instagramTranscript/cli.py at master · Mrswami/instagramTranscript · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
"""
Instagramtranscript CLI Script.

Command-line execution script for transcribing Instagram Reels and Posts directly
from the terminal without launching a web browser.

Usage:
    python cli.py "https://www.instagram.com/reel/Cxxxxxx/" --model base --outdir ./output
"""

import sys
import argparse
from pathlib import Path
from dotenv import load_dotenv
from transcriber import InstagramTranscriber

load_dotenv()


def main() -> None:
    """
    Parse command-line arguments and run Instagram Transcriber pipeline.
    """
    parser = argparse.ArgumentParser(
        description="Download audio and transcribe Instagram Reels or Posts using OpenAI Whisper AI."
    )
    parser.add_argument("url", help="Instagram Reel or Post URL (e.g. https://www.instagram.com/reel/Cxxxxxx/)")
    parser.add_argument(
        "--model",
        default="base",
        choices=["tiny", "base", "small", "medium"],
        help="Whisper AI model size (default: base)"
    )
    parser.add_argument(
        "--outdir",
        default="output",
        help="Target output directory for audio and transcript files (default: output)"
    )
    parser.add_argument(
        "--api-key",
        default=None,
        help="Optional OpenAI API Key for fast cloud transcription using whisper-1 API"
    )

    args = parser.parse_args()

    print(f"[CLI] Processing Instagram URL: {args.url}")
    transcriber = InstagramTranscriber(output_dir=args.outdir)

    try:
        result = transcriber.process_url(args.url, model_name=args.model, openai_api_key=args.api_key)

        print("\n" + "=" * 50)
        print("=== TRANSCRIPTION COMPLETE ===")
        print("=" * 50)
        print(f"Audio Saved: {result['audio_file']}")
        print("\nTRANSCRIPT:")
        print(result['text'])
        print("=" * 50)

        out_path = Path(args.outdir)
        (out_path / "transcript.txt").write_text(result['text'], encoding="utf-8")
        (out_path / "transcript.srt").write_text(result['srt'], encoding="utf-8")
        (out_path / "transcript.vtt").write_text(result['vtt'], encoding="utf-8")
        (out_path / "transcript.json").write_text(result['json'], encoding="utf-8")

        print(f"[CLI] Saved transcript files (.txt, .srt, .vtt, .json) to folder: {out_path.resolve()}")

    except Exception as e:
        print(f"[CLI Error] Error: {e}", file=sys.stderr)
        sys.exit(1)


if __name__ == "__main__":
    main()