music-mirror/tools/submit_scrobbles.py

#!/usr/bin/env python3
"""Submit a Rockbox scrobbler log to Last.fm, then set it aside.

Rockbox writes /.scrobbler.log on the device in AUDIOSCROBBLER 1.1 format: one
tab-separated line per track, rated `L` for listened or `S` for skipped. Only
the listened ones are submitted; a skip is not a play.

Scrobbling is a write method, so unlike everything else here it needs the API
secret and a session key, obtained once through the browser. Read-only calls
elsewhere in these projects need neither.
"""

import argparse
import hashlib
import json
import os
import sys
import time
import urllib.error
import urllib.parse
import urllib.request
from pathlib import Path

API_ROOT = "https://ws.audioscrobbler.com/2.0/"

# Last.fm's documented ceiling for one track.scrobble call.
BATCH = 50

# Rockbox names the log for whether the target has a real-time clock. Without
# one every timestamp it writes is zero, which is not a time anything can
# scrobble.
LOG_NAMES = (".scrobbler.log", ".scrobbler-timeless.log")

# Rockbox core writes this whenever "play log" is on, with no plugin running:
#     timestamp:elapsed_ms:length_ms:/Music/Artist/Album/Track.mp3
# It is rotated once it grows past half a megabyte. Converting it needs tags,
# which is why the on-device plugin exists -- reading them back off the player
# is slow. Off the mirror it is free, so the plugin can be skipped entirely.
PLAYBACK_LOG_NAMES = ("playback.log", "playback_*.log")

# The plugin counts a track as listened at savepct of its length, defaulting to
# fifty. Same rule here, or the two disagree about what a play is.
LISTENED_FRACTION = 0.5

# Below this a timestamp is not a wall-clock time. Without a real-time clock
# Rockbox logs ticks in milliseconds instead, which is not a date.
EARLIEST_PLAUSIBLE = 1_000_000_000

SESSION_FILE = Path(
    os.getenv("XDG_CONFIG_HOME", Path.home() / ".config")
) / "music-mirror" / "lastfm.json"


class LastfmError(Exception):
    """A Last.fm request that failed."""


def parse_log(text):
    """Return the listened tracks in an AUDIOSCROBBLER log, oldest first.

    Fields are artist, album, title, track number, length, rating, timestamp
    and MusicBrainz id. Rockbox converts any tab inside a field to a space
    before writing, so splitting on tabs is safe.
    """
    played, skipped, timeless = [], 0, 0
    for line in text.splitlines():
        if not line or line.startswith("#"):
            continue
        fields = line.split("\t")
        if len(fields) < 7:
            continue
        artist, album, title, number, length, rating, timestamp = fields[:7]
        mbid = fields[7] if len(fields) > 7 else ""
        if rating.strip().upper() != "L":
            skipped += 1
            continue
        try:
            when = int(timestamp)
        except ValueError:
            continue
        if when <= 0:
            timeless += 1
            continue
        if not artist or not title:
            continue
        played.append(
            {
                "artist": artist,
                "album": album,
                "track": title,
                "trackNumber": number if number not in ("", "-1") else "",
                "duration": length if length.isdigit() and int(length) > 0 else "",
                "timestamp": str(when),
                "mbid": mbid,
            }
        )
    played.sort(key=lambda entry: int(entry["timestamp"]))
    return played, skipped, timeless


def parse_playback_log(text):
    """Return (timestamp, elapsed_ms, length_ms, path) for each logged play."""
    plays = []
    for line in text.splitlines():
        fields = line.strip().split(":", 3)
        if len(fields) != 4:
            continue
        stamp, elapsed, length, path = fields
        try:
            plays.append((int(stamp), int(elapsed), int(length), path))
        except ValueError:
            continue
    return plays


def device_to_local(path, device_prefix, mirror):
    """Map a path as the player sees it onto the mirror it was copied from."""
    prefix = "/" + device_prefix.strip("/")
    if prefix != "/":
        if not path.startswith(prefix + "/"):
            return None
        path = path[len(prefix) :]
    return Path(mirror) / path.lstrip("/")


def read_tags(path, runner=None):
    """Return the tags of a local file, via ffprobe."""
    runner = runner or _ffprobe
    try:
        payload = json.loads(runner(path))
    except (OSError, ValueError):
        return {}
    return {
        key.lower(): value
        for key, value in (payload.get("format", {}).get("tags") or {}).items()
    }


def _ffprobe(path):
    import subprocess

    return subprocess.run(
        ["ffprobe", "-v", "error", "-show_entries", "format_tags",
         "-of", "json", str(path)],
        capture_output=True, text=True, check=True,
    ).stdout


def plays_from_playback_log(text, device_prefix, mirror, runner=None):
    """Return submittable entries, plus counts of what was left out.

