feat: musicbrainz overall search

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

music_kraken/objects/song.py

@@ -477,8 +477,6 @@ class Artist(Base):
     general_genre: str
     unformatted_location: str
 
-    artwork: List[Artwork]
-
     source_collection: SourceCollection
     contact_collection: Collection[Contact]
 
@@ -495,8 +493,6 @@ class Artist(Base):
         "lyrical_themes": list,
         "general_genre": lambda: "",
 
-        "artwork": list,
-
         "source_collection": SourceCollection,
         "album_collection": Collection,
         "contact_collection": Collection,
@@ -515,7 +511,6 @@ 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

@@ -1,5 +1,6 @@
 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

@@ -0,0 +1,145 @@
+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:
-            artist_soup: BeautifulSoup
-            for artist_soup in list_element.find_all("a"):
-                artist_source_list = []
-                href = artist_soup["href"]
-                if href is not None:
-                    artist_source_list = [Source(self.SOURCE_TYPE, self.HOST + href)]
-                artist_list.append(Artist(
-                    name=artist_soup.text.strip(),
-                    source_list=artist_source_list
-                ))
+            if list_element is not None:
+                artist_soup: BeautifulSoup
+                for artist_soup in list_element.find_all("a"):
+                    artist_source_list = []
+                    href = artist_soup["href"]
+                    if href is not None:
+                        artist_source_list = [Source(self.SOURCE_TYPE, self.HOST + href)]
+                    artist_list.append(Artist(
+                        name=artist_soup.text.strip(),
+                        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()
 
-        # album artwork
+        # 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:
@@ -918,8 +918,7 @@ class Musify(Page):
             name=name,
             country=country,
             source_list=source_list,
-            notes=notes,
-            artwork=self._fetch_artist_artwork(soup, **kwargs)
+            notes=notes
         )
 
     def _parse_album_card(self, album_card: BeautifulSoup, artist_name: str = None, **kwargs) -> Album:
@@ -1057,20 +1056,6 @@ 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
@@ -1083,7 +1068,7 @@ 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

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