feat: musicbrainz overall search

development/actual_donwload.py

@@ -8,6 +8,8 @@ if __name__ == "__main__":
     commands = [
         "s: #a Crystal F",
         "10",
+        "1",
+        "3",
     ]
 
     

music_kraken/audio/metadata.py

@@ -93,6 +93,10 @@ def write_metadata_to_target(metadata: Metadata, target: Target, song: Song):
             # resize the image to the preferred resolution
             img.thumbnail((main_settings["preferred_artwork_resolution"], main_settings["preferred_artwork_resolution"]))
 
+            # https://stackoverflow.com/a/59476938/16804841
+            if img.mode != 'RGB':
+                img = img.convert('RGB')
+
             img.save(converted_target.file_path, "JPEG")
 
         # https://stackoverflow.com/questions/70228440/mutagen-how-can-i-correctly-embed-album-art-into-mp3-file-so-that-i-can-see-t

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/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/formatted_text.py

@@ -38,11 +38,19 @@ class FormattedText:
     def markdown(self) -> str:
         return md(self.html).strip()
     
+    @markdown.setter
+    def markdown(self, value: str) -> None:
+        self.html = mistune.markdown(value)
+
     @property
     def plain(self) -> str:
         md = self.markdown
         return md.replace("\n\n", "\n")
     
+    @plain.setter
+    def plain(self, value: str) -> None:
+        self.html = mistune.markdown(plain_to_markdown(value))
+
     def __str__(self) -> str:
         return self.markdown
 

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/genius.py

@@ -79,6 +79,8 @@ class Genius(Page):
             artwork.append(url=url)
 
     def parse_api_object(self, data: dict) -> Optional[DatabaseObject]:
+        if data is None:
+            return None
         object_type = data.get("_type")
 
         artwork = Artwork()
@@ -93,13 +95,13 @@ class Genius(Page):
         })
 
         notes = FormattedText()
-        description = data.get("description", {})
+        description = data.get("description") or {}
         if "html" in description:
             notes.html = description["html"]
         elif "markdown" in description:
             notes.markdown = description["markdown"]
         elif "description_preview" in data:
-            notes.plain = data["description_preview"]
+            notes.plaintext = data["description_preview"]
 
         if source.url is None:
             return None
@@ -113,7 +115,7 @@ class Genius(Page):
                 additional_sources.append(Source(ALL_SOURCE_TYPES.TWITTER, f"https://x.com/{data['twitter_name']}/"))
 
             return Artist(
-                name=data.get("name"),
+                name=data["name"].strip() if data.get("name") is not None else None,
                 source_list=[source],
                 artwork=artwork,
                 notes=notes,
@@ -123,12 +125,16 @@ class Genius(Page):
             self.add_to_artwork(artwork, data.get("cover_art_thumbnail_url"))
             self.add_to_artwork(artwork, data.get("cover_art_url"))
 
+            for cover_art in data.get("cover_arts", []):
+                self.add_to_artwork(artwork, cover_art.get("image_url"))
+                self.add_to_artwork(artwork, cover_art.get("thumbnail_image_url"))
+
             return Album(
-                title=data.get("name"),
+                title=data.get("name").strip(),
                 source_list=[source],
                 artist_list=[self.parse_api_object(data.get("artist"))],
                 artwork=artwork,
-                date=ID3Timestamp(**data.get("release_date_components", {})),
+                date=ID3Timestamp(**(data.get("release_date_components") or {})),
             )
 
         if object_type == "song":
@@ -143,7 +149,7 @@ class Genius(Page):
             if primary_artist is not None:
                 _artist_name = primary_artist.name
                 main_artist_list.append(primary_artist)
-            for feature_artist in data.get("featured_artists", []):
+            for feature_artist in (*(data.get("featured_artists") or []), *(data.get("producer_artists") or []), *(data.get("writer_artists") or [])):
                 artist = self.parse_api_object(feature_artist)
                 if artist is not None:
                     featured_artist_list.append(artist)
@@ -197,16 +203,16 @@ class Genius(Page):
             dump_to_file("genius_itemprop_artist.json", content, is_json=True, exit_after_dump=False)
             data = json.loads(content)
 
-            artist = self.parse_api_object(data.get("artist", {}))
+            artist = self.parse_api_object(data.get("artist"))
             
