12 Commits

Author SHA1 Message Date
Andy
79e8184474 ci: enable manual triggering of release workflow 2026-03-17 09:10:50 -06:00
Andy
178eed9236 ci: add GitHub Actions release workflow for major/minor versions 2026-03-17 09:08:20 -06:00
Andy
63d2ba60c4 chore(changelog): tag v4.0.0 release 2026-03-17 08:57:34 -06:00
Andy
f46aa9d8c8 chore(changelog): update changelog for upcoming release and reorganize sections 2026-03-17 08:55:14 -06:00
Andy
b1447eb14b fix(dl): filter CC subtitle languages with --s-lang and extract all manifest CCs
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.
2026-03-16 14:09:05 -06:00
Andy
e02aa66843 feat(dl): add --worst flag and SHIELD OkHttp fingerprint preset
Add --worst CLI flag to select the lowest bitrate video track within a specified resolution (e.g. --worst -q 720). Requires -q/--quality.
Add shield_okhttp TLS fingerprint preset for NVIDIA SHIELD Android TV with OkHttp 4.11 JA3 signature.
2026-03-11 13:59:07 -06:00
Sp5rky
c82bb5fe34 Merge pull request #88 from CodeName393/fix-aria2c-progress-bar
fix(aria2c): Correct progress bar tracking for HLS downloads
2026-03-07 20:21:25 -07:00
Andy
ec2ecfe7b4 fix(ism): prevent duplicate track IDs for audio tracks with same lang/codec/bitrate
Include StreamIndex Name and Url attributes in the track ID hash to disambiguate tracks that share the same codec, language, bitrate, and QualityLevel index.
2026-03-07 13:01:36 -07:00
Andy
15acaea208 feat(dl): extract closed captions from HLS manifests and improve CC extraction
- Parse CLOSED-CAPTIONS entries from HLS manifests and attach CC metadata (language, name, instream_id) to video tracks
- Move CC extraction to run after decryption instead of before, fixing extraction failures on encrypted streams
- Extract CCs even when other subtitle tracks exist, using manifest CC language info instead of guessing
- Try ccextractor on the original file before repacking to preserve container-level CC data (e.g. c608 boxes) that ffmpeg remux strips
- Display deduplicated closed captions in --list output and download progress, positioned after subtitles
- Add closed_captions field to Video track class
2026-03-05 15:57:29 -07:00
CodeName393
def18a4c44 fix(aria2c): Correct progress bar tracking for HLS downloads
Modified the download generator in aria2c to track progress by the number of completed segments (len(completed)) when downloading multiple files. Single-file downloads remain byte-based.
2026-03-05 14:43:24 +09:00
Sp5rky
7dd6323be5 Merge pull request #87 from CodeName393/add-HDR-Vivid-TAG
fix(title): Add HDR Vivid Format HDR Tag
2026-03-04 15:38:03 -07:00
CodeName393
d68bb28a66 fix(title): Add HDR Vivid Format HDR Tag
The existing HDR Vivid format HDR tag processing is missing due to the feature of the title map.
2026-03-04 23:17:18 +09:00
10 changed files with 352 additions and 147 deletions

