music_kraken/download/page_attributes.py

@@ -30,9 +30,31 @@ from ..utils.exception import MKMissingNameException
 from ..utils.exception.download import UrlNotFoundException
 from ..utils.shared import DEBUG_PAGES
 
-from ..pages import scan_for_pages, get_pages
+from ..pages import Page, EncyclopaediaMetallum, Musify, YouTube, YoutubeMusic, Bandcamp, Genius, INDEPENDENT_DB_OBJECTS
 
 
+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",
@@ -40,28 +62,66 @@ 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, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
+    def __init__(self, exclude_pages: Set[Type[Page]] = None, exclude_shady: bool = False, download_options: DownloadOptions = None, fetch_options: FetchOptions = None):
         self.LOGGER = logging.getLogger("download")
         
         self.download_options: DownloadOptions = download_options or DownloadOptions()
         self.fetch_options: FetchOptions = fetch_options or FetchOptions()
 
-        scan_for_pages(download_options=self.download_options, fetch_options=self.fetch_options, **kwargs)
+        # 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]]
 
     def search(self, query: Query) -> SearchResults:
         result = SearchResults()
         
-        for page in get_pages():
+        for page_type in self.pages:
             result.add(
-                page=type(page),
-                search_result=page.search(query=query)
+                page=page_type,
+                search_result=self._page_instances[page_type].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,
@@ -257,10 +317,12 @@ class Pages:
         tmp.delete()
         return r
 
-    def fetch_url(self, url: str, **kwargs) -> DataObject:
+    def fetch_url(self, url: str, stop_at_level: int = 2) -> Tuple[Type[Page], DataObject]:
         source = Source.match_url(url, ALL_SOURCE_TYPES.MANUAL)
         
-        if source is None or source.page is None:
+        if source is None:
             raise UrlNotFoundException(url=url)
         
-        return source.page.fetch_object_from_source(source=source, **kwargs)
+        _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)

music_kraken/pages/__init__.py

@@ -36,7 +36,7 @@ def deregister_page(page_type: Type[Page]):
         p.__del__()
     del _registered_pages[page_type]
 
-def scan_for_pages(**kwargs):
+def scan_for_pages():
     # assuming the wanted pages are the leaf classes of the interface
     leaf_classes = []
 
@@ -51,5 +51,6 @@ def scan_for_pages(**kwargs):
         else:
             _class_list.extend(_class_subclasses)
 
+    print(leaf_classes)
     for leaf_class in leaf_classes:
-        register_page(leaf_class, **kwargs)
+        register_page(leaf_class)

music_kraken/pages/_abstract.py

@@ -1,19 +1,15 @@
-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, TYPE_CHECKING
+from typing import Optional, Union, Type, Dict, Set, List, Tuple, TypedDict
 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,
@@ -38,6 +34,18 @@ 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
@@ -48,14 +56,14 @@ class Page:
         cls.LOGGER = logging.getLogger(cls.__name__)
         return super().__new__(cls)
 
-    def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
+    def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None):
         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()
+        self.SOURCE_TYPE.deregister_page(self)
 
     def _search_regex(self, pattern, string, default=None, fatal=True, flags=0, group=None):
         """