fix: bandcamp

Reviewed-on: #27

.vscode/launch.json

@@ -0,0 +1,22 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal"
+        },
+        {
+            "name": "Python Debugger: Download script",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "development/actual_donwload.py",
+            "console": "integratedTerminal"
+        }
+    ]
+}

.vscode/settings.json

@@ -19,6 +19,7 @@
         "albumsort",
         "APIC",
         "Bandcamp",
+        "bitrate",
         "dotenv",
         "encyclopaedia",
         "ENDC",
@@ -27,6 +28,7 @@
         "metallum",
         "musify",
         "OKBLUE",
+        "OKGREEN",
         "pathvalidate",
         "Referer",
         "sponsorblock",

.woodpecker.yml

@@ -11,7 +11,6 @@ steps:
   build-stable:
     image: python
     commands:
-      - sed -i 's/name = "music-kraken"/name = "music-kraken-stable"/' pyproject.toml
       - python -m pip install -r requirements-dev.txt
       - python3 -m build
     environment:

development/actual_donwload.py

@@ -6,8 +6,8 @@ logging.getLogger().setLevel(logging.DEBUG)
 
 if __name__ == "__main__":
     commands = [
-        "s: #a Crystal F",
-        "dm: 10, 20"
+        "s: #a Psychonaut 4",
+        "d: 0",
     ]
 
     

music_kraken/audio/codec.py

@@ -47,7 +47,7 @@ def correct_codec(target: Target, bitrate_kb: int = main_settings["bitrate"], au
 
     # run the ffmpeg command with a progressbar
     ff = FfmpegProgress(ffmpeg_command)
-    with tqdm(total=100, desc=f"removing {len(interval_list)} segments") as pbar:
+    with tqdm(total=100, desc=f"processing") as pbar:
         for progress in ff.run_command_with_progress():
             pbar.update(progress-pbar.n)
 

music_kraken/cli/main_downloader.py

@@ -166,9 +166,9 @@ class Downloader:
         self.genre = genre or get_genre()
         self.process_metadata_anyway = process_metadata_anyway
 
-        print()
-        print(f"Downloading to: \"{self.genre}\"")
-        print()
+        output()
+        output(f"Downloading to: \"{self.genre}\"", color=BColors.HEADER)
+        output()
 
     def print_current_options(self):
         self.page_dict = dict()
@@ -304,20 +304,16 @@ class Downloader:
     def goto(self, data_object: DatabaseObject):
         page: Type[Page]
 
-        self.pages.fetch_details(data_object)
+        self.pages.fetch_details(data_object, stop_at_level=1)
 
-        print(data_object)
-        print(data_object.options)
         self.set_current_options(GoToResults(data_object.options, max_items_per_page=self.max_displayed_options))
 
         self.print_current_options()
 
     def download(self, data_objects: List[DatabaseObject], **kwargs) -> bool:
         output()
-        if len(data_objects) == 1:
-            output(f"Downloading {data_objects[0].option_string}...", color=BColors.BOLD)
-        else:
-            output(f"Downloading {len(data_objects)} objects...", *("- " + o.option_string for o in data_objects), color=BColors.BOLD, sep="\n")
+        if len(data_objects) > 1:
+            output(f"Downloading  {len(data_objects)} objects...", *("- " + o.option_string for o in data_objects), color=BColors.BOLD, sep="\n")
 
         _result_map: Dict[DatabaseObject, DownloadResult] = dict()
 
@@ -380,13 +376,13 @@ class Downloader:
                     continue
                 
                 i = 0
-                if possible_index.isdigit():
+                try:
                     i = int(possible_index)
-                else:
+                except ValueError:
                     raise MKInvalidInputException(message=f"The index \"{possible_index}\" is not a number.")
 
-                if i < 0 and i >= len(self.current_results):
-                    raise MKInvalidInputException(message=f"The index \"{i}\" is not within the bounds of 0-{len(self.current_results)}.")
+                if i < 0 or i >= len(self.current_results):
+                    raise MKInvalidInputException(message=f"The index \"{i}\" is not within the bounds of 0-{len(self.current_results) - 1}.")
                 
                 indices.append(i)
 

music_kraken/download/page_attributes.py

@@ -118,7 +118,7 @@ class Pages:
         audio_pages = self._audio_pages_set.intersection(_page_types)
         
         for download_page in audio_pages:
-            return self._page_instances[download_page].download(music_object=music_object, genre=genre, download_all=download_all, process_metadata_anyway=process_metadata_anyway)
+            return self._page_instances[download_page].download(music_object=music_object, genre=genre)
         
         return DownloadResult(error_message=f"No audio source has been found for {music_object}.")
 

music_kraken/download/results.py

@@ -28,6 +28,9 @@ class Results:
         self._by_index = dict()
         self._page_by_index = dict()
 
+    def __len__(self) -> int:
+        return max(self._by_index.keys())
+
     def __getitem__(self, index: int): 
         return self._by_index[index]
 

music_kraken/objects/collection.py

@@ -2,6 +2,8 @@ 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 .parents import OuterProxy
 from ..utils import object_trace
 from ..utils import output, BColors
@@ -47,8 +49,15 @@ class Collection(Generic[T]):
 
         self.extend(data)
 
+    def __hash__(self) -> int:
+        return id(self)
+
+    @property
+    def collection_names(self) -> List[str]:
+        return list(set(self._collection_for.values()))
+
     def __repr__(self) -> str:
-        return f"Collection({' | '.join(self._collection_for.values())} {id(self)})"
+        return f"Collection({' | '.join(self.collection_names)} {id(self)})"
 
     def _map_element(self, __object: T, no_unmap: bool = False, **kwargs):
         if not no_unmap:
@@ -104,8 +113,9 @@ class Collection(Generic[T]):
         """
         
         self._data.append(other)
+        other._inner._is_in_collection.add(self)
 