91
.github/workflows/release.yml vendored Normal file
View File

@@ -0,0 +1,91 @@
name: Release
on:
workflow_dispatch:
push:
branches: [main]
paths:
- "pyproject.toml"
permissions:
contents: write
jobs:
check-version:
runs-on: ubuntu-latest
outputs:
should_release: ${{ steps.version_check.outputs.should_release }}
new_version: ${{ steps.version_check.outputs.new_version }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Check for major/minor version bump
id: version_check
run: |
NEW_VERSION=$(grep -m1 '^version' pyproject.toml | sed 's/version = "\(.*\)"/\1/')
echo "Detected version in pyproject.toml: $NEW_VERSION"
LATEST_TAG=$(git tag --list | grep -E '^[0-9]+\.[0-9]+\.[0-9]+$' | sort -V | tail -1)
echo "Latest git tag: $LATEST_TAG"
if [ -z "$LATEST_TAG" ]; then
echo "No previous tag found, treating as new release"
echo "should_release=true" >> "$GITHUB_OUTPUT"
echo "new_version=$NEW_VERSION" >> "$GITHUB_OUTPUT"
exit 0
fi
OLD_MAJOR=$(echo "$LATEST_TAG" | cut -d. -f1)
OLD_MINOR=$(echo "$LATEST_TAG" | cut -d. -f2)
NEW_MAJOR=$(echo "$NEW_VERSION" | cut -d. -f1)
NEW_MINOR=$(echo "$NEW_VERSION" | cut -d. -f2)
if [ "$NEW_MAJOR" -gt "$OLD_MAJOR" ] || [ "$NEW_MINOR" -gt "$OLD_MINOR" ]; then
echo "Major or minor version bump detected: $LATEST_TAG -> $NEW_VERSION"
echo "should_release=true" >> "$GITHUB_OUTPUT"
else
echo "Patch-only change ($LATEST_TAG -> $NEW_VERSION), skipping release"
echo "should_release=false" >> "$GITHUB_OUTPUT"
fi
echo "new_version=$NEW_VERSION" >> "$GITHUB_OUTPUT"
release:
needs: check-version
if: needs.check-version.outputs.should_release == 'true'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install uv
uses: astral-sh/setup-uv@v4
- name: Set up Python
run: uv python install 3.12
- name: Install dependencies and build
run: |
uv sync
uv build
- name: Extract changelog for release
id: changelog
run: |
VERSION=${{ needs.check-version.outputs.new_version }}
# Extract the section for this version from CHANGELOG.md
awk "/^## \[$VERSION\]/{found=1; next} /^## \[/{if(found) exit} found{print}" CHANGELOG.md > release_notes.md
echo "Extracted release notes:"
cat release_notes.md
- name: Create GitHub Release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
VERSION=${{ needs.check-version.outputs.new_version }}
gh release create "$VERSION" \
--title "$VERSION" \
--notes-file release_notes.md \
dist/unshackle-${VERSION}-py3-none-any.whl \
dist/unshackle-${VERSION}.tar.gz

View File

@@ -6,7 +6,7 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
This changelog is automatically generated using [git-cliff](https://git-cliff.org).
## [Unreleased]
## [4.0.0] - 2026-03-17
### Features
@@ -19,6 +19,11 @@ This changelog is automatically generated using [git-cliff](https://git-cliff.or
- *tracks*: Add edition tags to output filenames
- *templates*: [**breaking**] Add customizable output filename templates
- *templates*: Add configurable language tagging rule engine
- Update unshackle version to 4.0.0
- *dl*: Add --animeapi and --enrich options for anime metadata and tagging
- *dl*: Add skip messages for --no-audio and --no-chapters flags
- *dl*: Extract closed captions from HLS manifests and improve CC extraction
- *dl*: Add --worst flag and SHIELD OkHttp fingerprint preset
### Bug Fixes
@@ -33,6 +38,13 @@ This changelog is automatically generated using [git-cliff](https://git-cliff.or
- *n_m3u8dl_re*: Disable segment count validation for duration-based DASH
- Correct formatting and add missing newlines in selector and EXAMPLE service
- *dependencies*: Update pyplayready version to 0.8.3 and adjust dependencies
- *drm*: Update PlayReady KID extraction for pyplayready 0.8.3 compatibility
- *api*: Resolve Sentinel serialization, missing params, and add search endpoint
- *dash*: Pass period_filter to n_m3u8dl_re via filtered MPD file
- *title*: Add HDR Vivid Format HDR Tag
- *ism*: Prevent duplicate track IDs for audio tracks with same lang/codec/bitrate
- *aria2c*: Correct progress bar tracking for HLS downloads
- *dl*: Filter CC subtitle languages with --s-lang and extract all manifest CCs
### Documentation
@@ -45,10 +57,6 @@ This changelog is automatically generated using [git-cliff](https://git-cliff.or
- *example*: Migrate EXAMPLE service to track_request pattern
- *providers*: Extract metadata providers into modular system
### Maintenance
- *changelog*: Update changelog for upcoming release and reorganize sections
## [3.0.0] - 2026-02-15
### Features

