draft:
All checks were successful
ci/woodpecker/push/woodpecker Pipeline was successful

This commit is contained in:
Hazel 2024-05-23 17:27:24 +02:00
parent cd2e7d7173
commit 906ddb679d
10 changed files with 76 additions and 596 deletions

View File

@ -1,255 +0,0 @@
import logging
import re
from collections import defaultdict
from pathlib import Path
from typing import Dict, List, Optional, Set, Tuple, Type
from ..audio import correct_codec, write_metadata_to_target
from ..objects import Album, Artist, Collection
from ..objects import DatabaseObject as DataObject
from ..objects import Label, Options, Song, Source, Target
from ..pages import get_pages, scan_for_pages
from ..utils import BColors, output
from ..utils.config import main_settings, youtube_settings
from ..utils.enums import ALL_SOURCE_TYPES, SourceType
from ..utils.exception import MKMissingNameException
from ..utils.exception.download import UrlNotFoundException
from ..utils.path_manager import LOCATIONS
from ..utils.shared import DEBUG_PAGES
from ..utils.string_processing import fit_to_file_system
from ..utils.support_classes.download_result import DownloadResult
from ..utils.support_classes.query import Query
from . import DownloadOptions, FetchOptions
from .results import SearchResults
fetch_map = {
Song: "fetch_song",
Album: "fetch_album",
Artist: "fetch_artist",
Label: "fetch_label",
}
class Pages:
def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
self.LOGGER = logging.getLogger("download")
self.download_options: DownloadOptions = download_options or DownloadOptions()
self.fetch_options: FetchOptions = fetch_options or FetchOptions()
scan_for_pages(download_options=self.download_options, fetch_options=self.fetch_options, **kwargs)
def search(self, query: Query) -> SearchResults:
result = SearchResults()
for page in get_pages():
result.add(
page=type(page),
search_result=page.search(query=query)
)
return result
def fetch_details(self, data_object: DataObject, stop_at_level: int = 1, **kwargs) -> DataObject:
source: Source
for source in data_object.source_collection.get_sources(source_type_sorting={
"only_with_page": True,
}):
new_data_object = self.fetch_from_source(source=source, stop_at_level=stop_at_level)
if new_data_object is not None:
data_object.merge(new_data_object)
return data_object
def fetch_from_source(self, source: Source, **kwargs) -> Optional[DataObject]:
if not source.has_page:
return None
source_type = source.page.get_source_type(source=source)
if source_type is None:
self.LOGGER.debug(f"Could not determine source type for {source}.")
return None
func = getattr(source.page, fetch_map[source_type])
# fetching the data object and marking it as fetched
data_object: DataObject = func(source=source, **kwargs)
data_object.mark_as_fetched(source.hash_url)
return data_object
def fetch_from_url(self, url: str) -> Optional[DataObject]:
source = Source.match_url(url, ALL_SOURCE_TYPES.MANUAL)
if source is None:
return None
return self.fetch_from_source(source=source)
def _skip_object(self, data_object: DataObject) -> bool:
if isinstance(data_object, Album):
if not self.download_options.download_all and data_object.album_type in self.download_options.album_type_blacklist:
return True
return False
def download(self, data_object: DataObject, genre: str, **kwargs) -> DownloadResult:
# fetch the given object
self.fetch_details(data_object)
output(f"\nDownloading {data_object.option_string}...", color=BColors.BOLD)
# fetching all parent objects (e.g. if you only download a song)
if not kwargs.get("fetched_upwards", False):
to_fetch: List[DataObject] = [data_object]
while len(to_fetch) > 0:
new_to_fetch = []
for d in to_fetch:
if self._skip_object(d):
continue
self.fetch_details(d)
for c in d.get_parent_collections():
new_to_fetch.extend(c)
to_fetch = new_to_fetch
kwargs["fetched_upwards"] = True
# download all children
download_result: DownloadResult = DownloadResult()
for c in data_object.get_child_collections():
for d in c:
if self._skip_object(d):
continue
download_result.merge(self.download(d, genre, **kwargs))
# actually download if the object is a song
if isinstance(data_object, Song):
"""
TODO
