feat: musicbrainz overall search

music_kraken/connection/cache.py

@@ -6,6 +6,7 @@ from typing import List, Optional
 from functools import lru_cache
 import logging
 
+from ..utils import output, BColors
 from ..utils.config import main_settings
 from ..utils.string_processing import fit_to_file_system
 
@@ -204,9 +205,12 @@ class Cache:
         for path in self._dir.iterdir():
             if path.is_dir():
                 for file in path.iterdir():
+                    output(f"Deleting file {file}", color=BColors.GREY)
                     file.unlink()
+                output(f"Deleting folder {path}", color=BColors.HEADER)
                 path.rmdir()
             else:
+                output(f"Deleting folder {path}", color=BColors.HEADER)
                 path.unlink()
 
         self.cached_attributes.clear()

music_kraken/download/page_attributes.py

@@ -30,7 +30,7 @@ from ..utils.exception import MKMissingNameException
 from ..utils.exception.download import UrlNotFoundException
 from ..utils.shared import DEBUG_PAGES
 
-from ..pages import Page, EncyclopaediaMetallum, Musify, YouTube, YoutubeMusic, Bandcamp, Genius, INDEPENDENT_DB_OBJECTS
+from ..pages import Page, EncyclopaediaMetallum, Musify, YouTube, YoutubeMusic, Bandcamp, Musicbrainz, Genius, INDEPENDENT_DB_OBJECTS
 
 
 ALL_PAGES: Set[Type[Page]] = {
@@ -38,7 +38,8 @@ ALL_PAGES: Set[Type[Page]] = {
     Genius,
     Musify,
     YoutubeMusic,
-    Bandcamp
+    Bandcamp,
+    Musicbrainz
 }
 
 if youtube_settings["use_youtube_alongside_youtube_music"]:

music_kraken/pages/__init__.py

@@ -1,5 +1,6 @@
 from .encyclopaedia_metallum import EncyclopaediaMetallum
 from .musify import Musify
+from .musicbrainz import Musicbrainz
 from .youtube import YouTube
 from .youtube_music import YoutubeMusic
 from .bandcamp import Bandcamp

music_kraken/pages/genius.py

@@ -134,7 +134,7 @@ class Genius(Page):
                 source_list=[source],
                 artist_list=[self.parse_api_object(data.get("artist"))],
                 artwork=artwork,
-                date=ID3Timestamp(**data.get("release_date_components", {})),
+                date=ID3Timestamp(**(data.get("release_date_components") or {})),
             )
 
         if object_type == "song":