View File

@@ -25,6 +25,7 @@ import click
import jsonpickle
import yaml
from construct import ConstError
from langcodes import Language
from pymediainfo import MediaInfo
from pyplayready.cdm import Cdm as PlayReadyCdm
from pyplayready.device import Device as PlayReadyDevice
@@ -61,7 +62,7 @@ from unshackle.core.tracks import Audio, Subtitle, Tracks, Video
from unshackle.core.tracks.attachment import Attachment
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,
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.click_types import (AUDIO_CODEC_LIST, LANGUAGE_RANGE, QUALITY_LIST, SEASON_RANGE,
ContextData, MultipleChoice, MultipleVideoCodecChoice,
@@ -505,6 +506,12 @@ class dl:
@click.option(
"--reset-cache", "reset_cache", is_flag=True, default=False, help="Clear title cache before fetching."
)
@click.option(
"--worst",
is_flag=True,
default=False,
help="Select the lowest bitrate track within the specified quality. Requires -q/--quality.",
)
@click.option(
"--best-available",
"best_available",
@@ -990,6 +997,7 @@ class dl:
no_mux: bool,
workers: Optional[int],
downloads: int,
worst: bool,
best_available: bool,
split_audio: Optional[bool] = None,
*_: Any,
@@ -1015,6 +1023,10 @@ class dl:
self.log.error("--require-subs and --s-lang cannot be used together")
sys.exit(1)
if worst and not quality:
self.log.error("--worst requires -q/--quality to be specified")
sys.exit(1)
if select_titles and wanted:
self.log.error("--select-titles and -w/--wanted cannot be used together")
sys.exit(1)
@@ -1608,20 +1620,18 @@ class dl:
for resolution, color_range, codec in product(
quality or [None], non_hybrid_ranges, vcodec or [None]
):
match = next(
(
t
for t in non_hybrid_tracks
if (
not resolution
or t.height == resolution
or int(t.width * (9 / 16)) == resolution
)
and (not color_range or t.range == color_range)
and (not codec or t.codec == codec)
),
None,
)
candidates = [
t
for t in non_hybrid_tracks
if (
not resolution
or t.height == resolution
or int(t.width * (9 / 16)) == resolution
)
and (not color_range or t.range == color_range)
and (not codec or t.codec == codec)
]
match = candidates[-1] if worst and candidates else next(iter(candidates), None)
if match and match not in non_hybrid_selected:
non_hybrid_selected.append(match)
@@ -1631,20 +1641,18 @@ class dl:
for resolution, color_range, codec in product(
quality or [None], range_ or [None], vcodec or [None]
):
match = next(
(
t
for t in title.tracks.videos
if (
not resolution
or t.height == resolution
or int(t.width * (9 / 16)) == resolution
)
and (not color_range or t.range == color_range)
and (not codec or t.codec == codec)
),
None,
)
candidates = [
t
for t in title.tracks.videos
if (
not resolution
or t.height == resolution
or int(t.width * (9 / 16)) == resolution
)
and (not color_range or t.range == color_range)
and (not codec or t.codec == codec)
]
match = candidates[-1] if worst and candidates else next(iter(candidates), None)
if match and match not in selected_videos:
selected_videos.append(match)
title.tracks.videos = selected_videos
@@ -1704,8 +1712,6 @@ class dl:
f"Required languages found ({', '.join(require_subs)}), downloading all available subtitles"
)
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
missing_langs = [
@@ -2025,49 +2031,6 @@ class dl:
dl_time = time_elapsed_since(dl_start_time)
console.print(Padding(f"Track downloads finished in [progress.elapsed]{dl_time}[/]", (0, 5)))
video_track_n = 0
while (
not title.tracks.subtitles
and not no_subs
and not (hasattr(service, "NO_SUBTITLES") and service.NO_SUBTITLES)
and not video_only
and not no_video
and len(title.tracks.videos) > video_track_n
and any(
x.get("codec_name", "").startswith("eia_")
for x in ffprobe(title.tracks.videos[video_track_n].path).get("streams", [])
)
):
with console.status(f"Checking Video track {video_track_n + 1} for Closed Captions..."):
try:
# TODO: Figure out the real language, it might be different
# EIA-CC tracks sadly don't carry language information :(
# TODO: Figure out if the CC language is original lang or not.
# Will need to figure out above first to do so.
video_track = title.tracks.videos[video_track_n]
track_id = f"ccextractor-{video_track.id}"
cc_lang = title.language or video_track.language
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:
# will not appear in track listings as it's added after all times it lists
title.tracks.add(cc)
self.log.info(f"Extracted a Closed Caption 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:
self.log.error(
"Cannot extract Closed Captions as the ccextractor executable was not found..."
)
break
video_track_n += 1
# Subtitle output mode configuration (for sidecar originals)
subtitle_output_mode = config.subtitle.get("output_mode", "mux")
sidecar_format = config.subtitle.get("sidecar_format", "srt")
@@ -2133,6 +2096,75 @@ class dl:
if has_decrypted:
self.log.info(f"Decrypted tracks with {decrypt_tool}")
# Extract Closed Captions from decrypted video tracks
if (
not no_subs
and not (hasattr(service, "NO_SUBTITLES") and service.NO_SUBTITLES)
and not video_only
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):
has_manifest_cc = bool(getattr(video_track, "closed_captions", None))
has_eia_cc = (
not has_manifest_cc
and not title.tracks.subtitles
and any(
x.get("codec_name", "").startswith("eia_")
for x in ffprobe(video_track.path).get("streams", [])
)
)
if not has_manifest_cc and not has_eia_cc:
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..."):
try:
for cc_idx, cc_entry in enumerate(cc_entries):
cc_lang = (
Language.get(cc_entry["language"])
if cc_entry.get("language")
else title.language or video_track.language
)
track_id = f"ccextractor-{video_track.id}-{cc_idx}"
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 ({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:
self.log.error(
"Cannot extract Closed Captions as the ccextractor executable was not found..."
)
break
# Now repack the decrypted tracks
with console.status("Repackaging tracks with FFMPEG..."):
has_repacked = False

