Initial commit

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

lyrics_dl/__init__.py

@@ -0,0 +1,55 @@
+from typing import Optional
+import traceback
+
+# Initialize classes from lyrics_dl/providers
+import lyrics_dl.providers
+from lyrics_dl.core import Song
+from lyrics_dl.registry import Registry
+from lyrics_dl.config import LyricsDlConfig
+from lyrics_dl.logger import DefaultLogger, AbstractLogger
+
+
+class LyricsDl:
+    logger: AbstractLogger
+
+    def __init__(self, config: LyricsDlConfig = LyricsDlConfig(), logger: AbstractLogger = DefaultLogger()):
+        self.logger = logger
+
+        providers_classes = Registry.get_synced_providers()
+
+        self.providers = []
+
+        for name in config.order:
+            Provider = providers_classes[name]
+            provider_config = config.providers_configs.get(name)
+
+            if not provider_config:
+                provider_config = {}
+
+            try:
+                provider = Provider(**provider_config)
+            except TypeError as e:
+                self.logger.error(f"[lyrics-dl] {e}")
+                continue
+
+            self.providers.append(provider)
+
+    def fetch_lyrics(self, song: Song) -> Optional[str]:
+        self.logger.info(f"[lyrics-dl] Fetching lyrics for \"{song.artist} - {song.title}\"")
+        for provider in self.providers:
+            self.logger.info(f"[{provider.name}] Fetching lyrics...")
+
+            try:
+                lyrics = provider.fetch_lyrics(song)
+            except Exception as e:
+                lyrics = None
+                self.logger.error(f"[{provider.name}] Got exception while fetching lyrics! ({type(e).__name__}: {e})")
+                self.logger.debug(f"[{provider.name}] {traceback.format_exc()}")
+
+            if lyrics:
+                self.logger.info(f"[{provider.name}] Found lyrics!")
+                return lyrics
+
+            self.logger.info(f"[{provider.name}] No lyrics was found!")
+
+        return None

lyrics_dl/__main__.py

@@ -0,0 +1,62 @@
+import argparse
+from pathlib import Path
+
+from lyrics_dl.core import Song
+from lyrics_dl.config import LyricsDlConfig
+from lyrics_dl.logger import DefaultLogger
+from lyrics_dl import LyricsDl
+
+
+logger = DefaultLogger()
+config = LyricsDlConfig()
+lyrics_dl = LyricsDl(config=config, logger=logger)
+
+
+def process_file(path, force=False):
+    lyrics_path = path.with_suffix(".lrc")
+
+    if lyrics_path.exists() and not force:
+        logger.error("[lyrics-dl] Lyrics file already exists!")
+        return
+
+    # TODO handle errors
+    try:
+        song = Song.from_file(path)
+    except Exception as e:
+        logger.error(f"[lyrics-dl] {path}: {e}")
+        return
+
+    lyrics = lyrics_dl.fetch_lyrics(song)
+
+    if not lyrics:
+        logger.error("[lyrics-dl] No lyrics was found!")
+        return
+
+    with open(lyrics_path, "w") as f:
+        f.write(lyrics)
+
+
+def process_directory(path, extensions):
+    for file_path in path.rglob("*"):
+        if file_path.suffix[1:] not in extensions:
+            continue
+
+        process_file(file_path)
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("path", type=Path, help="Path to the song file or directory")
+parser.add_argument("-e", "--extensions", type=str, help="Music files extensions, separated by a comma. For example: wav,flac,mp3")
+parser.add_argument("-f", "--force-override", action="store_true", help="Force override .lrc file, if it already exists")
+
+args = parser.parse_args()
+
+if args.path.is_dir():
+    if not args.extensions:
+        extensions = ["flac", "alac", "mp3", "m4a", "mp4", "aac", "wav", "opus", "ogg"]
+    else:
+        extensions = args.extensions.split(",")
+
+    process_directory(args.path, extensions)
+else:
+    process_file(args.path)