add the traced artist and album to the naming.
I am able to do that, because duplicate values are removed later on.
"""
self._download_song(data_object, naming={
"genre": [genre],
"audio_format": [main_settings["audio_format"]],
})
return download_result
def _extract_fields_from_template(self, path_template: str) -> Set[str]:
return set(re.findall(r"{([^}]+)}", path_template))
def _parse_path_template(self, path_template: str, naming: Dict[str, List[str]]) -> str:
field_names: Set[str] = self._extract_fields_from_template(path_template)
for field in field_names:
if len(naming[field]) == 0:
raise MKMissingNameException(f"Missing field for {field}.")
path_template = path_template.replace(f"{{{field}}}", naming[field][0])
return path_template
def _download_song(self, song: Song, naming: dict) -> DownloadOptions:
"""
TODO
Search the song in the file system.
"""
r = DownloadResult(total=1)
# pre process the data recursively
song.compile()
# manage the naming
naming: Dict[str, List[str]] = defaultdict(list, naming)
naming["song"].append(song.title_value)
naming["isrc"].append(song.isrc)
naming["album"].extend(a.title_value for a in song.album_collection)
naming["album_type"].extend(a.album_type.value for a in song.album_collection)
naming["artist"].extend(a.name for a in song.artist_collection)
naming["artist"].extend(a.name for a in song.feature_artist_collection)
for a in song.album_collection:
naming["label"].extend([l.title_value for l in a.label_collection])
# removing duplicates from the naming, and process the strings
for key, value in naming.items():
# https://stackoverflow.com/a/17016257
naming[key] = list(dict.fromkeys(value))
song.genre = naming["genre"][0]
# manage the targets
tmp: Target = Target.temp(file_extension=main_settings["audio_format"])
song.target_collection.append(Target(
relative_to_music_dir=True,
file_path=Path(
self._parse_path_template(main_settings["download_path"], naming=naming),
self._parse_path_template(main_settings["download_file"], naming=naming),
)
))
for target in song.target_collection:
if target.exists:
output(f'{target.file_path} {BColors.OKGREEN.value}[already exists]', color=BColors.GREY)
r.found_on_disk += 1
if not self.download_options.download_again_if_found:
target.copy_content(tmp)
else:
target.create_path()
output(f'{target.file_path}', color=BColors.GREY)
# this streams from every available source until something succeeds, setting the skip intervals to the values of the according source
used_source: Optional[Source] = None
skip_intervals: List[Tuple[float, float]] = []
for source in song.source_collection.get_sources(source_type_sorting={
"only_with_page": True,
"sort_key": lambda page: page.download_priority,
"reverse": True,
}):
if tmp.exists:
break
used_source = source
streaming_results = source.page.download_song_to_target(source=source, target=tmp, desc="download")
skip_intervals = source.page.get_skip_intervals(song=song, source=source)
# if something has been downloaded but it somehow failed, delete the file
if streaming_results.is_fatal_error and tmp.exists:
tmp.delete()
# if everything went right, the file should exist now
if not tmp.exists:
if used_source is None:
r.error_message = f"No source found for {song.option_string}."
else:
r.error_message = f"Something went wrong downloading {song.option_string}."
return r
# post process the audio
found_on_disk = used_source is None
if not found_on_disk or self.download_options.process_audio_if_found:
correct_codec(target=tmp, skip_intervals=skip_intervals)
r.sponsor_segments = len(skip_intervals)
if used_source is not None:
used_source.page.post_process_hook(song=song, temp_target=tmp)
if not found_on_disk or self.download_options.process_metadata_if_found:
write_metadata_to_target(metadata=song.metadata, target=tmp, song=song)
# copy the tmp target to the final locations
for target in song.target_collection:
tmp.copy_content(target)
tmp.delete()
return r
def fetch_url(self, url: str, **kwargs) -> DataObject:
source = Source.match_url(url, ALL_SOURCE_TYPES.MANUAL)
if source is None or source.page is None:
raise UrlNotFoundException(url=url)
return source.page.fetch_object_from_source(source=source, **kwargs)

