alembic/pipeline/lib/manual/backfill-buy-url.py

#!/usr/bin/env python3
"""
backfill-buy-url.py — stamp the Bandcamp purchase URL onto library files for
albums/tracks already imported from a Bandcamp purchase.

The forward path (sync-bandcamp.py) tags new purchases at download time. This
one-shot covers everything bought *before* that change landed. It:

  1. Pulls the current Bandcamp collection (cookies auth) and builds an index
     keyed by (album_artist, album) -> release URL. (Bandcamp's embedded ALBUM
     tag matches the collection item_title exactly, and ALBUMARTIST matches the
     band name — verified against the library.)
  2. Walks the FLAC library, reads ALBUMARTIST/ALBUM, and where a match exists,
     writes the COMMERCIAL_INFORMATION Vorbis comment (AzuraCast maps this to
     the buy_url custom field — see sync-bandcamp.py BUY_URL_TAG).
  3. Optionally tells AzuraCast to reprocess each touched file so the custom
     field repopulates without waiting for the periodic media scan.

Dry-run by default. Stdlib only (mutagen NOT required — uses metaflac).

Usage:
  backfill-buy-url.py --cookies F --state F [--library DIR] [--apply]
                      [--azuracast-key ID:SECRET] [--azuracast-base URL]
                      [--station N] [--force]
"""
import sys, os, re, json, time, html, argparse, subprocess
import urllib.request
from http.cookiejar import MozillaCookieJar
from pathlib import Path

COLLECTION_ITEMS_URL = "https://bandcamp.com/api/fancollection/1/collection_items"
UA = "Mozilla/5.0 (X11; Linux x86_64) backfill-buy-url/1.0"
BUY_URL_TAG = "COMMERCIAL_INFORMATION"


# ---- Bandcamp collection ---------------------------------------------------
def opener(jar):
    return urllib.request.build_opener(urllib.request.HTTPCookieProcessor(jar))


def get_fan_id(username, jar):
    req = urllib.request.Request(f"https://bandcamp.com/{username}",
                                 headers={"User-Agent": UA})
    page = html.unescape(opener(jar).open(req, timeout=60).read().decode("utf-8", "replace"))
    m = re.search(r'"fan_id"\s*:\s*"?(\d+)', page)
    if not m:
        sys.exit("[backfill] could not find fan_id (cookies expired / wrong user?)")
    return int(m.group(1))


def fetch_collection(fan_id, jar):
    items = []
    tok = "9999999999::a::"
    while True:
        body = json.dumps({"fan_id": fan_id, "older_than_token": tok, "count": 100}).encode()
        req = urllib.request.Request(
            COLLECTION_ITEMS_URL, data=body,
            headers={"User-Agent": UA, "Content-Type": "application/json",
                     "Accept": "application/json", "Referer": "https://bandcamp.com/"})
        data = json.loads(opener(jar).open(req, timeout=60).read())
        page = data.get("items", [])
        items.extend(page)
        if not data.get("more_available") or not page:
            break
        nt = data.get("last_token")
        if not nt or nt == tok:
            break
        tok = nt
    return items


# ---- matching --------------------------------------------------------------
def norm(s):
    return re.sub(r"\s+", " ", (s or "").strip()).casefold()


def build_index(items):
    """(album_artist, album) -> url. Index both the bare title and the
    "<title> - Single" form (single-track purchases get that ALBUM tag)."""
    idx = {}
    for it in items:
        url = it.get("item_url")
        band = it.get("band_name")
        title = it.get("item_title")
        if not (url and band and title):
            continue
        for album in (title, f"{title} - Single"):
            idx.setdefault((norm(band), norm(album)), url)
    return idx


def flac_tag(path, name):
    r = subprocess.run(["metaflac", f"--show-tag={name}", path],
                       capture_output=True, text=True)
    for line in r.stdout.splitlines():
        if "=" in line:
            return line.split("=", 1)[1]
    return ""


def set_flac_tag(path, name, value):
    subprocess.run(["metaflac", f"--remove-tag={name}", path], capture_output=True)
    return subprocess.run(["metaflac", f"--set-tag={name}={value}", path],
                          capture_output=True).returncode == 0


