s8n
24a9497e7d
processes/ -> playbooks/ (git mv preserves history; updated cross-refs in ROADMAP, README, subtitles playbook + scripts). playbooks/import-media/README.md v1.0 — 7-step import workflow: stage on onyx -> rsync to nullstone -> chmod -> verify scan -> Items/Counts bump -> optional subtitle pass -> run-log Cross-references docs/05/07/08, ADMIN-GUIDE, README. Mirrors the existing subtitles playbook structure (CHANGELOG + runs/_template). CHANGELOG v1.0 lists known gaps (bin/cleanup-import.sh and bin/normalize.py still doc-only, ROADMAP M6). First run logged: playbooks/import-media/runs/lilo-stitch-2002.md. Lilo & Stitch (2002) imported to /home/user/media/movies/, item c2f4aff133c1b9631500fadf293b0b2f, TMDb 11544, MovieCount 3 -> 4. LibraryMonitor didn't auto-fire — needed manual /Library/Refresh; playbook updated to make this an unconditional step. Source: 1080p BluRay HEVC 10-bit / EAC3 5.1 / 2x PGS embedded subs. Per quality bar (README.md:41) — passes.
56 lines
2.3 KiB
Python
Executable file
56 lines
2.3 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
"""Clean YouTube auto-caption VTT into a flat SRT with no rolling-window dupes."""
|
|
import re, sys, pathlib
|
|
|
|
def parse_vtt(text):
|
|
"""Yield (start, end, line) tuples, dropping inline timing tags and empty lines."""
|
|
blocks = re.split(r'\n\n+', text.strip())
|
|
for b in blocks:
|
|
if 'WEBVTT' in b or b.startswith('Kind:') or b.startswith('Language:'):
|
|
continue
|
|
m = re.search(r'(\d{2}:\d{2}:\d{2}[.,]\d{3})\s*-->\s*(\d{2}:\d{2}:\d{2}[.,]\d{3})', b)
|
|
if not m: continue
|
|
start, end = m.group(1), m.group(2)
|
|
# Strip cue settings and inline <00:..><c>...</c> tags
|
|
body = b[m.end():].strip()
|
|
body = re.sub(r'<\d{2}:\d{2}:\d{2}\.\d{3}>', '', body)
|
|
body = re.sub(r'</?c[^>]*>', '', body)
|
|
body = re.sub(r'align:\S+|position:\S+', '', body).strip()
|
|
# Last non-empty line is "new" content (rolling window puts the freshly spoken line at bottom)
|
|
lines = [ln.strip() for ln in body.split('\n') if ln.strip()]
|
|
if not lines: continue
|
|
yield start, end, lines[-1]
|
|
|
|
def to_srt_time(t):
|
|
return t.replace('.', ',')
|
|
|
|
def merge(events):
|
|
"""Drop the 10ms 'gap' cues and merge consecutive identical text."""
|
|
out = []
|
|
for s, e, txt in events:
|
|
# Skip the bridge cue with same text already on top
|
|
if out and out[-1][2] == txt:
|
|
out[-1] = (out[-1][0], to_srt_time(e), txt) # extend
|
|
continue
|
|
out.append([to_srt_time(s), to_srt_time(e), txt])
|
|
# second pass to drop micro-cues
|
|
final = []
|
|
for s, e, txt in out:
|
|
sh, sm, ssms = s.split(':'); ssec, sms = ssms.split(',')
|
|
eh, em, esms = e.split(':'); esec, ems = esms.split(',')
|
|
sm_total = int(sh)*3600+int(sm)*60+int(ssec)+int(sms)/1000
|
|
em_total = int(eh)*3600+int(em)*60+int(esec)+int(ems)/1000
|
|
if em_total - sm_total < 0.05: continue # 50ms bridge cue
|
|
final.append((s, e, txt))
|
|
return final
|
|
|
|
def write_srt(events, path):
|
|
with open(path, 'w') as f:
|
|
for i, (s, e, txt) in enumerate(events, 1):
|
|
f.write(f"{i}\n{s} --> {e}\n{txt}\n\n")
|
|
|
|
if __name__ == '__main__':
|
|
vtt = pathlib.Path(sys.argv[1]).read_text()
|
|
events = list(merge(parse_vtt(vtt)))
|
|
write_srt(events, sys.argv[2])
|
|
print(f"wrote {len(events)} cues -> {sys.argv[2]}")
|