feat: added detection to autoscann pages

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/pages/__init__.py

@@ -1,8 +1,56 @@
-from .encyclopaedia_metallum import EncyclopaediaMetallum
+from typing import Type, Generator, Set, Dict, List
-from .musify import Musify
+from collections import defaultdict
-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,

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,
@@ -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,
@@ -575,7 +580,8 @@ 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)
-                break
+                if browse_id is not None:
+                    break
 
         if browse_id is None:
             return 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/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)