url not work
# if clen is none for some videos url works
uni_sources1 = []
for u in uni_sources:
if u['file_size'] != None: uni_sources1.append(u)
elif u['file_size'] == None and u['clen'] == None: uni_sources1.append(u)
uni_sources = uni_sources1[:]

uni_idx = 0 if uni_sources else None
for i, source in enumerate(uni_sources):
if source['quality'] > target_resolution:
break
uni_idx = i

# need original track as default
pair_idx = 0 if pair_sources else None
for i, pair_info in enumerate(pair_sources):
if pair_info['quality'] > target_resolution:
break
if 'undefined' not in pair_info['audios'][0]['audio_track']: continue
if pair_info['quality'] > target_resolution: break
pair_idx = i

# if pair_idx is bigger than pair_sources list size
# try: _ = pair_sources[pair_idx]
# except IndexError: pair_idx = pair_idx - 1

##################################################################################

return {
'uni_sources': uni_sources,
'uni_idx': uni_idx,
Expand Down Expand Up @@ -366,7 +394,7 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
gevent.spawn(fetch_watch_page_info, video_id, playlist_id, index),


gevent.spawn(fetch_player_response, 'android_vr', video_id)
gevent.spawn(fetch_player_response, 'ios', video_id)
)
gevent.joinall(tasks)
util.check_gevent_exceptions(*tasks)
Expand Down
31 changes: 29 additions & 2 deletions youtube/yt_data_extract/watch_extraction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
import urllib.parse
import traceback
import re
import settings

# from https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/youtube.py
_formats = {
Expand Down Expand Up @@ -476,8 +477,29 @@ def _extract_formats(info, player_response):
# Example: https://www.youtube.com/watch?v=gF9kkB0UWYQ
# Only get the original language for now so a foreign
# translation will not be picked just because it comes first
if deep_get(yt_fmt, 'audioTrack', 'audioIsDefault') is False:
continue
# if deep_get(yt_fmt, 'audioTrack', 'audioIsDefault') is False:
# continue

# mine
# if deep_get(yt_fmt, 'audioTrack', 'audioIsDefault') is True and deep_get(yt_fmt, 'audioTrack', 'isAutoDubbed') is True:
# continue

# mine
# in case no contentLength provided
# if itag in [18]:
# clen = int(str(deep_get(urllib.parse.parse_qs(urllib.parse.urlparse(yt_fmt.get('url')).query), 'clen', 0)) + '0')
# yt_fmt['contentLength'] = clen
# if itag not in [140, 134, 18]:
# continue

# mine
# what if user upload audio track without using auto dubbing???
if settings.disable_dubbing and deep_get(yt_fmt, 'audioTrack', 'isAutoDubbed') is True: continue
allowed = [a.strip().lower() for a in settings.allowed_dubbing_languages.split(';') if a not in ['', ' ', ',', ';', ':']] + ['undefined']
lng = deep_get(yt_fmt, 'audioTrack', 'displayName', default='undefined')
if 'original' in lng.lower(): lng = 'undefined'
if len(allowed) == 1: pass # in case allowed list is empty
elif lng.lower().split(' ')[0] not in allowed: continue

fmt = {}
fmt['itag'] = itag
Expand All @@ -494,6 +516,7 @@ def _extract_formats(info, player_response):
fmt['fps'] = yt_fmt.get('fps')
fmt['init_range'] = yt_fmt.get('initRange')
fmt['index_range'] = yt_fmt.get('indexRange')
fmt['audio_track'] = lng # mine
for key in ('init_range', 'index_range'):
if fmt[key]:
fmt[key]['start'] = int(fmt[key]['start'])
Expand Down Expand Up @@ -522,6 +545,10 @@ def _extract_formats(info, player_response):
extract_int(yt_fmt.get('qualityLabel'), whole_word=False)
)

# mine
# need clen for uni_sources
if itag in [18]: fmt['clen'] = urllib.parse.parse_qs(urllib.parse.urlparse(fmt['url']).query).get('clen')

info['formats'].append(fmt)

# get ip address
Expand Down