feat: mehrere Zeitbereiche (-z) mit Zeit-Überschriften in einer Datei

- Zeitformat: 00:05:10 (hⓂ️s), 00:20 (h:m = Minute 20), 25 (Minute 25)
- -z "00:05-00:06 00:10-00:12 00:25": A-B, A (bis Ende), -B (ab Anfang)
- jeder Bereich unter einer Überschrift [HH:MM:SS - HH:MM:SS] mit den
  tatsächlichen Zeiten; nach der Satz-Erweiterung überlappende Blöcke
  werden verschmolzen
- rede_korrigieren.py korrigiert und gliedert jeden Block einzeln; das
  Modell sieht die Überschriften nicht

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

extract_text.py

@@ -7,7 +7,10 @@ import shutil
 import tempfile
 import textwrap
 
-from vtt2txt import add_time_options, check_time_range, time_suffix, vtt_to_lines
+from vtt2txt import (
+    add_time_options, join_segments, resolve_time_ranges, split_segments, time_suffix,
+    vtt_to_text,
+)
 from yt_untertitel import (
     YT_DLP, choose_track, default_name, download, fetch_info, no_track_message,
     original_language,
@@ -28,7 +31,7 @@ def parse_args():
     parser.add_argument(
         "-o", "--output", type=Path,
         help="Ausgabedatei (Standard: <Kanal>_<Titel>_<Datum>.txt, "
-        "mit -s/-e zusätzlich der Zeitraum)",
+        "mit -s/-e/-z zusätzlich die Zeiträume)",
     )
     parser.add_argument(
         "-f", "--fliesstext", action="store_true",
@@ -36,7 +39,7 @@ def parse_args():
     )
     add_time_options(parser)
     args = parser.parse_args()
-    check_time_range(parser, args)
+    resolve_time_ranges(parser, args)
 
     if args.output is not None and args.output.is_dir():
         parser.error(f"-o/--output ist ein Verzeichnis: {args.output}")
@@ -45,12 +48,12 @@ def parse_args():
     return args
 
 
-def fetch_text(url, lang=None, start=None, end=None, exact=False):
-    """Download the subtitles of a video; return (video info, text lines).
+def fetch_text(url, lang=None, ranges=(), exact=False):
+    """Download the subtitles of a video; return (video info, text).
 
-    Without `lang` the language of the original audio is used. `start`/`end`
-    (seconds) keep only the captions of that time range, completed to whole
-    sentences unless `exact`.
+    Without `lang` the language of the original audio is used. With time
+    `ranges` (seconds) the text has one block per range under a header with
+    its actual times, see vtt2txt.vtt_to_text.
     """
     info = fetch_info(url)
     print(f"Video: {info.get('title', '?')}")
@@ -70,35 +73,40 @@ def fetch_text(url, lang=None, start=None, end=None, exact=False):
         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"), start, end, exact)
+        text = vtt_to_text(vtt.read_text(encoding="utf-8-sig"), ranges, exact)
 
-    if not lines:
-        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
+    if not text:
+        if ranges:
+            raise SystemExit("Die Untertitel enthalten im gewählten Zeitraum keinen Text.")
+        raise SystemExit("Die Untertitel enthalten keinen Text.")
+    return info, text
 
 
 def main():
     args = parse_args()
-    info, lines = fetch_text(args.url, args.lang, args.start, args.ende, args.exakt)
-    suffix = time_suffix(args.start, args.ende)
+    info, text = fetch_text(args.url, args.lang, args.bereiche, args.exakt)
+    suffix = time_suffix(args.bereiche)
     output = args.output or Path(f"{default_name(info)}{suffix}.txt")
+    segments = split_segments(text)
 
     if args.fliesstext:
-        # Never split words, not even at hyphens ("EU-Gipfel")
-        text = textwrap.fill(
-            " ".join(lines), width=FLOW_WIDTH,
-            break_long_words=False, break_on_hyphens=False,
-        )
-    else:
-        text = "\n".join(lines)
+        # Each block on its own, headers stay lines of their own; never split
+        # words, not even at hyphens ("EU-Gipfel")
+        segments = [
+            (header, textwrap.fill(
+                " ".join(body.split()), width=FLOW_WIDTH,
+                break_long_words=False, break_on_hyphens=False,
+            ))
+            for header, body in segments
+        ]
+        text = join_segments(segments)
 
     output.parent.mkdir(parents=True, exist_ok=True)
     output.write_text(text + "\n", encoding="utf-8")
     print(
         f"Gespeichert: {output} "
-        f"({len(text.splitlines())} Zeilen, {len(text.split())} Wörter)"
+        f"({len(text.splitlines())} Zeilen, "
+        f"{sum(len(body.split()) for _, body in segments)} Wörter)"
     )