feat: implemented consistent settings

music_kraken/download/page_attributes.py

@@ -30,31 +30,9 @@ 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 scan_for_pages, get_pages
 
 
-ALL_PAGES: Set[Type[Page]] = {
-    # EncyclopaediaMetallum,
-    Genius,
-    Musify,
-    YoutubeMusic,
-    Bandcamp
-}
-
-if youtube_settings["use_youtube_alongside_youtube_music"]:
-    ALL_PAGES.add(YouTube)
-
-AUDIO_PAGES: Set[Type[Page]] = {
-    Musify,
-    YouTube,
-    YoutubeMusic,
-    Bandcamp
-}
-
-SHADY_PAGES: Set[Type[Page]] = {
-    Musify,
-}
-
 fetch_map = {
     Song: "fetch_song",
     Album: "fetch_album",
@@ -62,66 +40,28 @@ fetch_map = {
     Label: "fetch_label",
 }
 
-if DEBUG_PAGES:
-    DEBUGGING_PAGE = Bandcamp
-    print(f"Only downloading from page {DEBUGGING_PAGE}.")
-
-    ALL_PAGES = {DEBUGGING_PAGE}
-    AUDIO_PAGES = ALL_PAGES.union(AUDIO_PAGES)
-
 
 class Pages:
-    def __init__(self, exclude_pages: Set[Type[Page]] = None, exclude_shady: bool = False, download_options: DownloadOptions = None, fetch_options: FetchOptions = None):
+    def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
         self.LOGGER = logging.getLogger("download")
         
         self.download_options: DownloadOptions = download_options or DownloadOptions()
         self.fetch_options: FetchOptions = fetch_options or FetchOptions()
 
-        # initialize all page instances
-        self._page_instances: Dict[Type[Page], Page] = dict()
-        self._source_to_page: Dict[SourceType, Type[Page]] = dict()
-        
-        exclude_pages = exclude_pages if exclude_pages is not None else set()
-        
-        if exclude_shady:
-            exclude_pages = exclude_pages.union(SHADY_PAGES)
-        
-        if not exclude_pages.issubset(ALL_PAGES):
-            raise ValueError(f"The excluded pages have to be a subset of all pages: {exclude_pages} | {ALL_PAGES}")
-        
-        def _set_to_tuple(page_set: Set[Type[Page]]) -> Tuple[Type[Page], ...]:
-            return tuple(sorted(page_set, key=lambda page: page.__name__))
-        
-        self._pages_set: Set[Type[Page]] = ALL_PAGES.difference(exclude_pages)
-        self.pages: Tuple[Type[Page], ...] = _set_to_tuple(self._pages_set)
-
-        self._audio_pages_set: Set[Type[Page]] = self._pages_set.intersection(AUDIO_PAGES)
-        self.audio_pages: Tuple[Type[Page], ...] = _set_to_tuple(self._audio_pages_set)
-        
-        for page_type in self.pages:
-            self._page_instances[page_type] = page_type(fetch_options=self.fetch_options, download_options=self.download_options)
-            self._source_to_page[page_type.SOURCE_TYPE] = page_type
-
-    def _get_page_from_enum(self, source_page: SourceType) -> Page:
-        if source_page not in self._source_to_page:
-            return None
-        return self._page_instances[self._source_to_page[source_page]]
+        scan_for_pages(download_options=self.download_options, fetch_options=self.fetch_options, **kwargs)
 
     def search(self, query: Query) -> SearchResults:
         result = SearchResults()
         
-        for page_type in self.pages:
+        for page in get_pages():
             result.add(
-                page=page_type,
-                search_result=self._page_instances[page_type].search(query=query)
+                page=type(page),
+                search_result=page.search(query=query)
             )
             
         return result
     
     def fetch_details(self, data_object: DataObject, stop_at_level: int = 1, **kwargs) -> DataObject:
-        if not isinstance(data_object, INDEPENDENT_DB_OBJECTS):
-            return data_object
-        
         source: Source
         for source in data_object.source_collection.get_sources(source_type_sorting={
             "only_with_page": True,
@@ -317,12 +257,10 @@ class Pages:
         tmp.delete()
         return r
 
-    def fetch_url(self, url: str, stop_at_level: int = 2) -> Tuple[Type[Page], DataObject]:
+    def fetch_url(self, url: str, **kwargs) -> DataObject:
         source = Source.match_url(url, ALL_SOURCE_TYPES.MANUAL)
         
-        if source is None:
+        if source is None or source.page is None:
             raise UrlNotFoundException(url=url)
         
-        _actual_page = self._source_to_page[source.source_type]
-        
-        return _actual_page, self._page_instances[_actual_page].fetch_object_from_source(source=source, stop_at_level=stop_at_level)
+        return source.page.fetch_object_from_source(source=source, **kwargs)

music_kraken/pages/__init__.py

@@ -1,8 +1,55 @@
-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 typing import Type, Generator, Set, Dict, List
+from collections import defaultdict
 
-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(**kwargs):
+    # 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)
+
+    for leaf_class in leaf_classes:
+        register_page(leaf_class, **kwargs)

music_kraken/pages/_abstract.py

@@ -1,15 +1,19 @@
+from __future__ import annotations
+
 import logging
 import random
 import re
 from copy import copy
 from pathlib import Path
-from typing import Optional, Union, Type, Dict, Set, List, Tuple, TypedDict
+from typing import Optional, Union, Type, Dict, Set, List, Tuple, TypedDict, TYPE_CHECKING
 from string import Formatter
 from dataclasses import dataclass, field
 
 import requests
 from bs4 import BeautifulSoup
 
+if TYPE_CHECKING:
+    from ..download.page_attributes import DownloadOptions, FetchOptions
 from ..connection import Connection
 from ..objects import (
     Song,
@@ -34,34 +38,25 @@ from ..utils import trace, output, BColors
 INDEPENDENT_DB_OBJECTS = Union[Label, Album, Artist, Song]
 INDEPENDENT_DB_TYPES = Union[Type[Song], Type[Album], Type[Artist], Type[Label]]
 
-@dataclass
-class FetchOptions:
-    download_all: bool = False
-    album_type_blacklist: Set[AlbumType] = field(default_factory=lambda: set(AlbumType(a) for a in main_settings["album_type_blacklist"]))
-
-@dataclass
-class DownloadOptions:
-    download_all: bool = False
-    album_type_blacklist: Set[AlbumType] = field(default_factory=lambda: set(AlbumType(a) for a in main_settings["album_type_blacklist"]))
-
-    process_audio_if_found: bool = False
-    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):
+    def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
         self.SOURCE_TYPE.register_page(self)
         
         self.download_options: DownloadOptions = download_options or DownloadOptions()
         self.fetch_options: FetchOptions = fetch_options or FetchOptions()
 
+    def __del__(self):
+        self.SOURCE_TYPE.deregister_page()
+
     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,

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/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)