-            for e in data.get("artist_albums", []):
+            for e in (data.get("artist_albums") or []):
                 r = self.parse_api_object(e)
                 if not isinstance(r, Album):
                     continue
 
                 artist.album_collection.append(r)
             
-            for e in data.get("artist_songs", []):
+            for e in (data.get("artist_songs") or []):
                 r = self.parse_api_object(e)
                 if not isinstance(r, Song):
                     continue
@@ -223,133 +229,69 @@ class Genius(Page):
 
         return artist
 
-    def _parse_track_element(self, track: dict, artwork: Artwork) -> Optional[Song]:
-        lyrics_list: List[Lyrics] = []
-
-        _lyrics: Optional[str] = track.get("item", {}).get("recordingOf", {}).get("lyrics", {}).get("text")
-        if _lyrics is not None:
-            lyrics_list.append(Lyrics(text=FormattedText(plain=_lyrics)))
-
-        return Song(
-            title=clean_song_title(track["item"]["name"]),
-            source_list=[Source(self.SOURCE_TYPE, track["item"]["mainEntityOfPage"])],
-            tracksort=int(track["position"]),
-            artwork=artwork,
-        )
-
     def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
-        album = Album()
+        album: Album = Album()
+        # https://genius.com/api/artists/24527/albums?page=1
 
-        r = self.connection.get(source.url, name=f"album_{urlparse(source.url).netloc.split('.')[0]}_{urlparse(source.url).path.replace('/', '').replace('album', '')}")
+        r = self.connection.get(source.url, name=source.url)
         if r is None:
             return album
-
         soup = self.get_soup_from_response(r)
 
-        data_container = soup.find("script", {"type": "application/ld+json"})
+        # find the content attribute in the meta tag which is contained in the head
+        data_container = soup.find("meta", {"itemprop": "page_data"})
+        if data_container is not None:
+            content = data_container["content"]
+            dump_to_file("genius_itemprop_album.json", content, is_json=True, exit_after_dump=False)
+            data = json.loads(content)
 
-        if DEBUG:
+            album = self.parse_api_object(data.get("album"))
-            dump_to_file("album_data.json", data_container.text, is_json=True, exit_after_dump=False)
 
-        data = json.loads(data_container.text)
+            for e in data.get("album_appearances", []):
-        artist_data = data["byArtist"]
+                r = self.parse_api_object(e.get("song"))
-
+                if not isinstance(r, Song):
-        artist_source_list = []
-        if "@id" in artist_data:
-            artist_source_list = [Source(self.SOURCE_TYPE, _parse_artist_url(artist_data["@id"]))]
-        album = Album(
-            title=data["name"].strip(),
-            source_list=[Source(self.SOURCE_TYPE, data.get("mainEntityOfPage", data["@id"]))],
-            date=ID3Timestamp.strptime(data["datePublished"], "%d %b %Y %H:%M:%S %Z"),
-            artist_list=[Artist(
-                name=artist_data["name"].strip(),
-                source_list=artist_source_list
-            )]
-        )
-
-        artwork: Artwork = Artwork()
-
-        def _get_artwork_url(_data: dict) -> Optional[str]:
-            if "image" in _data:
-                return _data["image"]
-            for _property in _data.get("additionalProperty", []):
-                if _property.get("name") == "art_id":
-                    return f"https://f4.bcbits.com/img/a{_property.get('value')}_2.jpg"
-
-        _artwork_url = _get_artwork_url(data)
-        if _artwork_url is not None:
-            artwork.append(url=_artwork_url, width=350, height=350)
-        else:
-            for album_release in data.get("albumRelease", []):
-                _artwork_url = _get_artwork_url(album_release)
-                if _artwork_url is not None:
-                    artwork.append(url=_artwork_url, width=350, height=350)
-                    break
-
-
-        for i, track_json in enumerate(data.get("track", {}).get("itemListElement", [])):
-            if DEBUG:
-                dump_to_file(f"album_track_{i}.json", json.dumps(track_json), is_json=True, exit_after_dump=False)
-
-            try:
-                album.song_collection.append(self._parse_track_element(track_json, artwork=artwork))
-            except KeyError:
                     continue
 
+                album.song_collection.append(r)
+
         album.source_collection.append(source)
+        
         return album
 