View File

@ -1,8 +1,8 @@
from typing import Tuple, Type, Dict, List, Generator, Union
from dataclasses import dataclass
from typing import Dict, Generator, List, Tuple, Type, Union
from ..objects import DatabaseObject
from ..pages import Page, EncyclopaediaMetallum, Musify
from . import Page
@dataclass

View File

@ -1,55 +1,9 @@
from typing import Type, Generator, Set, Dict, List
from collections import defaultdict
from typing import Dict, Generator, List, Set, Type
from ._bandcamp import Bandcamp
from ._encyclopaedia_metallum import EncyclopaediaMetallum
from ._genius import Genius
from ._musify import Musify
from ._youtube import YouTube
from ._youtube_music import YoutubeMusic
from ._bandcamp import Bandcamp
from ._genius import Genius
from ._abstract import Page, INDEPENDENT_DB_OBJECTS
_registered_pages: Dict[Type[Page], Set[Page]] = defaultdict(set)
def get_pages(*page_types: List[Type[Page]]) -> Generator[Page, None, None]:
if len(page_types) == 0:
page_types = _registered_pages.keys()
for page_type in page_types:
yield from _registered_pages[page_type]
def register_page(page_type: Type[Page], **kwargs):
if page_type in _registered_pages:
return
_registered_pages[page_type].add(page_type(**kwargs))
def deregister_page(page_type: Type[Page]):
if page_type not in _registered_pages:
return
for p in _registered_pages[page_type]:
p.__del__()
del _registered_pages[page_type]
def scan_for_pages(**kwargs):
# assuming the wanted pages are the leaf classes of the interface
leaf_classes = []
_class_list = [Page]
while len(_class_list):
_class = _class_list.pop()
_class_subclasses = _class.__subclasses__()
if len(_class_subclasses) == 0:
if _class.REGISTER:
leaf_classes.append(_class)
else:
_class_list.extend(_class_subclasses)
for leaf_class in leaf_classes:
register_page(leaf_class, **kwargs)

View File

@ -1,152 +0,0 @@
from __future__ import annotations
import logging
import random
import re
from copy import copy
from pathlib import Path
from typing import Optional, Union, Type, Dict, Set, List, Tuple, TypedDict, TYPE_CHECKING
from string import Formatter
from dataclasses import dataclass, field
import requests
from bs4 import BeautifulSoup
if TYPE_CHECKING:
from ..download.page_attributes import DownloadOptions, FetchOptions
from ..connection import Connection
from ..objects import (
Song,
Source,
Album,
Artist,
Target,
DatabaseObject,
Options,
Collection,
Label,
)
from ..utils.enums import SourceType
from ..utils.enums.album import AlbumType
from ..audio import write_metadata_to_target, correct_codec
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, output, BColors
INDEPENDENT_DB_OBJECTS = Union[Label, Album, Artist, Song]
INDEPENDENT_DB_TYPES = Union[Type[Song], Type[Album], Type[Artist], Type[Label]]
class Page:
REGISTER = True
SOURCE_TYPE: SourceType
LOGGER: logging.Logger
def __new__(cls, *args, **kwargs):
cls.LOGGER = logging.getLogger(cls.__name__)
return super().__new__(cls)
def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
self.SOURCE_TYPE.register_page(self)
self.download_options: DownloadOptions = download_options or DownloadOptions()
self.fetch_options: FetchOptions = fetch_options or FetchOptions()
def __del__(self):
self.SOURCE_TYPE.deregister_page()
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
patterns returning the first matching group.
In case of failure return a default value or raise a WARNING or a
RegexNotFoundError, depending on fatal, specifying the field name.
"""
if isinstance(pattern, str):
mobj = re.search(pattern, string, flags)
else:
for p in pattern:
mobj = re.search(p, string, flags)
if mobj:
break
if mobj:
if group is None:
# return the first matching group
return next(g for g in mobj.groups() if g is not None)
elif isinstance(group, (list, tuple)):
return tuple(mobj.group(g) for g in group)
else:
return mobj.group(group)
return default
def get_source_type(self, source: Source) -> Optional[Type[DatabaseObject]]:
return None
def get_soup_from_response(self, r: requests.Response) -> BeautifulSoup:
return BeautifulSoup(r.content, "html.parser")
# to search stuff
def search(self, query: Query) -> List[DatabaseObject]:
music_object = query.music_object
search_functions = {
Song: self.song_search,
Album: self.album_search,
Artist: self.artist_search,
Label: self.label_search
}
if type(music_object) in search_functions:
r = search_functions[type(music_object)](music_object)
if r is not None and len(r) > 0:
return r
r = []
for default_query in query.default_search:
for single_option in self.general_search(default_query):
r.append(single_option)
return r
def general_search(self, search_query: str) -> List[DatabaseObject]:
return []
def label_search(self, label: Label) -> List[Label]:
return []
def artist_search(self, artist: Artist) -> List[Artist]:
return []
def album_search(self, album: Album) -> List[Album]:
return []
def song_search(self, song: Song) -> List[Song]:
return []
# to fetch stuff
def fetch_song(self, source: Source, stop_at_level: int = 1) -> Song:
return Song()
def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
return Album()
def fetch_artist(self, source: Source, stop_at_level: int = 1) -> Artist:
return Artist()
def fetch_label(self, source: Source, stop_at_level: int = 1) -> Label:
return Label()
# to download stuff
def get_skip_intervals(self, song: Song, source: Source) -> List[Tuple[float, float]]:
return []
def post_process_hook(self, song: Song, temp_target: Target, **kwargs):
pass
def download_song_to_target(self, source: Source, target: Target, desc: str = None) -> DownloadResult:
return DownloadResult()

