feat: added detection to autoscann pages

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

music_kraken/pages/__init__.py

@@ -1,9 +1,56 @@
-from .encyclopaedia_metallum import EncyclopaediaMetallum
+from typing import Type, Generator, Set, Dict, List
-from .musify import Musify
+from collections import defaultdict
-from .musicbrainz import Musicbrainz
-from .youtube import YouTube
-from .youtube_music import YoutubeMusic
-from .bandcamp import Bandcamp
-from .genius import Genius
 
-from .abstract import Page, INDEPENDENT_DB_OBJECTS
+from ._encyclopaedia_metallum import EncyclopaediaMetallum
+from ._musify import Musify
+from ._youtube import YouTube
+from ._youtube_music import YoutubeMusic
+from ._bandcamp import Bandcamp
+from ._genius import Genius
+from ._abstract import Page, INDEPENDENT_DB_OBJECTS
+
+
+_registered_pages: Dict[Type[Page], Set[Page]] = defaultdict(set)
+
+
+def get_pages(*page_types: List[Type[Page]]) -> Generator[Page, None, None]:
+    if len(page_types) == 0:
+        page_types = _registered_pages.keys()
+
+    for page_type in page_types:
+        yield from _registered_pages[page_type]
+
+
+def register_page(page_type: Type[Page], **kwargs):
+    if page_type in _registered_pages:
+        return
+
+    _registered_pages[page_type].add(page_type(**kwargs))
+
+
+def deregister_page(page_type: Type[Page]):
+    if page_type not in _registered_pages:
+        return
+
+    for p in _registered_pages[page_type]:
+        p.__del__()
+    del _registered_pages[page_type]
+
+def scan_for_pages():
+    # assuming the wanted pages are the leaf classes of the interface
+    leaf_classes = []
+
+    _class_list = [Page]
+    while len(_class_list):
+        _class = _class_list.pop()
+        _class_subclasses = _class.__subclasses__()
+
+        if len(_class_subclasses) == 0:
+            if _class.REGISTER:
+                leaf_classes.append(_class)
+        else:
+            _class_list.extend(_class_subclasses)
+
+    print(leaf_classes)
+    for leaf_class in leaf_classes:
+        register_page(leaf_class)

music_kraken/pages/_abstract.py

@@ -48,12 +48,12 @@ class DownloadOptions:
     process_metadata_if_found: bool = True
 
 class Page:
+    REGISTER = True
     SOURCE_TYPE: SourceType
     LOGGER: logging.Logger
 
     def __new__(cls, *args, **kwargs):
         cls.LOGGER = logging.getLogger(cls.__name__)
-
         return super().__new__(cls)
 
     def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None):
@@ -62,6 +62,9 @@ class Page:
         self.download_options: DownloadOptions = download_options or DownloadOptions()
         self.fetch_options: FetchOptions = fetch_options or FetchOptions()
 
+    def __del__(self):
+        self.SOURCE_TYPE.deregister_page(self)
+
     def _search_regex(self, pattern, string, default=None, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of

music_kraken/pages/_bandcamp.py

@@ -6,7 +6,7 @@ from bs4 import BeautifulSoup
 import pycountry
 
 from ..objects import Source, DatabaseObject
-from .abstract import Page
+from ._abstract import Page
 from ..objects import (
     Artist,
     Source,

music_kraken/pages/_encyclopaedia_metallum.py

@@ -6,7 +6,7 @@ from urllib.parse import urlparse, urlencode
 
 from ..connection import Connection
 from ..utils.config import logging_settings
-from .abstract import Page
+from ._abstract import Page
 from ..utils.enums import SourceType, ALL_SOURCE_TYPES
 from ..utils.enums.album import AlbumType
 from ..utils.support_classes.query import Query
@@ -207,6 +207,7 @@ def create_grid(
 