-        # all of the existing hooks to get the defined datastructure
+        # all of the existing hooks to get the defined datastructures
         for collection_attribute, generator in self.extend_object_to_attribute.items():
             other.__getattribute__(collection_attribute).extend(generator, **kwargs)
 
@@ -143,35 +153,35 @@ class Collection(Generic[T]):
 
         if other is None:
             return
+        if not other._inner._has_data:
+            return
         if other.id in self._indexed_from_id:
             return
 
         object_trace(f"Appending {other.option_string} to {self}")
 
-        
-        for c in self.pull_from:
-            r = c._find_object(other)
-            if r is not None:
-                output("found pull from", r, other, self, color=BColors.RED, sep="\t")
-                other.merge(r, **kwargs)
-                c.remove(r, existing=r, **kwargs)
-                break
-
-        existing_object = self._find_object(other)
-
         # switching collection in the case of push to
         for c in self.push_to:
             r = c._find_object(other)
             if r is not None:
-                output("found push to", r, other, self, color=BColors.RED, sep="\t")
+                # output("found push to", r, other, c, self, color=BColors.RED, sep="\t")
                 return c.append(other, **kwargs)
+
+        for c in self.pull_from:
+            r = c._find_object(other)
+            if r is not None:
+                # output("found pull from", r, other, c, self, color=BColors.RED, sep="\t")
+                c.remove(r, existing=r, **kwargs)
         
-        if existing_object is None:
+        existing = self._find_object(other)
+
+        if existing is None:
             self._append_new_object(other, **kwargs)
         else:
-            existing_object.merge(other, **kwargs)
+            existing.merge(other, **kwargs)
 
-    def remove(self, *other_list: List[T], silent: bool = False, existing: Optional[T] = None, **kwargs):
+    def remove(self, *other_list: List[T], silent: bool = False, existing: Optional[T] = None, remove_from_other_collection=True, **kwargs):
+        other: T
         for other in other_list:
             existing: Optional[T] = existing or self._indexed_values["id"].get(other.id, None)
             if existing is None:
@@ -179,16 +189,13 @@ class Collection(Generic[T]):
                     raise ValueError(f"Object {other} not found in {self}")
                 return other
 
-            """
-            for collection_attribute, generator in self.extend_object_to_attribute.items():
-                other.__getattribute__(collection_attribute).remove(*generator, silent=silent, **kwargs)
-
-            for attribute, new_object in self.append_object_to_attribute.items():
-                other.__getattribute__(attribute).remove(new_object, silent=silent, **kwargs)
-            """ 
-
-            self._data.remove(existing)
-            self._unmap_element(existing)
+            if remove_from_other_collection:
+                for c in copy.copy(other._inner._is_in_collection):
+                    c.remove(other, silent=True, remove_from_other_collection=False, **kwargs)
+                other._inner._is_in_collection = set()
+            else:
+                self._data.remove(existing)
+                self._unmap_element(existing)
 
     def contains(self, __object: T) -> bool:
         return self._find_object(__object) is not None

music_kraken/objects/formatted_text.py

@@ -32,7 +32,7 @@ class FormattedText:
         if self.is_empty and other.is_empty:
             return True
 
-        return self.doc == other.doc
+        return self.html == other.html
 
     @property
     def markdown(self) -> str:

music_kraken/objects/parents.py

@@ -29,12 +29,17 @@ class InnerData:
     """
 
     _refers_to_instances: set = None
+    _is_in_collection: set = None
+
+    _has_data: bool = False
     """
     Attribute versions keep track, of if the attribute has been changed.
     """
 
     def __init__(self, object_type, **kwargs):
         self._refers_to_instances = set()
+        self._is_in_collection = set()
+
         self._fetched_from: dict = {}
 
         # initialize the default values
@@ -45,9 +50,19 @@ class InnerData:
         for key, value in kwargs.items():
             if hasattr(value, "__is_collection__"):
                 value._collection_for[self] = key
-                
+            
             self.__setattr__(key, value)
 
+            if self._has_data:
+                continue
+    
+    def __setattr__(self, key: str, value):
+        if self._has_data or not hasattr(self, "_default_values"):
+            return super().__setattr__(key, value)
+        
+        super().__setattr__("_has_data", not (key in self._default_values and self._default_values[key] == value))
+        return super().__setattr__(key, value)
+
     def __hash__(self):
         return self.id
 
@@ -58,6 +73,7 @@ class InnerData:
         """
 
         self._fetched_from.update(__other._fetched_from)
+        self._is_in_collection.update(__other._is_in_collection)
 
         for key, value in __other.__dict__.copy().items():
             if key.startswith("_"):

music_kraken/objects/song.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import random
 from collections import defaultdict
 from typing import List, Optional, Dict, Tuple, Type, Union
+import copy
 
 import pycountry
 
@@ -110,7 +111,7 @@ class Song(Base):
         "album_collection": Collection,
         "feature_artist_collection": Collection,
 
-        "title": lambda: "",
+        "title": lambda: None,
         "unified_title": lambda: None,
         "isrc": lambda: None,
         "genre": lambda: None,
@@ -118,13 +119,27 @@ class Song(Base):
         "tracksort": lambda: 0,
     }
 