    Skips are decided by the same fraction the on-device plugin uses, so the
    two never disagree about what counted as a play.
    """
    played, skipped, unresolved, timeless = [], 0, 0, 0
    for stamp, elapsed, length, device_path in parse_playback_log(text):
        if stamp < EARLIEST_PLAUSIBLE:
            timeless += 1
            continue
        if length > 0 and elapsed < length * LISTENED_FRACTION:
            skipped += 1
            continue
        local = device_to_local(device_path, device_prefix, mirror)
        tags = read_tags(local, runner) if local and local.is_file() else {}
        artist = tags.get("artist") or tags.get("album_artist") or ""
        title = tags.get("title") or ""
        if not artist or not title:
            unresolved += 1
            continue
        played.append(
            {
                "artist": artist,
                "track": title,
                "album": tags.get("album", ""),
                "trackNumber": (tags.get("track") or "").split("/")[0],
                "duration": str(length // 1000) if length > 0 else "",
                "timestamp": str(stamp),
                "mbid": tags.get("musicbrainz_trackid", ""),
            }
        )
    played.sort(key=lambda entry: int(entry["timestamp"]))
    return played, skipped, unresolved, timeless


def find_playback_logs(device):
    """Return every playback log on a device, oldest first."""
    found = []
    for pattern in PLAYBACK_LOG_NAMES:
        found.extend(sorted(Path(device).glob(f".rockbox/{pattern}")))
    return [path for path in found if path.is_file() and path.stat().st_size]


def sign(params, secret):
    """Return Last.fm's method signature for a set of parameters.

    Names are sorted by the ASCII table rather than numerically, which is why
    `artist[10]` comes before `artist[1]`. Getting that wrong produces an
    invalid signature and nothing else.
    """
    joined = "".join(f"{name}{params[name]}" for name in sorted(params))
    return hashlib.md5((joined + secret).encode("utf-8")).hexdigest()  # noqa: S324


def post(params, transport):
    """Sign, post, and return the decoded response."""
    body = urllib.parse.urlencode(params).encode("utf-8")
    request = urllib.request.Request(API_ROOT, data=body)
    try:
        payload = json.loads(transport(request))
    except urllib.error.HTTPError as error:
        detail = error.read().decode("utf-8", "replace")[:300]
        raise LastfmError(f"HTTP {error.code}: {detail}") from error
    except (urllib.error.URLError, TimeoutError, json.JSONDecodeError) as error:
        raise LastfmError(str(error)) from error
    if payload.get("error"):
        raise LastfmError(f"error {payload['error']}: {payload.get('message', '')}")
    return payload


def call(method, params, key, secret, session, transport):
    """Make one signed, authenticated call."""
    full = {**params, "method": method, "api_key": key}
    if session:
        full["sk"] = session
    full["api_sig"] = sign(full, secret)
    full["format"] = "json"
    return post(full, transport)


def authorise(key, secret, transport, opener=print):
    """Walk the one-time browser authorisation and return a session key."""
    token = call("auth.getToken", {}, key, secret, None, transport)["token"]
    url = f"https://www.last.fm/api/auth/?api_key={key}&token={token}"
    opener(f"Open this, approve the application, then press Enter:\n\n  {url}\n")
    input()
    session = call("auth.getSession", {"token": token}, key, secret, None, transport)
    return session["session"]["key"]


def load_session():
    if SESSION_FILE.is_file():
        return json.loads(SESSION_FILE.read_text(encoding="utf-8")).get("session")
    return None


def save_session(session):
    SESSION_FILE.parent.mkdir(parents=True, exist_ok=True)
    SESSION_FILE.write_text(json.dumps({"session": session}), encoding="utf-8")
    SESSION_FILE.chmod(0o600)


def batch_params(entries):
    """Return the indexed parameters for one track.scrobble call."""
    params = {}
    for index, entry in enumerate(entries):
        for name in ("artist", "track", "timestamp", "album", "trackNumber", "duration", "mbid"):
            if entry.get(name):
                params[f"{name}[{index}]"] = entry[name]
    return params


def submit(entries, key, secret, session, transport, delay=1.0):
    """Submit every entry. Returns how many the service accepted.

