kenzuya/unshackle
1
0
Fork 1
mirror of https://github.com/unshackle-dl/unshackle.git synced 2026-03-18 09:07:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(dl): filter CC subtitle languages with --s-lang and extract all manifest CCs

Browse Source 
Fixes issues introduced in 15acaea where CC extraction only used the first manifest entry and ignored --s-lang filtering entirely. Now all CC languages from the HLS manifest are iterated and filtered against --s-lang using the same match logic as regular subtitle selection.
This commit is contained in:
Andy
2026-03-16 14:09:05 -06:00
parent e02aa66843
commit b1447eb14b
1 changed files with 40 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
unshackle/commands/dl.py
View File

@@ -62,7 +62,7 @@ from unshackle.core.tracks import Audio, Subtitle, Tracks, Video
from unshackle.core.tracks.attachment import Attachment from unshackle.core.tracks.attachment import Attachment
from unshackle.core.tracks.hybrid import Hybrid from unshackle.core.tracks.hybrid import Hybrid
from unshackle.core.utilities import (find_font_with_fallbacks, get_debug_logger, get_system_fonts, init_debug_logger, from unshackle.core.utilities import (find_font_with_fallbacks, get_debug_logger, get_system_fonts, init_debug_logger,
is_close_match, suggest_font_packages, time_elapsed_since) is_close_match, is_exact_match, suggest_font_packages, time_elapsed_since)
from unshackle.core.utils import tags from unshackle.core.utils import tags
from unshackle.core.utils.click_types import (AUDIO_CODEC_LIST, LANGUAGE_RANGE, QUALITY_LIST, SEASON_RANGE, from unshackle.core.utils.click_types import (AUDIO_CODEC_LIST, LANGUAGE_RANGE, QUALITY_LIST, SEASON_RANGE,
ContextData, MultipleChoice, MultipleVideoCodecChoice, ContextData, MultipleChoice, MultipleVideoCodecChoice,
@@ -1712,8 +1712,6 @@ class dl:
f"Required languages found ({', '.join(require_subs)}), downloading all available subtitles" f"Required languages found ({', '.join(require_subs)}), downloading all available subtitles"
) )
elif s_lang and "all" not in s_lang: elif s_lang and "all" not in s_lang:
from unshackle.core.utilities import is_exact_match
match_func = is_exact_match if exact_lang else is_close_match match_func = is_exact_match if exact_lang else is_close_match
missing_langs = [ missing_langs = [
@@ -2105,6 +2103,7 @@ class dl:
and not video_only and not video_only
and not no_video and not no_video
): ):
match_func = is_exact_match if exact_lang else is_close_match
for video_track_n, video_track in enumerate(title.tracks.videos): for video_track_n, video_track in enumerate(title.tracks.videos):
has_manifest_cc = bool(getattr(video_track, "closed_captions", None)) has_manifest_cc = bool(getattr(video_track, "closed_captions", None))
has_eia_cc = ( has_eia_cc = (
@@ -2118,31 +2117,48 @@ class dl:
if not has_manifest_cc and not has_eia_cc: if not has_manifest_cc and not has_eia_cc:
continue continue
# Build list of CC entries to extract
if has_manifest_cc:
cc_entries = video_track.closed_captions
# Filter CC languages against --s-lang if specified
if s_lang and "all" not in s_lang:
cc_entries = [
entry for entry in cc_entries
if entry.get("language")
and match_func(Language.get(entry["language"]), s_lang)
]
if not cc_entries:
continue
else:
# EIA fallback: single entry with unknown language
cc_entries = [{}]
with console.status(f"Checking Video track {video_track_n + 1} for Closed Captions..."): with console.status(f"Checking Video track {video_track_n + 1} for Closed Captions..."):
try: try:
cc_lang = ( for cc_idx, cc_entry in enumerate(cc_entries):
Language.get(video_track.closed_captions[0]["language"]) cc_lang = (
if has_manifest_cc and video_track.closed_captions[0].get("language") Language.get(cc_entry["language"])
else title.language or video_track.language if cc_entry.get("language")
) else title.language or video_track.language
track_id = f"ccextractor-{video_track.id}"
cc = video_track.ccextractor(
track_id=track_id,
out_path=config.directories.temp
/ config.filenames.subtitle.format(id=track_id, language=cc_lang),
language=cc_lang,
original=False,
)
if cc:
cc.cc = True
title.tracks.add(cc)
self.log.info(
f"Extracted a Closed Caption from Video track {video_track_n + 1}"
) )
else: track_id = f"ccextractor-{video_track.id}-{cc_idx}"
self.log.info( cc = video_track.ccextractor(
f"No Closed Captions were found in Video track {video_track_n + 1}" track_id=track_id,
out_path=config.directories.temp
/ config.filenames.subtitle.format(id=track_id, language=cc_lang),
language=cc_lang,
original=False,
) )
if cc:
cc.cc = True
title.tracks.add(cc)
self.log.info(
f"Extracted a Closed Caption ({cc_lang}) from Video track {video_track_n + 1}"
)
else:
self.log.info(
f"No Closed Captions were found in Video track {video_track_n + 1}"
)
except EnvironmentError: except EnvironmentError:
self.log.error( self.log.error(
"Cannot extract Closed Captions as the ccextractor executable was not found..." "Cannot extract Closed Captions as the ccextractor executable was not found..."