-    def __init__(self, title: str = "", unified_title: str = None, isrc: str = None, length: int = None,
-                 genre: str = None, note: FormattedText = None, source_list: List[Source] = None,
-                 target_list: List[Target] = None, lyrics_list: List[Lyrics] = None,
-                 main_artist_list: List[Artist] = None, feature_artist_list: List[Artist] = None,
-                 album_list: List[Album] = None, tracksort: int = 0, artwork: Optional[Artwork] = None, **kwargs) -> None:
+    def __init__(
+        self, 
+        title: str = None, 
+        isrc: str = None, 
+        length: int = None,
+        genre: str = None, 
+        note: FormattedText = None, 
+        source_list: List[Source] = None,
+        target_list: List[Target] = None, 
+        lyrics_list: List[Lyrics] = None,
+        main_artist_list: List[Artist] = None, 
+        feature_artist_list: List[Artist] = None,
+        album_list: List[Album] = None, 
+        tracksort: int = 0, 
+        artwork: Optional[Artwork] = None, 
+        **kwargs
+    ) -> None:
+        real_kwargs = copy.copy(locals())
+        real_kwargs.update(real_kwargs.pop("kwargs", {}))
 
-        Base.__init__(**locals())
+        Base.__init__(**real_kwargs)
 
     UPWARDS_COLLECTION_STRING_ATTRIBUTES = ("main_artist_collection", "feature_artist_collection", "album_collection")
     TITEL = "title"
@@ -210,14 +225,6 @@ class Song(Base):
         r += get_collection_string(self.feature_artist_collection, " feat. {}")
         return r
 
-    @property
-    def options(self) -> List[P]:
-        options = self.main_artist_collection.shallow_list
-        options.extend(self.feature_artist_collection)
-        options.extend(self.album_collection)
-        options.append(self)
-        return options
-
     @property
     def tracksort_str(self) -> str:
         """
@@ -273,15 +280,27 @@ class Album(Base):
     TITEL = "title"
 
     # This is automatically generated
-    def __init__(self, title: str = None, unified_title: str = None, album_status: AlbumStatus = None,
-                 album_type: AlbumType = None, language: Language = None, date: ID3Timestamp = None,
-                 barcode: str = None, albumsort: int = None, notes: FormattedText = None,
-                 source_list: List[Source] = None, artist_list: List[Artist] = None, song_list: List[Song] = None,
-                 label_list: List[Label] = None, **kwargs) -> None:
-        super().__init__(title=title, unified_title=unified_title, album_status=album_status, album_type=album_type,
-                         language=language, date=date, barcode=barcode, albumsort=albumsort, notes=notes,
-                         source_list=source_list, artist_list=artist_list, song_list=song_list, label_list=label_list,
-                         **kwargs)
+    def __init__(
+        self, 
+        title: str = None, 
+        unified_title: str = None, 
+        album_status: AlbumStatus = None,
+        album_type: AlbumType = None, 
+        language: Language = None, 
+        date: ID3Timestamp = None,
+        barcode: str = None, 
+        albumsort: int = None, 
+        notes: FormattedText = None,
+        source_list: List[Source] = None, 
+        artist_list: List[Artist] = None, 
+        song_list: List[Song] = None,
+        label_list: List[Label] = None, 
+        **kwargs
+    ) -> None:
+        real_kwargs = copy.copy(locals())
+        real_kwargs.update(real_kwargs.pop("kwargs", {}))
+
+        Base.__init__(**real_kwargs)
 
     DOWNWARDS_COLLECTION_STRING_ATTRIBUTES = ("song_collection",)
     UPWARDS_COLLECTION_STRING_ATTRIBUTES = ("label_collection", "artist_collection")
@@ -413,14 +432,8 @@ class Album(Base):
         return self.album_type.value
 
 
-"""
-All objects dependent on Artist
-"""
-
-
 class Artist(Base):
     name: str
-    unified_name: str
     country: Country
     formed_in: ID3Timestamp
     notes: FormattedText
@@ -437,8 +450,7 @@ class Artist(Base):
     label_collection: Collection[Label]
 
     _default_factories = {
-        "name": str,
-        "unified_name": lambda: None,
+        "name": lambda: None,
         "country": lambda: None,
         "unformatted_location": lambda: None,
 
@@ -457,17 +469,28 @@ class Artist(Base):
     TITEL = "name"
 
     # This is automatically generated
-    def __init__(self, name: str = "", unified_name: str = None, country: Country = None,
-                 formed_in: ID3Timestamp = None, notes: FormattedText = None, lyrical_themes: List[str] = None,
-                 general_genre: str = None, unformatted_location: str = None, source_list: List[Source] = None,
-                 contact_list: List[Contact] = None, feature_song_list: List[Song] = None,
-                 main_album_list: List[Album] = None, label_list: List[Label] = None, **kwargs) -> None:
-        
-        super().__init__(name=name, unified_name=unified_name, country=country, formed_in=formed_in, notes=notes,
-                         lyrical_themes=lyrical_themes, general_genre=general_genre,
-                         unformatted_location=unformatted_location, source_list=source_list, contact_list=contact_list,
-                         feature_song_list=feature_song_list, main_album_list=main_album_list, label_list=label_list,
-                         **kwargs)
+    def __init__(
+        self, 
+        name: str = None, 
+        unified_name: str = None, 
+        country: Country = None,
+        formed_in: ID3Timestamp = None, 
+        notes: FormattedText = None, 
+        lyrical_themes: List[str] = None,
+        general_genre: str = None, 
+        unformatted_location: str = None, 
+        source_list: List[Source] = None,
+        contact_list: List[Contact] = None, 
+        feature_song_list: List[Song] = None,
+        main_album_list: List[Album] = None, 
+        label_list: List[Label] = None, 
+        **kwargs
+    ) -> None:
+        real_kwargs = copy.copy(locals())
+        real_kwargs.update(real_kwargs.pop("kwargs", {}))
+
+        Base.__init__(**real_kwargs)
+
 
     DOWNWARDS_COLLECTION_STRING_ATTRIBUTES = ("main_album_collection", "feature_song_collection")
     UPWARDS_COLLECTION_STRING_ATTRIBUTES = ("label_collection",)
@@ -593,11 +616,6 @@ class Artist(Base):
         return r
 