    Batches are counted as they succeed rather than at the end, so a failure
    partway through leaves an honest number and the caller can keep the rest of
    the log instead of losing it.
    """
    accepted = 0
    for start in range(0, len(entries), BATCH):
        chunk = entries[start : start + BATCH]
        payload = call(
            "track.scrobble", batch_params(chunk), key, secret, session, transport
        )
        block = payload.get("scrobbles", {})
        summary = block.get("@attr", block)
        accepted += int(summary.get("accepted", len(chunk)))
        ignored = int(summary.get("ignored", 0))
        if ignored:
            print(f"  {ignored} of {len(chunk)} ignored by Last.fm", file=sys.stderr)
        if start + BATCH < len(entries):
            time.sleep(delay)
    return accepted


def http_post(request, timeout=30):
    with urllib.request.urlopen(request, timeout=timeout) as response:  # noqa: S310
        return response.read().decode("utf-8")


def find_log(device):
    """Return the scrobbler log on a mounted device, or None."""
    for name in LOG_NAMES:
        candidate = Path(device) / name
        if candidate.is_file() and candidate.stat().st_size:
            return candidate
    return None


def main(argv=None, transport=http_post):
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("device", help="the mounted device, or a scrobbler log file")
    parser.add_argument(
        "--mirror",
        help="the mirror the device was copied from. Given this, Rockbox's own"
        " playback.log is converted here rather than needing the on-device"
        " plugin run first",
    )
    parser.add_argument(
        "--device-prefix",
        default="/Music",
        help="where the music sits on the device, stripped when mapping a logged"
        " path back onto the mirror",
    )
    parser.add_argument("--api-key", default=os.getenv("LASTFM_API_KEY"))
    parser.add_argument("--api-secret", default=os.getenv("LASTFM_API_SECRET"))
    parser.add_argument("--dry-run", action="store_true", help="parse and report only")
    parser.add_argument(
        "--keep", action="store_true", help="do not set the log aside afterwards"
    )
    args = parser.parse_args(argv)

    target = Path(args.device)
    log = target if target.is_file() else find_log(target)
    logs = []

    if log is not None:
        played, skipped, timeless = parse_log(
            log.read_text(encoding="utf-8", errors="replace")
        )
        unresolved = 0
        logs = [log]
        print(f"{log}: {len(played)} listened, {skipped} skipped", file=sys.stderr)
    elif args.mirror:
        # No plugin has been run, but the core log is there. Tags come off the
        # mirror, which is the only reason the plugin was needed at all.
        logs = find_playback_logs(target)
        if not logs:
            print("no scrobbler log to submit", file=sys.stderr)
            return 0
        text = "\n".join(
            path.read_text(encoding="utf-8", errors="replace") for path in logs
        )
        played, skipped, unresolved, timeless = plays_from_playback_log(
            text, args.device_prefix, args.mirror
        )
        print(
            f"{len(logs)} playback log(s): {len(played)} listened, {skipped} skipped",
            file=sys.stderr,
        )
        if unresolved:
            print(
                f"  {unresolved} could not be matched to a file in the mirror"
                " and were left out",
                file=sys.stderr,
            )
    else:
        print(
            "no scrobbler log to submit. Rockbox's own playback.log can be used"
            " instead -- pass --mirror so tags can be read from it.",
            file=sys.stderr,
        )
        return 0

    if timeless:
        print(
            f"  {timeless} entries have no timestamp, so this target has no clock."
            " They cannot be scrobbled without inventing when they happened.",
            file=sys.stderr,
        )
    if not played:
        return 0
    if args.dry_run:
        for entry in played[:20]:
            print(f"{entry['timestamp']}\t{entry['artist']}\t{entry['track']}")
        return 0

    if not args.api_key or not args.api_secret:
        print(
            "scrobbling is a write method: it needs LASTFM_API_KEY and"
            " LASTFM_API_SECRET, not just the read-only key",
            file=sys.stderr,
        )
        return 2

    session = load_session()
    if not session:
        session = authorise(args.api_key, args.api_secret, transport)
        save_session(session)

    try:
        accepted = submit(played, args.api_key, args.api_secret, session, transport)
    except LastfmError as error:
        print(f"submission failed: {error}", file=sys.stderr)
        return 1

    print(f"{accepted} scrobbles accepted", file=sys.stderr)
    if not args.keep and accepted:
        # Renamed rather than deleted: if Last.fm quietly dropped something,
        # the evidence is still on the device.
        for path in logs:
            aside = path.with_name(f"{path.name}.{played[-1]['timestamp']}.submitted")
            path.rename(aside)
            print(f"log moved to {aside.name}", file=sys.stderr)
    return 0


if __name__ == "__main__":
    sys.exit(main())