music_kraken/pages/musicbrainz.py

@@ -0,0 +1,145 @@
+from collections import defaultdict
+from dataclasses import dataclass
+from enum import Enum
+from typing import List, Optional, Type, Union, Generator, Dict, Any
+from urllib.parse import urlparse
+
+import pycountry
+import musicbrainzngs
+from bs4 import BeautifulSoup
+
+from ..connection import Connection
+from .abstract import Page
+from ..utils.enums import SourceType, ALL_SOURCE_TYPES
+from ..utils.enums.album import AlbumType, AlbumStatus
+from ..objects import (
+    Artist,
+    Source,
+    Song,
+    Album,
+    ID3Timestamp,
+    FormattedText,
+    Label,
+    Target,
+    DatabaseObject,
+    Lyrics,
+    Artwork
+)
+from ..utils.config import logging_settings, main_settings
+from ..utils import string_processing, shared
+from ..utils.string_processing import clean_song_title
+from ..utils.support_classes.query import Query
+from ..utils.support_classes.download_result import DownloadResult
+
+
+
+class Musicbrainz(Page):
+    SOURCE_TYPE = ALL_SOURCE_TYPES.MUSICBRAINZ
+
+    HOST = "https://musicbrainz.org"
+
+    def __init__(self, *args, **kwargs):
+        musicbrainzngs.set_useragent("mk", "1")
+
+        super().__init__(*args, **kwargs)
+    
+    def general_search(self, search_query: str) -> List[DatabaseObject]:
+        search_results = []
+
+        #Artist
+        search_results += self.artist_search(search_query).copy()
+
+        #Album
+        search_results += self.album_search(search_query).copy()
+
+        #Song
+        search_results += self.song_search(search_query).copy()
+
+        return search_results
+
+    def artist_search(self, search_query: str) -> List[Artist]:
+        artist_list = []
+        
+        #Artist
+        artist_dict_list: list = musicbrainzngs.search_artists(search_query)['artist-list']
+        artist_source_list: List[Source] = []
+        for artist_dict in artist_dict_list:
+            artist_source_list.append(Source(self.SOURCE_TYPE, self.HOST + "/artist/" + artist_dict['id']))
+            artist_list.append(Artist(
+                name=artist_dict['name'],
+                source_list=artist_source_list
+            ))
+  
+        return artist_list
+
+    def song_search(self, search_query: str) -> List[Song]:
+        song_list = []
+
+        #Song
+        song_dict_list: list = musicbrainzngs.search_recordings(search_query)['recording-list']
+        song_source_list: List[Source] = [] 
+        for song_dict in song_dict_list:
+            song_source_list.append(Source(self.SOURCE_TYPE, self.HOST + "/recording/" + song_dict['id'])) 
+            song_list.append(Song(
+                title=song_dict['title'],
+                source_list=song_source_list
+            )) 
+
+        return song_list
+    
+    def album_search(self, search_query: str) -> List[Album]:
+        album_list = []
+
+        #Album
+        album_dict_list: list = musicbrainzngs.search_release_groups(search_query)['release-group-list']
+        album_source_list: List[Source] = []
+        for album_dict in album_dict_list:
+            album_source_list.append(Source(self.SOURCE_TYPE, self.HOST + "/release-group/" + album_dict['id']))
+            album_list.append(Album(
+                title=album_dict['title'],
+                source_list=album_source_list
+            ))
+
+        return album_list
+
+
+    def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
+        album_list = []
+
+        #Album
+        album_dict_list: list = musicbrainzngs.search_release_groups(search_query)['release-group-list']
+        album_source_list: List[Source] = []
+        for album_dict in album_dict_list:
+            album_source_list.append(Source(self.SOURCE_TYPE, self.HOST + "/release-group/" + album_dict['id']))
+            album_list.append(Album(
+                title=album_dict['title'],
+                source_list=album_source_list
+            ))
+
+    def fetch_artist(self, source: Source, stop_at_level: int = 1) -> Artist:
+        artist_list = []
+        
+        #Artist
+        artist_dict_list: list = musicbrainzngs.search_artists(search_query)['artist-list']
+        artist_source_list: List[Source] = []
+        for artist_dict in artist_dict_list:
+            artist_source_list.append(Source(self.SOURCE_TYPE, self.HOST + "/artist/" + artist_dict['id']))
+            artist_list.append(Artist(
+                name=artist_dict['name'],
+                source_list=artist_source_list,
+            ))
+
+    def fetch_song(self, source: Source, stop_at_level: int = 1) -> Song:
+        song_list = []
+
+        #Song
+        song_dict_list: list = musicbrainzngs.search_recordings(search_query)['recording-list']
+        song_source_list: List[Source] = [] 
+        for song_dict in song_dict_list:
+            song_source_list.append(Source(self.SOURCE_TYPE, self.HOST + "/recording/" + song_dict['id'])) 
+            song_list.append(Song(
+                title=song_dict['title'],
+                source_list=song_source_list
+            )) 
+    
+        

music_kraken/pages/youtube_music/youtube_music.py

@@ -549,6 +549,11 @@ class YoutubeMusic(SuperYouTube):
         return album
 
     def fetch_lyrics(self, video_id: str, playlist_id: str = None) -> str:
+        """
+        1. fetches the tabs of a song, to get the browse id
+        2. finds the browse id of the lyrics
+        3. fetches the lyrics with the browse id
+        """
         request_data = {
             "context": {**self.credentials.context, "adSignalsInfo": {"params": []}},
             "videoId": video_id,
@@ -575,6 +580,7 @@ class YoutubeMusic(SuperYouTube):
             pageType = traverse_json_path(tab, "tabRenderer.endpoint.browseEndpoint.browseEndpointContextSupportedConfigs.browseEndpointContextMusicConfig.pageType", default="")
             if pageType in ("MUSIC_TAB_TYPE_LYRICS", "MUSIC_PAGE_TYPE_TRACK_LYRICS") or "lyrics" in pageType.lower():
                 browse_id = traverse_json_path(tab, "tabRenderer.endpoint.browseEndpoint.browseId", default=None)
+                if browse_id is not None:
                     break
 
         if browse_id is None:
@@ -721,7 +727,6 @@ class YoutubeMusic(SuperYouTube):
 
         self.download_values_by_url[source.url] = {
             "url": _best_format.get("url"),
-            "chunk_size": _best_format.get("downloader_options", {}).get("http_chunk_size", main_settings["chunk_size"]),
             "headers": _best_format.get("http_headers", {}),
         }
 

music_kraken/utils/config/config_files/logging_config.py

@@ -59,6 +59,11 @@ Reference for the logging formats: https://docs.python.org/3/library/logging.htm
         description="The logger for the musify scraper.",
         default_value="musify"
     ),
+    LoggerAttribute(
+        name="musicbrainz_logger",
+        description="The logger for the musicbrainz scraper.",
+        default_value="musicbrainz"
+    ),
     LoggerAttribute(
         name="youtube_logger",
         description="The logger for the youtube scraper.",