 
-"""
-Label
-"""
-
-
 class Label(Base):
     COLLECTION_STRING_ATTRIBUTES = ("album_collection", "current_artist_collection")
 
@@ -625,12 +643,21 @@ class Label(Base):
 
     TITEL = "name"
 
-    def __init__(self, name: str = None, unified_name: str = None, notes: FormattedText = None,
-                 source_list: List[Source] = None, contact_list: List[Contact] = None,
-                 album_list: List[Album] = None, current_artist_list: List[Artist] = None, **kwargs) -> None:
-        super().__init__(name=name, unified_name=unified_name, notes=notes, source_list=source_list,
-                         contact_list=contact_list, album_list=album_list, current_artist_list=current_artist_list,
-                         **kwargs)
+    def __init__(
+        self, 
+        name: str = None, 
+        unified_name: str = None, 
+        notes: FormattedText = None,
+        source_list: List[Source] = None, 
+        contact_list: List[Contact] = None,
+        album_list: List[Album] = None, 
+        current_artist_list: List[Artist] = None, 
+        **kwargs
+    ) -> None:
+        real_kwargs = copy.copy(locals())
+        real_kwargs.update(real_kwargs.pop("kwargs", {}))
+
+        Base.__init__(**real_kwargs)
 
     def __init_collections__(self):
         self.album_collection.append_object_to_attribute = {

music_kraken/pages/abstract.py

@@ -3,8 +3,9 @@ import random
 import re
 from copy import copy
 from pathlib import Path
-from typing import Optional, Union, Type, Dict, Set, List, Tuple
+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
@@ -28,11 +29,23 @@ from ..utils.config import main_settings
 from ..utils.support_classes.query import Query
 from ..utils.support_classes.download_result import DownloadResult
 from ..utils.string_processing import fit_to_file_system
-from ..utils import trace
+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 NamingDict(dict):
     CUSTOM_KEYS: Dict[str, str] = {
@@ -101,6 +114,10 @@ class Page:
     # set this to true, if all song details can also be fetched by fetching album details
     NO_ADDITIONAL_DATA_FROM_SONG = False
 
+    def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None):
+        self.download_options: DownloadOptions = download_options or DownloadOptions()
+        self.fetch_options: FetchOptions = fetch_options or FetchOptions()
+
     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
@@ -176,7 +193,6 @@ class Page:
         self, 
         music_object: DatabaseObject, 
         stop_at_level: int = 1,
-        post_process: bool = True
     ) -> DatabaseObject:
         """
         when a music object with lacking data is passed in, it returns
@@ -208,7 +224,6 @@ class Page:
                     source=source,
                     enforce_type=type(music_object),
                     stop_at_level=stop_at_level,
-                    post_process=False,
                     type_string=type(music_object).__name__,
                     entity_string=music_object.option_string,
                 )
@@ -230,7 +245,6 @@ class Page:
         source: Source, 
         stop_at_level: int = 2,
         enforce_type: Type[DatabaseObject] = None, 
-        post_process: bool = True,
         type_string: str = "",
         entity_string: str = "",
     ) -> Optional[DatabaseObject]:
@@ -254,7 +268,7 @@ class Page:
         }
 
         if obj_type in fetch_map:
-            music_object = fetch_map[obj_type](source, stop_at_level)
+            music_object = fetch_map[obj_type](source, stop_at_level=stop_at_level)
         else:
             self.LOGGER.warning(f"Can't fetch details of type: {obj_type}")
             return None
@@ -268,7 +282,7 @@ class Page:
 
                 for sub_element in collection:
                     sub_element.merge(
-                        self.fetch_details(sub_element, stop_at_level=stop_at_level - 1, post_process=False))
+                        self.fetch_details(sub_element, stop_at_level=stop_at_level - 1))
 
         return music_object
 
@@ -288,8 +302,6 @@ class Page:
         self, 
         music_object: DatabaseObject, 
         genre: str, 
-        download_all: bool = False,
-        process_metadata_anyway: bool = True
     ) -> DownloadResult:
         naming_dict: NamingDict = NamingDict({"genre": genre})
 
@@ -308,25 +320,22 @@ class Page:
 
         fill_naming_objects(music_object)
 
-        return self._download(music_object, naming_dict, download_all, process_metadata_anyway=process_metadata_anyway)
+        return self._download(music_object, naming_dict)
 
     def _download(
         self, 
         music_object: DatabaseObject, 
         naming_dict: NamingDict, 
-        download_all: bool = False,
-        skip_details: bool = False, 
-        process_metadata_anyway: bool = True
+        **kwargs
     ) -> DownloadResult:
-        trace(f"downloading {type(music_object).__name__} [{music_object.option_string}]")
-        skip_next_details = skip_details
+        if isinstance(music_object, Song):
+            output(f"Downloading {music_object.option_string} to:", color=BColors.BOLD)
+        else:
+            output(f"Downloading {music_object.option_string}...", color=BColors.BOLD)
 
         # Skips all releases, that are defined in shared.ALBUM_TYPE_BLACKLIST, if download_all is False
         if isinstance(music_object, Album):
-            if self.NO_ADDITIONAL_DATA_FROM_SONG:
-                skip_next_details = True
-
-            if not download_all and music_object.album_type.value in main_settings["album_type_blacklist"]:
+            if not self.download_options.download_all and music_object.album_type in self.download_options.album_type_blacklist:
                 return DownloadResult()
 
         if not (isinstance(music_object, Song) and self.NO_ADDITIONAL_DATA_FROM_SONG):
@@ -338,7 +347,7 @@ class Page:
         naming_dict.add_object(music_object)
 
         if isinstance(music_object, Song):
-            return self._download_song(music_object, naming_dict, process_metadata_anyway=process_metadata_anyway)
+            return self._download_song(music_object, naming_dict)
 
         download_result: DownloadResult = DownloadResult()
 
