Claude Fable 5
a7d7d1cf50
Short continuations (e.g. a single trailing word) carry no inline timing tags, so filtering by tags missed them. Instead, in files with inline timing tags, drop leading cue lines that repeat the previous cue's last line — covers both tagged and untagged new text. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
117 lines
3.4 KiB
Python
Executable File
117 lines
3.4 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Convert VTT or SRT subtitle files to Markdown plain text."""
|
|
import re
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
|
|
def strip_html(text):
|
|
return re.sub(r'<[^>]+>', '', text)
|
|
|
|
|
|
# YouTube auto-captions use rolling cues: each cue repeats the previous
|
|
# cue's last line as plain text before the new text (which usually, but not
|
|
# always, carries inline word timings like <00:00:00.200> or <c>…</c>).
|
|
def has_inline_timing_tags(text):
|
|
return re.search(r'<\d{2}:\d{2}:|<c[.\w]*>', text) is not None
|
|
|
|
|
|
def parse_vtt(content):
|
|
rolling = has_inline_timing_tags(content)
|
|
blocks = re.split(r'\n{2,}', content.strip())
|
|
cues = []
|
|
prev_last = None
|
|
for block in blocks:
|
|
lines = block.strip().splitlines()
|
|
if not lines:
|
|
continue
|
|
if lines[0].startswith('WEBVTT'):
|
|
continue
|
|
if lines[0].startswith('NOTE') or lines[0].startswith('STYLE'):
|
|
continue
|
|
ts_idx = next((i for i, l in enumerate(lines) if '-->' in l), None)
|
|
if ts_idx is None:
|
|
continue
|
|
text_lines = [strip_html(l).strip() for l in lines[ts_idx + 1:]]
|
|
if rolling:
|
|
while text_lines and prev_last and text_lines[0] == prev_last:
|
|
text_lines.pop(0)
|
|
non_empty = [l for l in text_lines if l]
|
|
if rolling and non_empty:
|
|
prev_last = non_empty[-1]
|
|
text = ' '.join(non_empty)
|
|
if text:
|
|
cues.append(text)
|
|
return cues
|
|
|
|
|
|
def parse_srt(content):
|
|
blocks = re.split(r'\n{2,}', content.strip())
|
|
cues = []
|
|
for block in blocks:
|
|
lines = block.strip().splitlines()
|
|
text_lines = []
|
|
for line in lines:
|
|
line = line.strip()
|
|
if re.match(r'^\d+$', line):
|
|
continue
|
|
if re.match(r'\d{2}:\d{2}:\d{2}[,\.]\d{3}\s*-->', line):
|
|
continue
|
|
cleaned = strip_html(line)
|
|
if cleaned:
|
|
text_lines.append(cleaned)
|
|
if text_lines:
|
|
cues.append(' '.join(text_lines))
|
|
return cues
|
|
|
|
|
|
def deduplicate(cues):
|
|
result = []
|
|
prev = None
|
|
for cue in cues:
|
|
if cue != prev:
|
|
result.append(cue)
|
|
prev = cue
|
|
return result
|
|
|
|
|
|
def to_markdown(cues):
|
|
cues = deduplicate(cues)
|
|
if not cues:
|
|
return ''
|
|
full = ' '.join(cues)
|
|
sentences = re.split(r'(?<=[.!?…])\s+', full)
|
|
paragraphs = []
|
|
for i in range(0, len(sentences), 8):
|
|
paragraphs.append(' '.join(sentences[i:i + 8]))
|
|
return '\n\n'.join(paragraphs)
|
|
|
|
|
|
def convert(input_path):
|
|
content = input_path.read_text(encoding='utf-8', errors='replace')
|
|
suffix = input_path.suffix.lower()
|
|
if suffix == '.vtt':
|
|
cues = parse_vtt(content)
|
|
elif suffix == '.srt':
|
|
cues = parse_srt(content)
|
|
else:
|
|
raise ValueError(f'Unsupported format: {suffix}')
|
|
return to_markdown(cues)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
if len(sys.argv) < 2:
|
|
print(f'Usage: {sys.argv[0]} <file.vtt|file.srt> [output.md]', file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
input_path = Path(sys.argv[1])
|
|
if not input_path.exists():
|
|
print(f'File not found: {input_path}', file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
md = convert(input_path)
|
|
|
|
output_path = Path(sys.argv[2]) if len(sys.argv) >= 3 else input_path.with_suffix('.md')
|
|
output_path.write_text(md, encoding='utf-8')
|
|
print(f'Saved: {output_path}')
|