View File

@ -1,33 +1,22 @@
from typing import List, Optional, Type
from urllib.parse import urlparse, urlunparse
import json
from enum import Enum
from bs4 import BeautifulSoup
import pycountry
from typing import List, Optional, Type
from urllib.parse import urlparse, urlunparse
import pycountry
from bs4 import BeautifulSoup
from ..objects import Source, DatabaseObject
from ._abstract import Page
from ..objects import (
Artist,
Source,
SourceType,
Song,
Album,
Label,
Target,
Contact,
ID3Timestamp,
Lyrics,
FormattedText,
Artwork,
)
from ..connection import Connection
from ..download import Page
from ..objects import (Album, Artist, Artwork, Contact, DatabaseObject,
FormattedText, ID3Timestamp, Label, Lyrics, Song,
Source, SourceType, Target)
from ..utils import dump_to_file
from ..utils.enums import SourceType, ALL_SOURCE_TYPES
from ..utils.support_classes.download_result import DownloadResult
from ..utils.string_processing import clean_song_title
from ..utils.config import main_settings, logging_settings
from ..utils.config import logging_settings, main_settings
from ..utils.enums import ALL_SOURCE_TYPES, SourceType
from ..utils.shared import DEBUG
from ..utils.string_processing import clean_song_title
from ..utils.support_classes.download_result import DownloadResult
if DEBUG:
from ..utils import dump_to_file

View File

@ -1,31 +1,20 @@
from collections import defaultdict
from typing import List, Optional, Dict, Type, Union
from bs4 import BeautifulSoup
from typing import Dict, List, Optional, Type, Union
from urllib.parse import urlencode, urlparse
import pycountry
from urllib.parse import urlparse, urlencode
from bs4 import BeautifulSoup
from ..connection import Connection
from ..utils.config import logging_settings
from ._abstract import Page
from ..utils.enums import SourceType, ALL_SOURCE_TYPES
from ..utils.enums.album import AlbumType
from ..utils.support_classes.query import Query
from ..objects import (
Lyrics,
Artist,
Source,
Song,
Album,
ID3Timestamp,
FormattedText,
Label,
Options,
DatabaseObject
)
from ..utils.shared import DEBUG
from ..download import Page
from ..objects import (Album, Artist, DatabaseObject, FormattedText,
ID3Timestamp, Label, Lyrics, Options, Song, Source)
from ..utils import dump_to_file
from ..utils.config import logging_settings
from ..utils.enums import ALL_SOURCE_TYPES, SourceType
from ..utils.enums.album import AlbumType
from ..utils.shared import DEBUG
from ..utils.support_classes.query import Query
ALBUM_TYPE_MAP: Dict[str, AlbumType] = defaultdict(lambda: AlbumType.OTHER, {
"Full-length": AlbumType.STUDIO_ALBUM,

View File

@ -1,33 +1,22 @@
from typing import List, Optional, Type
from urllib.parse import urlparse, urlunparse, urlencode
import json
from enum import Enum
from bs4 import BeautifulSoup
import pycountry
from typing import List, Optional, Type
from urllib.parse import urlencode, urlparse, urlunparse
import pycountry
from bs4 import BeautifulSoup
from ..objects import Source, DatabaseObject
from ._abstract import Page
from ..objects import (
Artist,
Source,
SourceType,
Song,
Album,
Label,
Target,
Contact,
ID3Timestamp,
Lyrics,
FormattedText,
Artwork,
)
from ..connection import Connection
from ..download import Page
from ..objects import (Album, Artist, Artwork, Contact, DatabaseObject,
FormattedText, ID3Timestamp, Label, Lyrics, Song,
Source, SourceType, Target)
from ..utils import dump_to_file, traverse_json_path
from ..utils.enums import SourceType, ALL_SOURCE_TYPES
from ..utils.support_classes.download_result import DownloadResult
from ..utils.string_processing import clean_song_title
from ..utils.config import main_settings, logging_settings
from ..utils.config import logging_settings, main_settings
from ..utils.enums import ALL_SOURCE_TYPES, SourceType
from ..utils.shared import DEBUG
from ..utils.string_processing import clean_song_title
from ..utils.support_classes.download_result import DownloadResult
if DEBUG:
from ..utils import dump_to_file