@@ -347,13 +356,11 @@ class Page:
 
             sub_ordered_music_object: DatabaseObject
             for sub_ordered_music_object in collection:
-                download_result.merge(self._download(sub_ordered_music_object, naming_dict.copy(), download_all,
-                                                     skip_details=skip_next_details,
-                                                     process_metadata_anyway=process_metadata_anyway))
+                download_result.merge(self._download(sub_ordered_music_object, naming_dict.copy()))
 
         return download_result
 
-    def _download_song(self, song: Song, naming_dict: NamingDict, process_metadata_anyway: bool = True):
+    def _download_song(self, song: Song, naming_dict: NamingDict):
         if "genre" not in naming_dict and song.genre is not None:
             naming_dict["genre"] = song.genre
 
@@ -373,40 +380,33 @@ class Page:
         if song.target_collection.empty:
             song.target_collection.append(new_target)
 
+        r = DownloadResult(1)
+        temp_target: Target = Target.temp()
+
+        found_on_disc = False
+        target: Target
+        for target in song.target_collection:
+            current_exists = target.exists
+
+            if current_exists:
+                output(f'- {target.file_path} {BColors.OKGREEN.value}[already exists]', color=BColors.GREY)
+                target.copy_content(temp_target)
+                found_on_disc = True
+
+                r.found_on_disk += 1
+                r.add_target(target)
+            else:
+                output(f'- {target.file_path}', color=BColors.GREY)
+
         if not song.source_collection.has_source_page(self.SOURCE_TYPE):
             return DownloadResult(error_message=f"No {self.__class__.__name__} source found for {song.option_string}.")
 
         sources = song.source_collection.get_sources(self.SOURCE_TYPE)
 
-        temp_target: Target = Target(
-            relative_to_music_dir=False,
-            file_path=Path(
-                main_settings["temp_directory"],
-                str(song.id)
-            )
-        )
-
-        r = DownloadResult(1)
-
-        found_on_disc = False
-        target: Target
-        for target in song.target_collection:
-            if target.exists:
-                if process_metadata_anyway:
-                    target.copy_content(temp_target)
-                found_on_disc = True
-
-                r.found_on_disk += 1
-                r.add_target(target)
-
-        if found_on_disc and not process_metadata_anyway:
-            self.LOGGER.info(f"{song.option_string} already exists, thus not downloading again.")
-            return r
-
         skip_intervals = []
         if not found_on_disc:
             for source in sources:
-                r = self.download_song_to_target(source=source, target=temp_target, desc=song.option_string)
+                r = self.download_song_to_target(source=source, target=temp_target, desc="downloading")
 
                 if not r.is_fatal_error:
                     skip_intervals = self.get_skip_intervals(song, source)
@@ -417,16 +417,19 @@ class Page:
                 song=song, 
                 temp_target=temp_target,
                 interval_list=skip_intervals,
+                found_on_disc=found_on_disc,
             ))
 
         return r
 
-    def _post_process_targets(self, song: Song, temp_target: Target, interval_list: List) -> DownloadResult:
-        correct_codec(temp_target, interval_list=interval_list)
+    def _post_process_targets(self, song: Song, temp_target: Target, interval_list: List, found_on_disc: bool) -> DownloadResult:
+        if not found_on_disc or self.download_options.process_audio_if_found:
+            correct_codec(temp_target, interval_list=interval_list)
 
         self.post_process_hook(song, temp_target)
 
-        write_metadata_to_target(song.metadata, temp_target, song)
+        if not found_on_disc or self.download_options.process_metadata_if_found:
+            write_metadata_to_target(song.metadata, temp_target, song)
 
         r = DownloadResult()
 

music_kraken/pages/bandcamp.py

@@ -22,6 +22,7 @@ from ..objects import (
     Artwork,
 )
 from ..connection import Connection
+from ..utils import dump_to_file
 from ..utils.support_classes.download_result import DownloadResult
 from ..utils.string_processing import clean_song_title
 from ..utils.config import main_settings, logging_settings

music_kraken/pages/musify.py

@@ -1,7 +1,7 @@
 from collections import defaultdict
 from dataclasses import dataclass
 from enum import Enum
-from typing import List, Optional, Type, Union, Generator
+from typing import List, Optional, Type, Union, Generator, Dict, Any
 from urllib.parse import urlparse
 
 import pycountry
@@ -24,7 +24,7 @@ from ..objects import (
     Lyrics,
     Artwork
 )
-from ..utils.config import logging_settings
+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
@@ -361,7 +361,7 @@ class Musify(Page):
 
         return Song(
             title=clean_song_title(song_title, artist_name=artist_list[0].name if len(artist_list) > 0 else None),
-            main_artist_list=artist_list,
+            feature_artist_list=artist_list,
             source_list=source_list
         )
 
@@ -418,6 +418,10 @@ class Musify(Page):
             
             href = artist_soup["href"]
             if href is not None:
+                href_parts = href.split("/")
+                if len(href_parts) <= 1 or href_parts[-2] != "artist":
+                    return
+
                 artist_src_list.append(Source(self.SOURCE_TYPE, self.HOST + href))
 
             name_elem: BeautifulSoup = artist_soup.find("span", {"itemprop": "name"})
@@ -510,7 +514,7 @@ class Musify(Page):
             title=clean_song_title(track_name, artist_name=artist_list[0].name if len(artist_list) > 0 else None),
             source_list=source_list,
             lyrics_list=lyrics_list,
-            main_artist_list=artist_list,
+            feature_artist_list=artist_list,
             album_list=album_list,
             artwork=artwork,
         )
@@ -652,10 +656,104 @@ class Musify(Page):
         return Song(
             title=clean_song_title(song_name, artist_name=artist_list[0].name if len(artist_list) > 0 else None),
             tracksort=tracksort,
-            main_artist_list=artist_list,
+            feature_artist_list=artist_list,
             source_list=source_list
         )
 