lyrics_dl/config.py

@@ -0,0 +1,20 @@
+from typing import Self
+import tomllib
+from dataclasses import dataclass, field
+from pathlib import Path
+
+
+@dataclass
+class LyricsDlConfig:
+    order: list[str] = field(default_factory=lambda: ["kugou", "youtube"])
+    providers_configs: dict[str, dict] = field(default_factory=lambda: {})
+
+    @classmethod
+    def from_file(cls, path: Path) -> Self:
+        with open(path, "rb") as f:
+            config = tomllib.load(f)
+
+        return cls(
+            order=config["providers"].pop("order"),
+            providers_configs=config["providers"],
+        )

lyrics_dl/core.py

@@ -0,0 +1,38 @@
+from dataclasses import dataclass
+from abc import ABC, abstractmethod
+from typing import Optional, Self
+from pathlib import Path
+import mutagen
+
+
+@dataclass
+class Song:
+    title: str
+    artist: str
+    album: Optional[str] = None
+    duration: Optional[int] = None
+
+    @classmethod
+    def from_file(cls, path: Path) -> Self:
+        metadata = mutagen.File(path)
+
+        if "title" not in metadata or "artist" not in metadata:
+            raise RuntimeError("Song is missing title or artist name")
+
+        title = ", ".join(metadata.get("title"))
+        artist = ", ".join(metadata.get("artist"))
+
+        album = metadata.get("album")
+        if album:
+            album = ", ".join(album)
+
+        duration = metadata.info.length
+
+        return cls(title=title, artist=artist, album=album, duration=duration)
+
+
+class AbstractProvider(ABC):
+    name: str = ""
+    @abstractmethod
+    def fetch_lyrics(self, song: Song) -> Optional[str]:
+        pass

lyrics_dl/logger.py

@@ -0,0 +1,55 @@
+from typing import Self
+from abc import ABC, abstractmethod
+import logging
+
+
+class AbstractLogger(ABC):
+    @abstractmethod
+    def debug(self, message: str) -> None:
+        pass
+
+    @abstractmethod
+    def info(self, message: str) -> None:
+        pass
+
+    @abstractmethod
+    def warning(self, message: str) -> None:
+        pass
+
+    @abstractmethod
+    def error(self, message: str) -> None:
+        pass
+
+
+class DefaultLogger(AbstractLogger):
+    __instance = None
+    __initialized = False
+
+    def __new__(cls) -> Self:
+        if cls.__instance is None:
+            cls.__instance = AbstractLogger.__new__(cls)
+        return cls.__instance
+
+    def __init__(self) -> None:
+        if self.__initialized:
+            return
+        self.__initialized = True
+
+        self.logger = logging.getLogger("lyrics-dl")
+        self.logger.setLevel(logging.DEBUG)
+
+        console_handler = logging.StreamHandler()
+        console_handler.setLevel(logging.DEBUG)
+        self.logger.addHandler(console_handler)
+
+    def debug(self, message: str) -> None:
+        self.logger.debug(message)
+
+    def info(self, message: str) -> None:
+        self.logger.info(message)
+
+    def warning(self, message: str) -> None:
+        self.logger.warning(message)
+
+    def error(self, message: str) -> None:
+        self.logger.error(message)

lyrics_dl/providers/__init__.py

@@ -0,0 +1,3 @@
+from lyrics_dl.providers import musixmatch
+from lyrics_dl.providers import kugou
+from lyrics_dl.providers import youtube

