6920b634c4
The live fetch no longer re-pulls everything each run: - playlists: re-fetch a playlist's tracks only when its snapshot_id changed (new/deleted playlists handled); state in spotify_playlist table. - liked songs: page newest-first, stop at the newest added_at already seen (watermark in ingest_state). - cover art: download only when the file is missing or the URL changed. New src/ingest/spotify_fetch.py drives this against the low-level SpotifyWebAPI client and upserts straight to the DB; fetch uses it when creds are set (falls back to the cached-JSON ingest otherwise). `fetch --spotify-full` forces a complete resync. Shared upsert helper extracted into spotify_raw. Verified with a mocked API: unchanged re-run does 0 playlist-track fetches and one liked page; a snapshot change re-fetches exactly that playlist. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
84 lines
2.6 KiB
Python
84 lines
2.6 KiB
Python
"""MusicIndexer CLI. Two main workflows plus granular helpers.
|
|
|
|
python main.py fetch # do all the work: pull + scan + parse + enrich + match
|
|
python main.py display # open the GUI to see what you're missing
|
|
|
|
`fetch` is incremental and DB-backed (see Env.py): the first run is slow
|
|
(initial scan + MusicBrainz lookups), later runs only touch what changed.
|
|
Helpers: `enrich` (resume MBID resolution), `match` (print the summary).
|
|
"""
|
|
import argparse
|
|
import logging
|
|
|
|
|
|
def _setup_logging():
|
|
logging.basicConfig(level=logging.INFO, format="%(message)s")
|
|
|
|
|
|
def cmd_fetch(args):
|
|
_setup_logging()
|
|
from src.workflows import run_fetch
|
|
|
|
run_fetch(enrich_limit=args.enrich_limit, enrich=not args.no_enrich,
|
|
spotify_full=args.spotify_full)
|
|
|
|
|
|
def cmd_display(args):
|
|
from src.workflows import run_display
|
|
|
|
run_display()
|
|
|
|
|
|
def cmd_enrich(args):
|
|
_setup_logging()
|
|
from src.db.database import init_db
|
|
from src.enrich.mbid import resolve_mbids, unresolved_count
|
|
|
|
init_db()
|
|
print(f"unresolved before: {unresolved_count(args.source)}")
|
|
print(f"resolved this run: {resolve_mbids(limit=args.limit, source=args.source)}")
|
|
print(f"unresolved after: {unresolved_count(args.source)}")
|
|
|
|
|
|
def cmd_match(args):
|
|
import json
|
|
|
|
from src.match.matcher import summary
|
|
|
|
print(json.dumps(summary(), indent=2))
|
|
|
|
|
|
def build_parser():
|
|
parser = argparse.ArgumentParser(prog="musicindexer", description=__doc__)
|
|
sub = parser.add_subparsers(dest="cmd", required=True)
|
|
|
|
fetch = sub.add_parser("fetch", help="incrementally fetch + scan + enrich + match")
|
|
fetch.add_argument("--enrich-limit", type=int, default=None,
|
|
help="cap MBID lookups this run (default: resolve all)")
|
|
fetch.add_argument("--no-enrich", action="store_true",
|
|
help="skip MusicBrainz enrichment; use MBIDs already on tracks")
|
|
fetch.add_argument("--spotify-full", action="store_true",
|
|
help="force a full Spotify resync (ignore snapshot/watermark)")
|
|
|
|
sub.add_parser("display", help="open the Streamlit GUI")
|
|
|
|
enrich = sub.add_parser("enrich", help="resume MBID resolution only")
|
|
enrich.add_argument("--limit", type=int, default=None)
|
|
enrich.add_argument("--source", choices=["spotify", "itunes", "local"], default=None)
|
|
|
|
sub.add_parser("match", help="print present/missing summary")
|
|
return parser
|
|
|
|
|
|
def main():
|
|
args = build_parser().parse_args()
|
|
{
|
|
"fetch": cmd_fetch,
|
|
"display": cmd_display,
|
|
"enrich": cmd_enrich,
|
|
"match": cmd_match,
|
|
}[args.cmd](args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|