+    
+    def _parse_album(self, soup: BeautifulSoup) -> Album:
+        name: str = None
+        source_list: List[Source] = []
+        artist_list: List[Artist] = []
+        date: ID3Timestamp = None
+
+        """
+        if breadcrumb list has 4 elements, then
+        the -2 is the artist link,
+        the -1 is the album
+        """
+        # breadcrumb
+        breadcrumb_soup: BeautifulSoup = soup.find("ol", {"class", "breadcrumb"})
+        breadcrumb_elements: List[BeautifulSoup] = breadcrumb_soup.find_all("li", {"class": "breadcrumb-item"})
+        if len(breadcrumb_elements) == 4:
+            # album
+            album_crumb: BeautifulSoup = breadcrumb_elements[-1]
+            name = album_crumb.text.strip()
+
+            # artist
+            artist_crumb: BeautifulSoup = breadcrumb_elements[-2]
+            anchor: BeautifulSoup = artist_crumb.find("a")
+            if anchor is not None:
+                href = anchor.get("href")
+
+                href_parts = href.split("/")
+                if not(len(href_parts) <= 1 or href_parts[-2] != "artist"):
+                    artist_source_list: List[Source] = []
+
+                    if href is not None:
+                        artist_source_list.append(Source(self.SOURCE_TYPE, self.HOST + href.strip()))
+
+                    span: BeautifulSoup = anchor.find("span")
+                    if span is not None:
+                        artist_list.append(Artist(
+                            name=span.get_text(strip=True),
+                            source_list=artist_source_list
+                        ))
+        else:
+            self.LOGGER.debug("there are not 4 breadcrumb items, which shouldn't be the case")
+
+        # meta
+        meta_url: BeautifulSoup = soup.find("meta", {"itemprop": "url"})
+        if meta_url is not None:
+            url = meta_url.get("content")
+            if url is not None:
+                source_list.append(Source(self.SOURCE_TYPE, self.HOST + url))
+
+        meta_name: BeautifulSoup = soup.find("meta", {"itemprop": "name"})
+        if meta_name is not None:
+            _name = meta_name.get("content")
+            if _name is not None:
+                name = _name
+                
+        # album info
+        album_info_ul: BeautifulSoup = soup.find("ul", {"class": "album-info"})
+        if album_info_ul is not None:
+            artist_anchor: BeautifulSoup
+            for artist_anchor in album_info_ul.find_all("a", {"itemprop": "byArtist"}):
+                # line 98
+                artist_source_list: List[Source] = []
+
+                artist_url_meta = artist_anchor.find("meta", {"itemprop": "url"})
+                if artist_url_meta is not None:
+                    artist_href = artist_url_meta.get("content")
+                    if artist_href is not None:
+                        artist_source_list.append(Source(self.SOURCE_TYPE, url=self.HOST + artist_href))
+
+                artist_meta_name = artist_anchor.find("meta", {"itemprop": "name"})
+                if artist_meta_name is not None:
+                    artist_name = artist_meta_name.get("content")
+                    if artist_name is not None:
+                        artist_list.append(Artist(
+                            name=artist_name,
+                            source_list=artist_source_list
+                        ))
+
+            time_soup: BeautifulSoup = album_info_ul.find("time", {"itemprop": "datePublished"})
+            if time_soup is not None:
+                raw_datetime = time_soup.get("datetime")
+                if raw_datetime is not None:
+                    try:
+                        date = ID3Timestamp.strptime(raw_datetime, "%Y-%m-%d")
+                    except ValueError:
+                        self.LOGGER.debug(f"Raw datetime doesn't match time format %Y-%m-%d: {raw_datetime}")
+
+        return Album(
+            title=name,
+            source_list=source_list,
+            artist_list=artist_list,
+            date=date
+        )
+
     def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
         """
         fetches album from source:
@@ -694,19 +792,14 @@ class Musify(Page):
 
         return album
     
-    def _get_artist_attributes(self, url: MusifyUrl) -> Artist:
+    def _fetch_initial_artist(self, url: MusifyUrl, source: Source, **kwargs) -> Artist:
         """
-        fetches the main Artist attributes from this endpoint
         https://musify.club/artist/ghost-bath-280348?_pjax=#bodyContent
-        it needs to parse html
-
-        :param url:
-        :return:
         """
 
         r = self.connection.get(f"https://musify.club/{url.source_type.value}/{url.name_with_id}?_pjax=#bodyContent", name="artist_attributes_" + url.name_with_id)
         if r is None:
-            return Artist()
+            return Artist(source_list=[source])
 
         soup = self.get_soup_from_response(r)
 
@@ -821,7 +914,7 @@ class Musify(Page):
             notes=notes
         )
 
-    def _parse_album_card(self, album_card: BeautifulSoup, artist_name: str = None) -> Album:
+    def _parse_album_card(self, album_card: BeautifulSoup, artist_name: str = None, **kwargs) -> Album:
         """
         <div class="card release-thumbnail" data-type="2">
             <a href="/release/ghost-bath-self-loather-2021-1554266">
@@ -845,46 +938,20 @@ class Musify(Page):
         </div>
         """
 
