feat: added hooks for collection on append

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/objects/artwork.py

@@ -1,18 +1,14 @@
 from __future__ import annotations
 
-from typing import List, Optional, Dict, Tuple, Type, Union, TypedDict
+from typing import Dict, List, Optional, Set, Tuple, Type, TypedDict, Union
-
-from .collection import Collection
-from .metadata import (
-    Mapping as id3Mapping,
-    ID3Timestamp,
-    Metadata
-)
-from ..utils.string_processing import unify, hash_url
-
-from .parents import OuterProxy as Base
 
 from ..utils.config import main_settings
+from ..utils.string_processing import hash_url, unify
+from .collection import Collection
+from .metadata import ID3Timestamp
+from .metadata import Mapping as id3Mapping
+from .metadata import Metadata
+from .parents import OuterProxy as Base
 
 
 class ArtworkVariant(TypedDict):
@@ -23,7 +19,9 @@ class ArtworkVariant(TypedDict):
 
 
 class Artwork:
-    def __init__(self, *variants: List[ArtworkVariant]) -> None:
+    def __init__(self, *variants: List[ArtworkVariant], parent_artworks: Set[Artwork] = None) -> None:
+        self.parent_artworks: Set[Artwork] = parent_artworks or set()
+        
         self._variant_mapping: Dict[str, ArtworkVariant] = {}
 
         for variant in variants:
@@ -36,7 +34,7 @@ class Artwork:
     def append(self, url: str, width: int = main_settings["preferred_artwork_resolution"], height: int = main_settings["preferred_artwork_resolution"], **kwargs) -> None:
         if url is None:
             return
-        
+     
         self._variant_mapping[hash_url(url=url)] = {
             "url": url,
             "width": width,
@@ -44,21 +42,36 @@ class Artwork:
             "deviation": self._calculate_deviation(width, height),
         }
 
+    @property
+    def flat_empty(self) -> bool:
+        return len(self._variant_mapping.keys()) <= 0
+
+    def _get_best_from_list(self, artwork_variants: List[ArtworkVariant]) -> Optional[ArtworkVariant]:
+        return min(artwork_variants, key=lambda x: x["deviation"])
+
     @property
     def best_variant(self) -> ArtworkVariant:
-        if len(self._variant_mapping.keys()) <= 0:
+        if self.flat_empty:
-            return None
+            return self._get_best_from_list([parent.best_variant for parent in self.parent_artworks])
-        return min(self._variant_mapping.values(), key=lambda x: x["deviation"])
+        return self._get_best_from_list(self._variant_mapping.values())
 
     def get_variant_name(self, variant: ArtworkVariant) -> str:
         return f"artwork_{variant['width']}x{variant['height']}_{hash_url(variant['url']).replace('/', '_')}"
 
     def __merge__(self, other: Artwork, **kwargs) -> None:
+        self.parent_artworks.update(other.parent_artworks)
+
         for key, value in other._variant_mapping.items():
             if key not in self._variant_mapping:
                 self._variant_mapping[key] = value
 
+    def __hash__(self) -> int:
+        return id(self)
+
     def __eq__(self, other: Artwork) -> bool:
+        if hash(self) == hash(other):
+            return True
+
         if not isinstance(other, Artwork):
             return False
         return any(a == b for a, b in zip(self._variant_mapping.keys(), other._variant_mapping.keys()))

music_kraken/objects/collection.py

@@ -1,16 +1,44 @@
 from __future__ import annotations
 
-from collections import defaultdict
-from typing import TypeVar, Generic, Dict, Optional, Iterable, List, Iterator, Tuple, Generator, Union, Any, Set
 import copy
+from collections import defaultdict
+from dataclasses import dataclass
+from typing import (Any, Callable, Dict, Generator, Generic, Iterable,
+                    Iterator, List, Optional, Set, Tuple, TypeVar, Union)
 
-from .parents import OuterProxy
+from ..utils import BColors, object_trace, output
-from ..utils import object_trace
+from .parents import InnerData, OuterProxy
-from ..utils import output, BColors
 
 T = TypeVar('T', bound=OuterProxy)
 
 
+@dataclass
+class AppendHookArguments:
+    """
+    This class is used to store the arguments for the append hook.
+    The best explanation is with an examples:
+    
+    ```
+    # this is the action that triggers the append hook
+    album = Album()
+    song = Song()
+    album.song_collection.append(song)
+    ```
+
+    In this case, the append hook is triggered with the following arguments:
+    ```
+    AppendHookArguments(
+        collection=album.song_collection,
+        new_object=song,
+        collection_root_objects=[album]
+    )
+    ```
+    """
+
+    collection: Collection
+    new_object: T
+    collection_root_objects: Set[InnerData]
+
 class Collection(Generic[T]):
     __is_collection__ = True
 
@@ -27,6 +55,7 @@ class Collection(Generic[T]):
             sync_on_append: Dict[str, Collection] = None,
             append_object_to_attribute: Dict[str, T] = None,
             extend_object_to_attribute: Dict[str, Collection] = None,
+            append_callbacks: List[Callable[[AppendHookArguments], None]] = None,
     ) -> None:
         self._collection_for: dict = dict()
 