-    def _fetch_lyrics(self, soup: BeautifulSoup) -> List[Lyrics]:
+    def get_json_content_from_response(self, response, start: str, end: str) -> Optional[str]:
-        track_lyrics = soup.find("div", {"class": "lyricsText"})
+        content = response.text
-        if track_lyrics:
+        start_index = content.find(start)
-            return [Lyrics(text=FormattedText(html=track_lyrics.prettify()))]
+        if start_index < 0:
-
+            return None
-        return []
+        start_index += len(start)
+        end_index = content.find(end, start_index)
+        if end_index < 0:
+            return None
+        return content[start_index:end_index]
 
     def fetch_song(self, source: Source, stop_at_level: int = 1) -> Song:
-        r = self.connection.get(source.url, name=f"song_{urlparse(source.url).netloc.split('.')[0]}_{urlparse(source.url).path.replace('/', '').replace('track', '')}")
+        song: Song = Song()
+
+        r = self.connection.get(source.url, name=source.url)
         if r is None:
-            return Song()
-
-        soup = self.get_soup_from_response(r)
-
-        data_container = soup.find("script", {"type": "application/ld+json"})
-        other_data = {}
-
-        other_data_list = soup.select("script[data-tralbum]")
-        if len(other_data_list) > 0:
-            other_data = json.loads(other_data_list[0]["data-tralbum"])
-
-        dump_to_file("bandcamp_song_data.json", data_container.text, is_json=True, exit_after_dump=False)
-        dump_to_file("bandcamp_song_data_other.json", json.dumps(other_data), is_json=True, exit_after_dump=False)
-        dump_to_file("bandcamp_song_page.html", r.text, exit_after_dump=False)
-
-        data = json.loads(data_container.text)
-        album_data = data["inAlbum"]
-        artist_data = data["byArtist"]
-
-        mp3_url = None
-        for key, value in other_data.get("trackinfo", [{}])[0].get("file", {"": None}).items():
-            mp3_url = value
-
-        song = Song(
-            title=clean_song_title(data["name"], artist_name=artist_data["name"]),
-            source_list=[source, Source(self.SOURCE_TYPE, data.get("mainEntityOfPage", data["@id"]), audio_url=mp3_url)],
-            album_list=[Album(
-                title=album_data["name"].strip(),
-                date=ID3Timestamp.strptime(data["datePublished"], "%d %b %Y %H:%M:%S %Z"),
-                source_list=[Source(self.SOURCE_TYPE, album_data["@id"])]
-            )],
-            artist_list=[Artist(
-                name=artist_data["name"].strip(),
-                source_list=[Source(self.SOURCE_TYPE, _parse_artist_url(artist_data["@id"]))]
-            )],
-            lyrics_list=self._fetch_lyrics(soup=soup)
-        )
-
             return song
 
-    def download_song_to_target(self, source: Source, target: Target, desc: str = None) -> DownloadResult:
+        # get the contents that are between `JSON.parse('` and `');`
-        if source.audio_url is None:
+        content = self.get_json_content_from_response(r, start="window.__PRELOADED_STATE__ = JSON.parse('", end="');\n      window.__APP_CONFIG__ = ")
-            return DownloadResult(error_message="Couldn't find download link.")
+        if content is not None:
-        return self.connection.stream_into(url=source.audio_url, target=target, description=desc)
+            content = content.replace("\\\\", "\\").replace('\\"', '"').replace("\\'", "'")
+            data = json.loads(content)
+
+            lyrics_html = traverse_json_path(data, "songPage.lyricsData.body.html", default=None)
+            if lyrics_html is not None:
+                song.lyrics_collection.append(Lyrics(FormattedText(html=lyrics_html)))
+
+            dump_to_file("genius_song_script_json.json", content, is_json=True, exit_after_dump=False)
+
+        soup = self.get_soup_from_response(r)
+        for lyrics in soup.find_all("div", {"data-lyrics-container": "true"}):
+            lyrics_object = Lyrics(FormattedText(html=lyrics.prettify()))
+            song.lyrics_collection.append(lyrics_object)
+
+        song.source_collection.append(source)
+        return song

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/youtube_music/youtube_music.py

@@ -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,
@@ -575,6 +580,7 @@ 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)
+                if browse_id is not None:
                     break
 
         if browse_id is 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/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.",