 
 class EncyclopaediaMetallum(Page):
+    REGISTER = False
     SOURCE_TYPE = ALL_SOURCE_TYPES.ENCYCLOPAEDIA_METALLUM
     LOGGER = logging_settings["metal_archives_logger"]
     

music_kraken/pages/_genius.py

@@ -6,7 +6,7 @@ from bs4 import BeautifulSoup
 import pycountry
 
 from ..objects import Source, DatabaseObject
-from .abstract import Page
+from ._abstract import Page
 from ..objects import (
     Artist,
     Source,
@@ -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") or {})),
+                date=ID3Timestamp(**data.get("release_date_components", {})),
             )
 
         if object_type == "song":

music_kraken/pages/_musify.py

@@ -8,7 +8,7 @@ import pycountry
 from bs4 import BeautifulSoup
 
 from ..connection import Connection
-from .abstract import Page
+from ._abstract import Page
 from ..utils.enums import SourceType, ALL_SOURCE_TYPES
 from ..utils.enums.album import AlbumType, AlbumStatus
 from ..objects import (

music_kraken/pages/_youtube.py

@@ -5,7 +5,7 @@ from enum import Enum
 import python_sponsorblock
 
 from ..objects import Source, DatabaseObject, Song, Target
-from .abstract import Page
+from ._abstract import Page
 from ..objects import (
     Artist,
     Source,
@@ -22,7 +22,7 @@ from ..utils.enums import SourceType, ALL_SOURCE_TYPES
 from ..utils.support_classes.download_result import DownloadResult
 from ..utils.config import youtube_settings, main_settings, logging_settings
 
-from .youtube_music.super_youtube import SuperYouTube, YouTubeUrl, get_invidious_url, YouTubeUrlType
+from ._youtube_music.super_youtube import SuperYouTube, YouTubeUrl, get_invidious_url, YouTubeUrlType
 
 
 """
@@ -38,7 +38,7 @@ def get_piped_url(path: str = "", params: str = "", query: str = "", fragment: s
 
 
 class YouTube(SuperYouTube):
-    # CHANGE
+    REGISTER = youtube_settings["use_youtube_alongside_youtube_music"]
     SOURCE_TYPE = ALL_SOURCE_TYPES.YOUTUBE
 
     def __init__(self, *args, **kwargs):

music_kraken/pages/_youtube_music/_list_render.py

@@ -3,7 +3,6 @@ from enum import Enum
 
 from ...utils.config import logging_settings
 from ...objects import Source, DatabaseObject
-from ..abstract import Page
 from ...objects import (
     Artist,
     Source,

music_kraken/pages/_youtube_music/_music_object_render.py

@@ -6,7 +6,6 @@ from ...utils.string_processing import clean_song_title
 from ...utils.enums import SourceType, ALL_SOURCE_TYPES
 
 from ...objects import Source, DatabaseObject
-from ..abstract import Page
 from ...objects import (
     Artist,
     Source,

music_kraken/pages/_youtube_music/super_youtube.py

@@ -6,7 +6,7 @@ import requests
 import python_sponsorblock
 
 from ...objects import Source, DatabaseObject, Song, Target
-from ..abstract import Page
+from .._abstract import Page
 from ...objects import (
     Artist,
     Source,

music_kraken/pages/_youtube_music/youtube_music.py

@@ -22,7 +22,7 @@ from ...utils import get_current_millis, traverse_json_path
 
 from ...utils import dump_to_file
 
-from ..abstract import Page
+from .._abstract import Page
 from ...objects import (
     DatabaseObject as DataObject,
     Source,

music_kraken/pages/musicbrainz.py

@@ -1,145 +0,0 @@
-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/utils/config/config_files/logging_config.py

@@ -59,11 +59,6 @@ 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.",

music_kraken/utils/enums/__init__.py

@@ -17,6 +17,9 @@ class SourceType:
     def register_page(self, page: Page):
         self.page = page
 
+    def deregister_page(self):
+        self.page = None
+
     def __hash__(self):
         return hash(self.name)