@@ -41,6 +70,7 @@ class Collection(Generic[T]):
         self.sync_on_append: Dict[str, Collection] = sync_on_append or {}
         self.pull_from: List[Collection] = []
         self.push_to: List[Collection] = []
+        self.append_callbacks: List[Callable[[AppendHookArguments], None]] = append_callbacks or []
 
         # This is to cleanly unmap previously mapped items by their id
         self._indexed_from_id: Dict[int, Dict[str, Any]] = defaultdict(dict)
@@ -141,6 +171,14 @@ class Collection(Generic[T]):
         for attribute, new_object in self.append_object_to_attribute.items():
             other.__getattribute__(attribute).append(new_object, **kwargs)
 
+        append_hook_args = AppendHookArguments(
+            collection=self,
+            new_object=other,
+            collection_root_objects=self._collection_for.keys(),
+        )
+        for callback in self.append_callbacks:
+            callback(append_hook_args)
+
     def append(self, other: Optional[T], **kwargs):
         """
         If an object, that represents the same entity exists in a relevant collection,

music_kraken/objects/song.py

@@ -477,6 +477,8 @@ class Artist(Base):
     general_genre: str
     unformatted_location: str
 
+    artwork: List[Artwork]
+
     source_collection: SourceCollection
     contact_collection: Collection[Contact]
 
@@ -493,6 +495,8 @@ class Artist(Base):
         "lyrical_themes": list,
         "general_genre": lambda: "",
 
+        "artwork": list,
+
         "source_collection": SourceCollection,
         "album_collection": Collection,
         "contact_collection": Collection,
@@ -511,6 +515,7 @@ class Artist(Base):
         notes: FormattedText = None, 
         lyrical_themes: List[str] = None,
         general_genre: str = None, 
+        artwork: List[Artwork] = None,
         unformatted_location: str = None, 
         source_list: List[Source] = None,
         contact_list: List[Contact] = None, 

music_kraken/pages/__init__.py

@@ -1,6 +1,5 @@
 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/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/pages/musify.py

@@ -457,17 +457,17 @@ class Musify(Page):
         for album_info in soup.find_all("ul", {"class": "album-info"}):
             list_element: BeautifulSoup = album_info.find("li")
             
-            if list_element is not None:
+        if list_element is not None:
-                artist_soup: BeautifulSoup
+            artist_soup: BeautifulSoup
-                for artist_soup in list_element.find_all("a"):
+            for artist_soup in list_element.find_all("a"):
-                    artist_source_list = []
+                artist_source_list = []
-                    href = artist_soup["href"]
+                href = artist_soup["href"]
-                    if href is not None:
+                if href is not None:
-                        artist_source_list = [Source(self.SOURCE_TYPE, self.HOST + href)]
+                    artist_source_list = [Source(self.SOURCE_TYPE, self.HOST + href)]
-                    artist_list.append(Artist(
+                artist_list.append(Artist(
-                        name=artist_soup.text.strip(),
+                    name=artist_soup.text.strip(),
-                        source_list=artist_source_list
+                    source_list=artist_source_list
-                    ))
+                ))
     
         # breadcrums
         breadcrumb_list_element_list: List[BeautifulSoup] = soup.find_all("ol", {"class": "breadcrumb"})
@@ -485,7 +485,7 @@ class Musify(Page):
             
             track_name = list_points[4].text.strip()
 
-        # artwork
+        # album artwork
         artwork: Artwork = Artwork()
         album_image_element_list: List[BeautifulSoup] = soup.find_all("img", {"class": "album-img"})
         for album_image_element in album_image_element_list:
@@ -918,7 +918,8 @@ class Musify(Page):
             name=name,
             country=country,
             source_list=source_list,
-            notes=notes
+            notes=notes,
+            artwork=self._fetch_artist_artwork(soup, **kwargs)
         )
 
     def _parse_album_card(self, album_card: BeautifulSoup, artist_name: str = None, **kwargs) -> Album:
@@ -1056,6 +1057,20 @@ class Musify(Page):
 
             artist.album_collection.append(album)
 
+    def _fetch_artist_artwork(self, soup: BeautifulSoup, **kwargs):
+        # artist artwork
+        artist_artwork: List[Artwork] = Artwork()
+        artist_a_element_list: List[BeautifulSoup] = soup.find_all("a")
+        for artist_a_element in artist_a_element_list:
+            if artist_a_element.find_all("img", {"class": "artist-img"}).count() > 0:
+                artwork_gallery = self.connection.get(artist_a_element("data-src", artist_a_element.get("href")))
+                if artwork_gallery is not None:
+                    gallery_image_element_list: List[BeautifulSoup] = artwork_gallery.find_all("img", {"class": "artist-img"})
+                    for gallery_image_element in gallery_image_element_list:
+                        artist_artwork.push(Artwork(url=gallery_image_element.get("data-src", gallery_image_element.get("src"))))
+
+        return artist_artwork
+
     def fetch_artist(self, source: Source, **kwargs) -> Artist:
         """
         TODO
@@ -1068,7 +1083,7 @@ class Musify(Page):
 
         artist = self._fetch_initial_artist(url, source=source, **kwargs)
         self._fetch_artist_discography(artist, url, artist.name, **kwargs)
-        
+        self._fetch_artist_artwork(artist, **kwargs)
         return artist
 
     def fetch_label(self, source: Source, stop_at_level: int = 1) -> Label:

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.",