feat: extract_text.py – YouTube-URL → Textdatei in einem Schritt

- Kombiniert yt_untertitel.py und vtt2txt.py; die VTT bleibt temporär
- Standardsprache ist die des Original-Audios (original_language())
- -o Ausgabedatei, Standard output.txt
- Tests ohne Netz, README

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

tests/test_extract_text.py

@@ -0,0 +1,116 @@
+"""Tests for extract_text.py; yt-dlp is always replaced by fakes (no network)."""
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+import extract_text
+import yt_untertitel as yt
+
+URL = "https://www.youtube.com/watch?v=abc123"
+
+VTT = (
+    "WEBVTT\n\n"
+    "00:00:01.000 --> 00:00:02.000\n \nGuten<00:00:01.500><c> Abend.</c>\n\n"
+    "00:00:02.000 --> 00:00:03.000\nGuten Abend.\nSchön, dass Sie da sind.\n"
+)
+
+GERMAN_VIDEO = {
+    "id": "abc123",
+    "title": "Eine Rede",
+    "subtitles": {"en": []},
+    "automatic_captions": {"de-orig": [], "de": [], "en": []},
+}
+
+
+def fake_yt_dlp(info, vtt=VTT):
+    """Stand-in for subprocess.run: answers the info request, writes the VTT file."""
+    calls = []
+
+    def run(command, capture_output, text):
+        calls.append(command)
+        if "--dump-single-json" in command:
+            return subprocess.CompletedProcess(command, 0, json.dumps(info), "")
+        track = command[command.index("--sub-langs") + 1]
+        template = command[command.index("-o") + 1]
+        Path(template.replace("%(ext)s", f"{track}.vtt")).write_text(vtt, encoding="utf-8")
+        return subprocess.CompletedProcess(command, 0, "", "")
+
+    run.calls = calls
+    return run
+
+
+@pytest.fixture(autouse=True)
+def yt_dlp_installed(monkeypatch):
+    monkeypatch.setattr(extract_text.shutil, "which", lambda name: f"/usr/bin/{name}")
+
+
+def run_main(monkeypatch, *args):
+    monkeypatch.setattr(sys, "argv", ["extract_text.py", *map(str, args)])
+    extract_text.main()
+
+
+def test_default_language_is_original_audio(tmp_path, monkeypatch, capsys):
+    run = fake_yt_dlp(GERMAN_VIDEO)
+    monkeypatch.setattr(yt.subprocess, "run", run)
+    monkeypatch.chdir(tmp_path)
+    run_main(monkeypatch, "-u", URL)
+
+    text = (tmp_path / "output.txt").read_text(encoding="utf-8")
+    assert text == "Guten Abend.\nSchön, dass Sie da sind.\n"
+    assert "de-orig" in run.calls[1]
+    assert "--write-auto-subs" in run.calls[1]
+    out = capsys.readouterr().out
+    assert "output.txt (2 Zeilen, 7 Wörter)" in out
+    # Only the text file remains, no VTT
+    assert [p.name for p in tmp_path.iterdir()] == ["output.txt"]
+
+
+def test_explicit_language_prefers_manual(tmp_path, monkeypatch):
+    run = fake_yt_dlp(GERMAN_VIDEO)
+    monkeypatch.setattr(yt.subprocess, "run", run)
+    target = tmp_path / "neu" / "rede.en.txt"
+    run_main(monkeypatch, "-u", URL, "-l", "en", "-o", target)
+
+    assert target.is_file()
+    assert "--write-subs" in run.calls[1]
+
+
+def test_original_language_from_metadata_without_auto_captions(tmp_path, monkeypatch):
+    info = {"id": "x", "language": "fr", "subtitles": {"fr": []}, "automatic_captions": {}}
+    run = fake_yt_dlp(info)
+    monkeypatch.setattr(yt.subprocess, "run", run)
+    run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt")
+    assert run.calls[1][run.calls[1].index("--sub-langs") + 1] == "fr"
+
+
+@pytest.mark.parametrize("info, args, message", [
+    # Translation only: no "en-orig", no manual "en"
+    (GERMAN_VIDEO, ["-l", "fr"], "Keine Untertitel in „fr“"),
+    ({"id": "x", "subtitles": {}, "automatic_captions": {}}, [], "Originalsprache"),
+])
+def test_no_matching_track(tmp_path, monkeypatch, info, args, message):
+    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(info))
+    with pytest.raises(SystemExit, match=message):
+        run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt", *args)
+    assert not (tmp_path / "out.txt").exists()
+
+
+def test_empty_subtitles(tmp_path, monkeypatch):
+    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt="WEBVTT\n"))
+    with pytest.raises(SystemExit, match="keinen Text"):
+        run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt")
+
+
+@pytest.mark.parametrize("args, message", [
+    ([], "required"),
+    (["-u", URL, "-o", "{dir}"], "ist ein Verzeichnis"),
+])
+def test_cli_errors(tmp_path, monkeypatch, capsys, args, message):
+    args = [a.format(dir=tmp_path) for a in args]
+    with pytest.raises(SystemExit) as exc:
+        run_main(monkeypatch, *args)
+    assert exc.value.code == 2
+    assert message in capsys.readouterr().err