dschlueter/youtube_abschrift_korrigieren
Watch
1
0
Fork
You've already forked youtube_abschrift_korrigieren
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat: Zeitraum-Auswahl (-s/-e) auch in rede_korrigieren.py und extract_text.py

Browse source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter 2026-10-11 19:07:56 +02:00
commit 82489ee83c
1 changed files with 111 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

23
extract_text.py
View file

@ -7,7 +7,7 @@ import shutil
import tempfile
import textwrap
from vtt2txt import vtt_to_lines
from vtt2txt import add_time_options, check_time_range, time_suffix, vtt_to_lines
from yt_untertitel import (
YT_DLP, choose_track, default_name, download, fetch_info, no_track_message,
original_language,
@ -27,13 +27,16 @@ def parse_args():
)
parser.add_argument(
"-o", "--output", type=Path,
help="Ausgabedatei (Standard: <Kanal>_<Titel>_<Datum>.txt)",
help="Ausgabedatei (Standard: <Kanal>_<Titel>_<Datum>.txt, "
"mit -s/-e zusätzlich der Zeitraum)",
)
parser.add_argument(
"-f", "--fliesstext", action="store_true",
help=f"Fließtext, auf {FLOW_WIDTH} Zeichen umbrochen, statt Untertitelzeilen",
)
add_time_options(parser)
args = parser.parse_args()
check_time_range(parser, args)
if args.output is not None and args.output.is_dir():
parser.error(f"-o/--output ist ein Verzeichnis: {args.output}")
@ -42,10 +45,11 @@ def parse_args():
return args
def fetch_text(url, lang=None):
def fetch_text(url, lang=None, start=None, end=None):
"""Download the subtitles of a video; return (video info, text lines).
Without `lang` the language of the original audio is used.
Without `lang` the language of the original audio is used. `start`/`end`
(seconds) keep only the captions of that time range.
"""
info = fetch_info(url)
print(f"Video: {info.get('title', '?')}")
@ -65,17 +69,20 @@ def fetch_text(url, lang=None):
vtt = Path(f"{target_base}.{track}.vtt")
if not vtt.is_file():
raise SystemExit("yt-dlp hat keine Untertitel-Datei geschrieben.")
lines = vtt_to_lines(vtt.read_text(encoding="utf-8-sig"))
lines = vtt_to_lines(vtt.read_text(encoding="utf-8-sig"), start, end)
if not lines:
raise SystemExit("Die Untertitel enthalten keinen Text.")
if start is None and end is None:
raise SystemExit("Die Untertitel enthalten keinen Text.")
raise SystemExit("Die Untertitel enthalten im gewählten Zeitraum keinen Text.")
return info, lines
def main():
args = parse_args()
info, lines = fetch_text(args.url, args.lang)
output = args.output or Path(f"{default_name(info)}.txt")
info, lines = fetch_text(args.url, args.lang, args.start, args.ende)
suffix = time_suffix(args.start, args.ende)
output = args.output or Path(f"{default_name(info)}{suffix}.txt")
if args.fliesstext:
# Never split words, not even at hyphens ("EU-Gipfel")