# ---- AzuraCast reprocess ---------------------------------------------------
def az_reprocess(base, key, station, host_paths, log):
    """Find each host path in AzuraCast and batch-reprocess so the custom
    field repopulates. host_path -> relative AzuraCast path is library-root
    stripped."""
    root = f"{os.environ.get('MUSIC_DATA_DIR', '/data/music')}/Library/"
    want = {p[len(root):] for p in host_paths if p.startswith(root)}
    headers = {"X-API-Key": key, "Accept": "application/json"}

    def get(path):
        req = urllib.request.Request(base + path, headers=headers)
        return json.loads(urllib.request.urlopen(req, timeout=60).read())

    unique_ids, page = [], 1
    while True:
        d = get(f"/api/station/{station}/files?per_page=500&page={page}")
        for row in d["rows"]:
            if row["path"] in want:
                unique_ids.append(row["unique_id"])
        if page >= d["total_pages"]:
            break
        page += 1
    if not unique_ids:
        log("  no matching AzuraCast files to reprocess")
        return
    body = json.dumps({"do": "reprocess", "files": unique_ids}).encode()
    req = urllib.request.Request(base + f"/api/station/{station}/files/batch",
                                 data=body, method="PUT",
                                 headers={**headers, "Content-Type": "application/json"})
    urllib.request.urlopen(req, timeout=120).read()
    log(f"  queued reprocess for {len(unique_ids)} AzuraCast file(s)")


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--cookies", required=True)
    ap.add_argument("--state", required=True, help="state.json (for reference/logging)")
    ap.add_argument("--library", default=f"{os.environ.get('MUSIC_DATA_DIR', '/data/music')}/Library")
    ap.add_argument("--apply", action="store_true")
    ap.add_argument("--force", action="store_true",
                    help="overwrite an existing buy-link tag")
    ap.add_argument("--azuracast-key", default=None)
    ap.add_argument("--azuracast-base", default=os.environ.get("AZURACAST_BASE", ""))
    ap.add_argument("--station", type=int, default=1)
    ap.add_argument("--username", default=None,
                    help="Bandcamp username; default read from config.env if present")
    args = ap.parse_args()

    user = args.username
    if not user:
        cfg = f"{os.environ.get('ALEMBIC_CONFIG_DIR', '/config')}/pipeline/bandcamp/config.env"
        if os.path.exists(cfg):
            for line in Path(cfg).read_text().splitlines():
                if line.startswith("BANDCAMP_USERNAME="):
                    user = line.split("=", 1)[1].strip().strip('"')
    if not user:
        sys.exit("[backfill] --username required (no config.env BANDCAMP_USERNAME)")

    print(f"[backfill] mode={'APPLY' if args.apply else 'DRY RUN'}  user={user!r}")
    jar = MozillaCookieJar(args.cookies)
    jar.load(ignore_discard=True, ignore_expires=True)
    fan_id = get_fan_id(user, jar)
    items = fetch_collection(fan_id, jar)
    idx = build_index(items)
    print(f"[backfill] collection: {len(items)} items, {len(idx)} match keys")

    flacs = list(Path(args.library).rglob("*.flac"))
    print(f"[backfill] scanning {len(flacs)} FLAC files...\n")

    matched = tagged = already = unmatched = 0
    touched = []
    for p in flacs:
        sp = str(p)
        albumartist = flac_tag(sp, "ALBUMARTIST") or flac_tag(sp, "ARTIST")
        album = flac_tag(sp, "ALBUM")
        url = idx.get((norm(albumartist), norm(album)))
        if not url:
            unmatched += 1
            continue
        matched += 1
        existing = flac_tag(sp, BUY_URL_TAG)
        if existing and not args.force:
            already += 1
            continue
        rel = sp[len(args.library):].lstrip("/")
        print(f"  + {rel}\n      -> {url}")
        if args.apply:
            if set_flac_tag(sp, BUY_URL_TAG, url):
                tagged += 1
                touched.append(sp)
            else:
                print("      ! metaflac write failed")
        else:
            tagged += 1
            touched.append(sp)

    print(f"\n[backfill] matched={matched}  {'tagged' if args.apply else 'would-tag'}={tagged}"
          f"  already-had={already}  unmatched-files={unmatched}")

    if args.apply and touched and args.azuracast_key:
        print("[backfill] telling AzuraCast to reprocess touched files...")
        az_reprocess(args.azuracast_base, args.azuracast_key, args.station,
                     touched, lambda m: print(m))
    elif not args.apply:
        print("[backfill] re-run with --apply to write (add --azuracast-key to reprocess)")


if __name__ == "__main__":
    main()