-        _id: Optional[str] = None
-        name: str = None
-        source_list: List[Source] = []
-        timestamp: Optional[ID3Timestamp] = None
-        album_status = None
-
-        def set_name(new_name: str):
-            nonlocal name
-            nonlocal artist_name
-            
-            # example of just setting not working:
-            # https://musify.club/release/unjoy-eurythmie-psychonaut-4-tired-numb-still-alive-2012-324067
-            if new_name.count(" - ") != 1:
-                name = new_name
-                return
-            
-            potential_artist_list, potential_name = new_name.split(" - ")
-            unified_artist_list = string_processing.unify(potential_artist_list)
-            if artist_name is not None:
-                if string_processing.unify(artist_name) not in unified_artist_list:
-                    name = new_name
-                    return
-                
-                name = potential_name
-                return
-            
-            name = new_name
+        album_kwargs: Dict[str, Any] = {
+            "source_list": [],
+        }
 
         album_status_id = album_card.get("data-type")
         if album_status_id.isdigit():
             album_status_id = int(album_status_id)
-        album_type = ALBUM_TYPE_MAP[album_status_id]
+        album_kwargs["album_type"] = ALBUM_TYPE_MAP[album_status_id]
 
         if album_status_id == 5:
-            album_status = AlbumStatus.BOOTLEG
+            album_kwargs["album_status"] = AlbumStatus.BOOTLEG
 
         def parse_release_anchor(_anchor: BeautifulSoup, text_is_name=False):
-            nonlocal _id
-            nonlocal name
-            nonlocal source_list
+            nonlocal album_kwargs
 
             if _anchor is None:
                 return
@@ -892,20 +959,13 @@ class Musify(Page):
             href = _anchor.get("href")
             if href is not None:
                 # add url to sources
-                source_list.append(Source(
+                album_kwargs["source_list"].append(Source(
                     self.SOURCE_TYPE,
                     self.HOST + href
                 ))
 
-                # split id from url
-                split_href = href.split("-")
-                if len(split_href) > 1:
-                    _id = split_href[-1]
-
-            if not text_is_name:
-                return
-
-            set_name(_anchor.text)
+            if text_is_name:
+                album_kwargs["title"] = clean_song_title(_anchor.text, artist_name)
 
         anchor_list = album_card.find_all("a", recursive=False)
         if len(anchor_list) > 0:
@@ -916,7 +976,7 @@ class Musify(Page):
             if thumbnail is not None:
                 alt = thumbnail.get("alt")
                 if alt is not None:
-                    set_name(alt)
+                    album_kwargs["title"] = clean_song_title(alt, artist_name)
 
                 image_url = thumbnail.get("src")
         else:
@@ -933,7 +993,7 @@ class Musify(Page):
                 13.11.2021
             </small>
             """
-            nonlocal timestamp
+            nonlocal album_kwargs
 
             italic_tagging_soup: BeautifulSoup = small_soup.find("i")
             if italic_tagging_soup is None:
@@ -943,7 +1003,7 @@ class Musify(Page):
                 return
 
             raw_time = small_soup.text.strip()
-            timestamp = ID3Timestamp.strptime(raw_time, "%d.%m.%Y")
+            album_kwargs["date"] = ID3Timestamp.strptime(raw_time, "%d.%m.%Y")
 
         # parse small date
         card_footer_list = album_card.find_all("div", {"class": "card-footer"})
@@ -956,112 +1016,18 @@ class Musify(Page):
         else:
             self.LOGGER.debug("there is not even 1 footer in the album card")
 
-        return Album(
-            title=name,
-            source_list=source_list,
-            date=timestamp,
-            album_type=album_type,
-            album_status=album_status
-        )
+        return Album(**album_kwargs)
 
-    def _parse_album(self, soup: BeautifulSoup) -> Album:
-        name: str = None
-        source_list: List[Source] = []
-        artist_list: List[Artist] = []
-        date: ID3Timestamp = None
-
-        """
-        if breadcrumb list has 4 elements, then
-        the -2 is the artist link,
-        the -1 is the album
-        """
-        # breadcrumb
-        breadcrumb_soup: BeautifulSoup = soup.find("ol", {"class", "breadcrumb"})
-        breadcrumb_elements: List[BeautifulSoup] = breadcrumb_soup.find_all("li", {"class": "breadcrumb-item"})
-        if len(breadcrumb_elements) == 4:
-            # album
-            album_crumb: BeautifulSoup = breadcrumb_elements[-1]
-            name = album_crumb.text.strip()
-
-            # artist
-            artist_crumb: BeautifulSoup = breadcrumb_elements[-2]
-            anchor: BeautifulSoup = artist_crumb.find("a")
-            if anchor is not None:
-                href = anchor.get("href")
-                artist_source_list: List[Source] = []
-
-                if href is not None:
-                    artist_source_list.append(Source(self.SOURCE_TYPE, self.HOST + href.strip()))
-
-                span: BeautifulSoup = anchor.find("span")
-                if span is not None:
-                    artist_list.append(Artist(
-                        name=span.get_text(strip=True),
-                        source_list=artist_source_list
-                    ))
-        else:
-            self.LOGGER.debug("there are not 4 breadcrumb items, which shouldn't be the case")
-
-        # meta
-        meta_url: BeautifulSoup = soup.find("meta", {"itemprop": "url"})
-        if meta_url is not None:
-            url = meta_url.get("content")
-            if url is not None:
-                source_list.append(Source(self.SOURCE_TYPE, self.HOST + url))
-
-        meta_name: BeautifulSoup = soup.find("meta", {"itemprop": "name"})
-        if meta_name is not None:
-            _name = meta_name.get("content")
-            if _name is not None:
-                name = _name
-                
-        # album info
-        album_info_ul: BeautifulSoup = soup.find("ul", {"class": "album-info"})
-        if album_info_ul is not None:
-            artist_anchor: BeautifulSoup
-            for artist_anchor in album_info_ul.find_all("a", {"itemprop": "byArtist"}):
-                # line 98
-                artist_source_list: List[Source] = []
-
-                artist_url_meta = artist_anchor.find("meta", {"itemprop": "url"})
-                if artist_url_meta is not None:
-                    artist_href = artist_url_meta.get("content")
-                    if artist_href is not None:
-                        artist_source_list.append(Source(self.SOURCE_TYPE, url=self.HOST + artist_href))
-
-                artist_meta_name = artist_anchor.find("meta", {"itemprop": "name"})
-                if artist_meta_name is not None:
-                    artist_name = artist_meta_name.get("content")
-                    if artist_name is not None:
-                        artist_list.append(Artist(
-                            name=artist_name,
-                            source_list=artist_source_list
-                        ))
-
-            time_soup: BeautifulSoup = album_info_ul.find("time", {"itemprop": "datePublished"})
-            if time_soup is not None:
-                raw_datetime = time_soup.get("datetime")
-                if raw_datetime is not None:
-                    try:
-                        date = ID3Timestamp.strptime(raw_datetime, "%Y-%m-%d")
-                    except ValueError:
-                        self.LOGGER.debug(f"Raw datetime doesn't match time format %Y-%m-%d: {raw_datetime}")
-
-        return Album(
-            title=name,
-            source_list=source_list,
-            artist_list=artist_list,
-            date=date
-        )
-
-    def _get_discography(self, url: MusifyUrl, artist_name: str = None, stop_at_level: int = 1) -> Generator[Album, None, None]:
+    def _fetch_artist_discography(self, artist: Artist, url: MusifyUrl, artist_name: str = None, **kwargs):
         """
         POST https://musify.club/artist/filteralbums
-        ArtistID: 280348
-        SortOrder.Property: dateCreated
-        SortOrder.IsAscending: false
-        X-Requested-With: XMLHttpRequest
+            ArtistID: 280348
+            SortOrder.Property: dateCreated
+            SortOrder.IsAscending: false
+            X-Requested-With: XMLHttpRequest
         """
+        _download_all = kwargs.get("download_all", False)
+        _album_type_blacklist = kwargs.get("album_type_blacklist", main_settings["album_type_blacklist"])
 