View File

@@ -431,14 +431,24 @@ def download(
raise ValueError(error)
# Yield aggregate progress for this call's downloads
if total_size > 0:
# Yield both advance (bytes downloaded this iteration) and total for rich progress
if dl_speed != -1:
yield dict(downloaded=f"{filesize.decimal(dl_speed)}/s", advance=0, completed=total_completed, total=total_size)
progress_data = {"advance": 0}
if len(gids) > 1:
# Multi-file mode (e.g., HLS): Return the count of completed segments
progress_data["completed"] = len(completed)
progress_data["total"] = len(gids)
else:
# Single-file mode: Return the total bytes downloaded
progress_data["completed"] = total_completed
if total_size > 0:
progress_data["total"] = total_size
else:
yield dict(advance=0, completed=total_completed, total=total_size)
elif dl_speed != -1:
yield dict(downloaded=f"{filesize.decimal(dl_speed)}/s")
progress_data["total"] = None
if dl_speed != -1:
progress_data["downloaded"] = f"{filesize.decimal(dl_speed)}/s"
yield progress_data
time.sleep(1)
except KeyboardInterrupt:

View File

@@ -112,6 +112,15 @@ class HLS:
session_drm = HLS.get_all_drm(session_keys)
audio_codecs_by_group_id: dict[str, Audio.Codec] = {}
cc_by_group_id: dict[str, list[dict[str, Any]]] = {}
for media in self.manifest.media:
if media.type == "CLOSED-CAPTIONS":
cc_by_group_id.setdefault(media.group_id, []).append({
"language": media.language,
"name": media.name,
"instream_id": media.instream_id,
"characteristics": media.characteristics,
})
tracks = Tracks()
for playlist in self.manifest.playlists:
@@ -161,6 +170,9 @@ class HLS:
width=playlist.stream_info.resolution[0] if playlist.stream_info.resolution else None,
height=playlist.stream_info.resolution[1] if playlist.stream_info.resolution else None,
fps=playlist.stream_info.frame_rate,
closed_captions=cc_by_group_id.get(
(playlist.stream_info.closed_captions or "").strip('"'), []
),
)
if primary_track_type is Video
else {}