View File

@ -1,34 +1,23 @@
from collections import defaultdict
from dataclasses import dataclass
from enum import Enum
from typing import List, Optional, Type, Union, Generator, Dict, Any
from typing import Any, Dict, Generator, List, Optional, Type, Union
from urllib.parse import urlparse
import pycountry
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 ..download import Page
from ..objects import (Album, Artist, Artwork, DatabaseObject, FormattedText,
ID3Timestamp, Label, Lyrics, Song, Source, Target)
from ..utils import shared, string_processing
from ..utils.config import logging_settings, main_settings
from ..utils import string_processing, shared
from ..utils.enums import ALL_SOURCE_TYPES, SourceType
from ..utils.enums.album import AlbumStatus, AlbumType
from ..utils.string_processing import clean_song_title
from ..utils.support_classes.query import Query
from ..utils.support_classes.download_result import DownloadResult
from ..utils.support_classes.query import Query
"""
https://musify.club/artist/ghost-bath-280348?_pjax=#bodyContent

View File

@ -1,29 +1,19 @@
from typing import List, Optional, Type, Tuple
from urllib.parse import urlparse, urlunparse, parse_qs
from enum import Enum
from typing import List, Optional, Tuple, Type
from urllib.parse import parse_qs, urlparse, urlunparse
import python_sponsorblock
from ..objects import Source, DatabaseObject, Song, Target
from ._abstract import Page
from ..objects import (
Artist,
Source,
Song,
Album,
Label,
Target,
FormattedText,
ID3Timestamp
)
from ..connection import Connection
from ..download import Page
from ..objects import (Album, Artist, DatabaseObject, FormattedText,
ID3Timestamp, Label, Song, Source, Target)
from ..utils.config import logging_settings, main_settings, youtube_settings
from ..utils.enums import ALL_SOURCE_TYPES, SourceType
from ..utils.string_processing import clean_song_title
from ..utils.enums import SourceType, ALL_SOURCE_TYPES
from ..utils.support_classes.download_result import DownloadResult
from ..utils.config import youtube_settings, main_settings, logging_settings
from ._youtube_music.super_youtube import SuperYouTube, YouTubeUrl, get_invidious_url, YouTubeUrlType
from ._youtube_music.super_youtube import (SuperYouTube, YouTubeUrl,
YouTubeUrlType, get_invidious_url)
"""
- https://yt.artemislena.eu/api/v1/search?q=Zombiez+-+Topic&page=1&date=none&type=channel&duration=none&sort=relevance

View File

@ -1,46 +1,33 @@
from __future__ import unicode_literals, annotations
from __future__ import annotations, unicode_literals
from typing import Dict, List, Optional, Set, Type
from urllib.parse import urlparse, urlunparse, quote, parse_qs, urlencode
import json
import logging
import random
import json
from dataclasses import dataclass
import re
from functools import lru_cache
from collections import defaultdict
from dataclasses import dataclass
from functools import lru_cache
from typing import Dict, List, Optional, Set, Type
from urllib.parse import parse_qs, quote, urlencode, urlparse, urlunparse
import youtube_dl
from youtube_dl.extractor.youtube import YoutubeIE
from youtube_dl.utils import DownloadError
from ...connection import Connection
from ...download import Page
from ...objects import Album, Artist, Artwork
from ...objects import DatabaseObject as DataObject
from ...objects import (FormattedText, ID3Timestamp, Label, Lyrics, Song,
Source, Target)
from ...utils import dump_to_file, get_current_millis, traverse_json_path
from ...utils.config import logging_settings, main_settings, youtube_settings
from ...utils.enums import ALL_SOURCE_TYPES, SourceType
from ...utils.enums.album import AlbumType
from ...utils.exception.config import SettingValueError
from ...utils.config import main_settings, youtube_settings, logging_settings
from ...utils.shared import DEBUG, DEBUG_YOUTUBE_INITIALIZING
from ...utils.string_processing import clean_song_title
from ...utils import get_current_millis, traverse_json_path
from ...utils import dump_to_file
from .._abstract import Page
from ...objects import (
DatabaseObject as DataObject,
Source,
FormattedText,
ID3Timestamp,
Artwork,
Artist,
Song,
Album,
Label,
Target,
Lyrics,
)
from ...connection import Connection
from ...utils.enums import SourceType, ALL_SOURCE_TYPES
from ...utils.enums.album import AlbumType
from ...utils.support_classes.download_result import DownloadResult
from ._list_render import parse_renderer
from ._music_object_render import parse_run_element
from .super_youtube import SuperYouTube