         endpoint = self.HOST + "/" + url.source_type.value + "/filteralbums"
 
@@ -1072,33 +1038,29 @@ class Musify(Page):
             "X-Requested-With": "XMLHttpRequest"
         }, name="discography_" + url.name_with_id)
         if r is None:
-            return []
-        soup: BeautifulSoup = BeautifulSoup(r.content, features="html.parser")
+            return
+
+        soup: BeautifulSoup = self.get_soup_from_response(r)
 
         for card_soup in soup.find_all("div", {"class": "card"}):
-            yield self._parse_album_card(card_soup, artist_name)
+            album = self._parse_album_card(card_soup, artist_name, **kwargs)
+            if not self.fetch_options.download_all and album.album_type in self.fetch_options.album_type_blacklist:
+                continue
 
-    def fetch_artist(self, source: Source, stop_at_level: int = 1) -> Artist:
+            artist.main_album_collection.append(album)
+
+    def fetch_artist(self, source: Source, **kwargs) -> Artist:
         """
-        fetches artist from source
-
+        TODO
         [x] discography
         [x] attributes
         [] picture gallery
-
-        Args:
-            source (Source): the source to fetch
-            stop_at_level: int = 1: if it is false, every album from discograohy will be fetched. Defaults to False.
-
-        Returns:
-            Artist: the artist fetched
         """
 
         url = parse_url(source.url)
 
-        artist = self._get_artist_attributes(url)
-
-        artist.main_album_collection.extend(self._get_discography(url, artist.name))
+        artist = self._fetch_initial_artist(url, source=source, **kwargs)
+        self._fetch_artist_discography(artist, url, artist.name, **kwargs)
         
         return artist
 

music_kraken/pages/youtube.py

@@ -42,7 +42,7 @@ class YouTube(SuperYouTube):
     SOURCE_TYPE = SourcePages.YOUTUBE
     LOGGER = logging_settings["youtube_logger"]
 
-    NO_ADDITIONAL_DATA_FROM_SONG = True
+    NO_ADDITIONAL_DATA_FROM_SONG = False
 
     def __init__(self, *args, **kwargs):
         self.connection: Connection = Connection(

music_kraken/utils/shared.py

@@ -12,7 +12,7 @@ if not load_dotenv(Path(__file__).parent.parent.parent / ".env"):
 
 __stage__ = os.getenv("STAGE", "prod")
 
-DEBUG = (__stage__ == "dev") and True
+DEBUG = (__stage__ == "dev") and False
 DEBUG_LOGGING = DEBUG and False
 DEBUG_TRACE = DEBUG and True
 DEBUG_OBJECT_TRACE = DEBUG and False

music_kraken/utils/string_processing.py

@@ -116,10 +116,13 @@ def clean_song_title(raw_song_title: str, artist_name: Optional[str] = None) ->
 
         # Remove artist from the start of the title
         if raw_song_title.lower().startswith(artist_name.lower()):
-            raw_song_title = raw_song_title[len(artist_name):].strip()
 
-            if raw_song_title.startswith("-"):
-                raw_song_title = raw_song_title[1:].strip()
+            possible_new_name = raw_song_title[len(artist_name):].strip()
+
+            for char in ("-", "–", ":", "|"):
+                if possible_new_name.startswith(char):
+                    raw_song_title = possible_new_name[1:].strip()
+                    break
 
     return raw_song_title.strip()
 

pyproject.toml

@@ -69,7 +69,7 @@ dependencies = [
     "toml~=0.10.2",
     "typing_extensions~=4.7.1",
 
-    "python-sponsorblock~=0.0.0",
+    "python-sponsorblock~=0.0.dev1",
     "youtube_dl",
 ]
 dynamic = [