lyrics_dl/providers/kugou.py

@@ -0,0 +1,80 @@
+from typing import Optional, Iterable
+from base64 import b64decode
+import zlib
+import re
+from itertools import filterfalse, islice
+from datetime import datetime
+
+import httpx
+
+from lyrics_dl.core import Song, AbstractProvider
+from lyrics_dl.registry import lyrics_provider
+
+
+KRC_ENCODE_KEY = [64, 71, 97, 119, 94, 50, 116, 71, 81, 54, 49, 45, 206, 210, 110, 105]
+
+RE_KRC_JUNK = re.compile(r"^\[((id|ar|ti|by|hash|al|sign|qq|total|language):|offset:0\]|.*\]<.*>?(Written by：|Lyrics by：|Composed by：|Producer：|作曲 :|作词 :)).*$")
+RE_WORD_TIMING = re.compile(r"<\d+,\d+,\d+>")
+
+
+def decode_krc(content: bytes) -> str:
+    content = b64decode(content)
+
+    buf = bytearray(len(content) - 4)
+    for i in range(4, len(content)):
+        buf[i - 4] = content[i] ^ KRC_ENCODE_KEY[(i - 4) % 16]
+
+    return zlib.decompress(buf).decode('utf-8-sig')
+
+
+def reformat_timings(lines: Iterable[str]) -> Iterable[str]:
+    for line in lines:
+        if not line.startswith("["):
+            yield line
+            continue
+
+        line = RE_WORD_TIMING.sub("", line)
+
+        raw_timings, text = line.split("]", 1)
+        beginning, _ = map(int, raw_timings[1:].split(","))
+
+        timing = datetime.fromtimestamp(beginning / 1000).strftime("%M:%S.%f")[:8]
+
+        yield f"[{timing}]{text}"
+
+
+@lyrics_provider
+class Kugou(AbstractProvider):
+    name = "kugou"
+
+    def fetch_lyrics(self: AbstractProvider, song: Song) -> Optional[str]:
+        keyword = f"{song.artist} - {song.title}"
+
+        response = httpx.get("https://krcs.kugou.com/search", params={
+            "ver": 1,
+            "man": "yes",
+            "client": "mobi",
+            "keyword": keyword
+        }).json()
+
+        candidates = response["candidates"]
+
+        if not candidates:
+            return None
+
+        id_, accesskey = candidates[0]["id"], candidates[0]["accesskey"]
+
+        r = httpx.get("https://krcs.kugou.com/download", params={
+            "ver": 1,
+            "man": "yes",
+            "client": "mobi",
+            "format": "lrc",
+            "id": id_,
+            "accesskey": accesskey
+        }).json()
+
+        krc = decode_krc(r["content"])
+
+        lines = reformat_timings(islice(filterfalse(RE_KRC_JUNK.match, krc.splitlines()), 1, None))
+
+        return "\n".join(lines)

lyrics_dl/providers/musixmatch.py

@@ -0,0 +1,36 @@
+from typing import Optional
+import httpx
+
+from lyrics_dl.core import Song, AbstractProvider
+from lyrics_dl.registry import lyrics_provider
+
+
+@lyrics_provider
+class Musixmatch(AbstractProvider):
+    name = "musixmatch"
+
+    def __init__(self, token: str) -> None:
+        self.token = token
+
+    def fetch_lyrics(self, song: Song) -> Optional[str]:
+        response = httpx.get("https://apic-desktop.musixmatch.com/ws/1.1/macro.subtitles.get", params={
+            "format": "json",
+            "namespace": "lyrics_synched",
+            "part": "lyrics_crowd,user,lyrics_verified_by",
+            "user_language": "en",
+            "f_subtitle_length_max_deviation": 1,
+            "subtitle_format": "lrc",
+            "app_id": "web-desktop-app-v1.0",
+            "usertoken": self.token,
+
+            "q_artist": song.artist,
+            "q_track": song.title,
+            "q_album": song.album,
+        }, follow_redirects=True).json()
+
+        response = response["message"]["body"]["macro_calls"]["track.subtitles.get"]["message"]["body"]
+
+        if not response:
+            return None
+
+        return response["subtitle_list"][0]["subtitle"]["subtitle_body"]