View File

@@ -145,7 +145,14 @@ class ISM:
fragment_time += duration_frag
track_id = hashlib.md5(
f"{codec}-{track_lang}-{ql.get('Bitrate') or 0}-{ql.get('Index') or 0}".encode()
"{codec}-{lang}-{bitrate}-{index}-{name}-{url}".format(
codec=codec,
lang=track_lang,
bitrate=ql.get("Bitrate") or 0,
index=ql.get("Index") or 0,
name=stream_index.get("Name") or "",
url=stream_index.get("Url") or "",
).encode()
).hexdigest()
data = {

View File

@@ -44,6 +44,17 @@ FINGERPRINT_PRESETS = {
"akamai": "4:16777216|16711681|0|m,p,a,s",
"description": "OkHttp 5.x (BoringSSL TLS stack)",
},
"shield_okhttp": {
"ja3": (
"771," # TLS 1.2
"4865-4866-4867-49195-49199-49196-49200-52393-52392-49171-49172-156-157-47-53," # Ciphers (OkHttp 4.11)
"0-23-65281-10-11-35-16-5-13-51-45-43-21," # Extensions (incl padding ext 21)
"29-23-24," # Named groups (x25519, secp256r1, secp384r1)
"0" # EC point formats
),
"akamai": "4:16777216|16711681|0|m,p,a,s",
"description": "NVIDIA SHIELD Android TV OkHttp 4.11 (captured JA3)",
},
}

View File

@@ -121,6 +121,8 @@ class Title:
base_layer = DYNAMIC_RANGE_MAP.get(hdr_format)
if base_layer and base_layer != "DV":
context["hdr"] += f".{base_layer}"
elif (primary_video_track.hdr_format or "").startswith("HDR Vivid"):
context["hdr"] = "HDR"
else:
context["hdr"] = DYNAMIC_RANGE_MAP.get(hdr_format, "")
elif trc and "HLG" in trc:

View File

@@ -103,53 +103,78 @@ class Tracks:
tree = Tree("", hide_root=True)
for track_type in self.TRACK_ORDER_MAP:
tracks = list(x for x in all_tracks if isinstance(x, track_type))
if not tracks:
continue
num_tracks = len(tracks)
track_type_plural = track_type.__name__ + ("s" if track_type != Audio and num_tracks != 1 else "")
tracks_tree = tree.add(f"[repr.number]{num_tracks}[/] {track_type_plural}")
for track in tracks:
if add_progress and track_type not in (Chapter, Attachment):
progress = Progress(
SpinnerColumn(finished_text=""),
BarColumn(),
"",
TimeRemainingColumn(compact=True, elapsed_when_finished=True),
"",
TextColumn("[progress.data.speed]{task.fields[downloaded]}"),
console=console,
speed_estimate_period=10,
if tracks:
num_tracks = len(tracks)
track_type_plural = track_type.__name__ + ("s" if track_type != Audio and num_tracks != 1 else "")
tracks_tree = tree.add(f"[repr.number]{num_tracks}[/] {track_type_plural}")
for track in tracks:
if add_progress and track_type not in (Chapter, Attachment):
progress = Progress(
SpinnerColumn(finished_text=""),
BarColumn(),
"",
TimeRemainingColumn(compact=True, elapsed_when_finished=True),
"",
TextColumn("[progress.data.speed]{task.fields[downloaded]}"),
console=console,
speed_estimate_period=10,
)
task = progress.add_task("", downloaded="-")
state = {"total": 100.0}
def update_track_progress(
task_id: int = task,
_state: dict[str, float] = state,
_progress: Progress = progress,
**kwargs,
) -> None:
"""
Ensure terminal status states render as a fully completed bar.
Some downloaders can report completed slightly below total
before emitting the final "Downloaded" state.
"""
if "total" in kwargs and kwargs["total"] is not None:
_state["total"] = kwargs["total"]
downloaded_state = kwargs.get("downloaded")
if downloaded_state in {"Downloaded", "Decrypted", "[yellow]SKIPPED"}:
kwargs["completed"] = _state["total"]
_progress.update(task_id=task_id, **kwargs)
progress_callables.append(update_track_progress)
track_table = Table.grid()
track_table.add_row(str(track)[6:], style="text2")
track_table.add_row(progress)
tracks_tree.add(track_table)
else:
tracks_tree.add(str(track)[6:], style="text2")
# Show Closed Captions right after Subtitles (even if no subtitle tracks exist)
if track_type is Subtitle:
seen_cc: set[str] = set()
unique_cc: list[str] = []
for video in (x for x in all_tracks if isinstance(x, Video)):
for cc in getattr(video, "closed_captions", []):
lang = cc.get("language", "und")
name = cc.get("name", "")
instream_id = cc.get("instream_id", "")
key = f"{lang}|{instream_id}"
if key in seen_cc:
continue
seen_cc.add(key)
parts = [f"[CC] | {lang}"]
if name:
parts.append(name)
if instream_id:
parts.append(instream_id)
unique_cc.append(" | ".join(parts))
if unique_cc:
cc_tree = tree.add(
f"[repr.number]{len(unique_cc)}[/] Closed Caption{'s' if len(unique_cc) != 1 else ''}"
)
task = progress.add_task("", downloaded="-")
state = {"total": 100.0}
def update_track_progress(
task_id: int = task,
_state: dict[str, float] = state,
_progress: Progress = progress,
**kwargs,
) -> None:
"""
Ensure terminal status states render as a fully completed bar.
Some downloaders can report completed slightly below total
before emitting the final "Downloaded" state.
"""
if "total" in kwargs and kwargs["total"] is not None:
_state["total"] = kwargs["total"]
downloaded_state = kwargs.get("downloaded")
if downloaded_state in {"Downloaded", "Decrypted", "[yellow]SKIPPED"}:
kwargs["completed"] = _state["total"]
_progress.update(task_id=task_id, **kwargs)
progress_callables.append(update_track_progress)
track_table = Table.grid()
track_table.add_row(str(track)[6:], style="text2")
track_table.add_row(progress)
tracks_tree.add(track_table)
else:
tracks_tree.add(str(track)[6:], style="text2")
for cc_str in unique_cc:
cc_tree.add(cc_str, style="text2")
return tree, progress_callables

View File

@@ -200,6 +200,7 @@ class Video(Track):
height: Optional[int] = None,
fps: Optional[Union[str, int, float]] = None,
scan_type: Optional[Video.ScanType] = None,
closed_captions: Optional[list[dict[str, Any]]] = None,
**kwargs: Any,
) -> None:
"""
@@ -264,6 +265,7 @@ class Video(Track):
raise ValueError("Expected fps to be a number, float, or a string as numerator/denominator form, " + str(e))
self.scan_type = scan_type
self.closed_captions: list[dict[str, Any]] = closed_captions or []
self.needs_duration_fix = False
def __str__(self) -> str:
@@ -346,22 +348,27 @@ class Video(Track):
if not binaries.CCExtractor:
raise EnvironmentError("ccextractor executable was not found.")
# ccextractor often fails in weird ways unless we repack
self.repackage()
out_path = Path(out_path)
try:
subprocess.run(
[binaries.CCExtractor, "-trim", "-nobom", "-noru", "-ru1", "-o", out_path, self.path],
check=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
except subprocess.CalledProcessError as e:
out_path.unlink(missing_ok=True)
if not e.returncode == 10: # No captions found
raise
def _run_ccextractor() -> bool:
try:
subprocess.run(
[binaries.CCExtractor, "-trim", "-nobom", "-noru", "-ru1", "-o", out_path, self.path],
check=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
except subprocess.CalledProcessError as e:
out_path.unlink(missing_ok=True)
if e.returncode != 10: # 10 = No captions found
raise
return out_path.exists()
# Try on the original file first (preserves container-level CC data like c608 boxes),
# then fall back to repacked file (ccextractor can fail on some container formats).
if not _run_ccextractor():
self.repackage()
_run_ccextractor()
if out_path.exists():
cc_track = Subtitle(