lyrics_dl/providers/youtube.py

@@ -0,0 +1,79 @@
+from typing import Optional, Dict
+from contextlib import redirect_stdout
+import subprocess
+import io
+import urllib
+import unittest.mock
+
+from yt_dlp import YoutubeDL
+
+from lyrics_dl.core import Song, AbstractProvider
+from lyrics_dl.registry import lyrics_provider
+from lyrics_dl import utils
+
+
+@lyrics_provider
+class Youtube(AbstractProvider):
+    name = "youtube"
+
+    def _craft_search_link(self, song: Song) -> str:
+        query = f"{song.artist} - {song.title}"
+        query = urllib.parse.quote(query)
+        # sp=... means search only videos with subtitles
+        url = f"https://www.youtube.com/results?search_query={query}&sp=EgIoAQ%253D%253D"
+        return url
+
+    def _download_subtitles(self, video_id: str) -> str:
+        # buffer = io.BytesIO()
+        buffer = io.StringIO()
+
+        # A dirty monkey patch; youtube-dl does not
+        # support "-" filename for subtitles, so we
+        # just force it to use it here.
+        with unittest.mock.patch("yt_dlp.YoutubeDL.subtitles_filename", new=lambda *_: "-"):
+            with redirect_stdout(buffer):
+                with YoutubeDL({"writesubtitles": True, "skip_download": True, "subtitlesformat": "srt/vtt/best", 'logtostderr': True}) as ydl:
+                    ydl.download(video_id)
+
+        return buffer.getvalue()
+
+    def _subtitles_to_lyrics(self, subtitles: str) -> str:
+        # "-fflags +bitexact" prevents ffmpeg from
+        # writing metadata to .lrc file
+        # TODO: use `with` statement
+        process = subprocess.Popen(["ffmpeg", "-loglevel", "quiet", "-i", "-", "-f", "lrc", "-fflags", "+bitexact", "-"], stdin=subprocess.PIPE, stdout=subprocess.PIPE)
+
+        if not process.stdin or not process.stdout:
+            return ""
+
+        process.stdin.write(subtitles.encode())
+        process.stdin.close()
+        process.wait()
+        return process.stdout.read().decode()[1:]
+
+    def fetch_lyrics(self, song: Song) -> Optional[str]:
+        search_link = self._craft_search_link(song)
+        with YoutubeDL({"extract_flat": True, "playlistend": 10}) as ydl:
+            videos = ydl.extract_info(search_link)["entries"]
+
+        if song.duration:
+            def match_duration(video: Dict) -> bool:
+                return utils.threshold_equal(video["duration"], song.duration, 2)
+            videos = filter(match_duration, videos)
+
+        def match_title(video: Dict) -> bool:
+            return True
+        videos = filter(match_title, videos)
+
+        video = utils.next_or_none(videos)
+
+        if not video:
+            return None
+
+        subtitles = self._download_subtitles(video["id"])
+        lyrics = self._subtitles_to_lyrics(subtitles)
+
+        if lyrics != "":
+            return lyrics
+
+        return None

lyrics_dl/registry.py

@@ -0,0 +1,20 @@
+from lyrics_dl.core import AbstractProvider
+
+
+class Registry:
+    providers: dict[str, type[AbstractProvider]] = {}
+
+    @staticmethod
+    def get_synced_providers() -> dict[str, type[AbstractProvider]]:
+        # TODO: stub
+        return dict(Registry.providers)
+
+    @staticmethod
+    def register_provider(provider_class: type[AbstractProvider]) -> None:
+        Registry.providers[provider_class.name] = provider_class
+
+
+def lyrics_provider(cls: type[AbstractProvider]) -> type[AbstractProvider]:
+    Registry.register_provider(cls)
+
+    return cls

lyrics_dl/utils.py

@@ -0,0 +1,14 @@
+from typing import Iterator, Optional, TypeVar
+
+
+def threshold_equal(a: float, b: float, epsilon: float) -> bool:
+    return abs(a - b) <= epsilon
+
+
+T = TypeVar('T')
+
+def next_or_none(iterator: Iterator[T]) -> Optional[T]:
+    try:
+        return next(iterator)
+    except StopIteration:
+        return None