feat: implemented the new page mechanics in the downloader

This commit is contained in:
Hazel 2024-05-23 14:32:31 +02:00
parent 8255ad5264
commit 40e9366a0b

View File

@ -30,31 +30,9 @@ from ..utils.exception import MKMissingNameException
from ..utils.exception.download import UrlNotFoundException from ..utils.exception.download import UrlNotFoundException
from ..utils.shared import DEBUG_PAGES from ..utils.shared import DEBUG_PAGES
from ..pages import Page, EncyclopaediaMetallum, Musify, YouTube, YoutubeMusic, Bandcamp, Genius, INDEPENDENT_DB_OBJECTS from ..pages import scan_for_pages, get_pages
ALL_PAGES: Set[Type[Page]] = {
# EncyclopaediaMetallum,
Genius,
Musify,
YoutubeMusic,
Bandcamp
}
if youtube_settings["use_youtube_alongside_youtube_music"]:
ALL_PAGES.add(YouTube)
AUDIO_PAGES: Set[Type[Page]] = {
Musify,
YouTube,
YoutubeMusic,
Bandcamp
}
SHADY_PAGES: Set[Type[Page]] = {
Musify,
}
fetch_map = { fetch_map = {
Song: "fetch_song", Song: "fetch_song",
Album: "fetch_album", Album: "fetch_album",
@ -62,66 +40,28 @@ fetch_map = {
Label: "fetch_label", Label: "fetch_label",
} }
if DEBUG_PAGES:
DEBUGGING_PAGE = Bandcamp
print(f"Only downloading from page {DEBUGGING_PAGE}.")
ALL_PAGES = {DEBUGGING_PAGE}
AUDIO_PAGES = ALL_PAGES.union(AUDIO_PAGES)
class Pages: class Pages:
def __init__(self, exclude_pages: Set[Type[Page]] = None, exclude_shady: bool = False, download_options: DownloadOptions = None, fetch_options: FetchOptions = None): def __init__(self, download_options: DownloadOptions = None, fetch_options: FetchOptions = None, **kwargs):
self.LOGGER = logging.getLogger("download") self.LOGGER = logging.getLogger("download")
self.download_options: DownloadOptions = download_options or DownloadOptions() self.download_options: DownloadOptions = download_options or DownloadOptions()
self.fetch_options: FetchOptions = fetch_options or FetchOptions() self.fetch_options: FetchOptions = fetch_options or FetchOptions()
# initialize all page instances scan_for_pages()
self._page_instances: Dict[Type[Page], Page] = dict()
self._source_to_page: Dict[SourceType, Type[Page]] = dict()
exclude_pages = exclude_pages if exclude_pages is not None else set()
if exclude_shady:
exclude_pages = exclude_pages.union(SHADY_PAGES)
if not exclude_pages.issubset(ALL_PAGES):
raise ValueError(f"The excluded pages have to be a subset of all pages: {exclude_pages} | {ALL_PAGES}")
def _set_to_tuple(page_set: Set[Type[Page]]) -> Tuple[Type[Page], ...]:
return tuple(sorted(page_set, key=lambda page: page.__name__))
self._pages_set: Set[Type[Page]] = ALL_PAGES.difference(exclude_pages)
self.pages: Tuple[Type[Page], ...] = _set_to_tuple(self._pages_set)
self._audio_pages_set: Set[Type[Page]] = self._pages_set.intersection(AUDIO_PAGES)
self.audio_pages: Tuple[Type[Page], ...] = _set_to_tuple(self._audio_pages_set)
for page_type in self.pages:
self._page_instances[page_type] = page_type(fetch_options=self.fetch_options, download_options=self.download_options)
self._source_to_page[page_type.SOURCE_TYPE] = page_type
def _get_page_from_enum(self, source_page: SourceType) -> Page:
if source_page not in self._source_to_page:
return None
return self._page_instances[self._source_to_page[source_page]]
def search(self, query: Query) -> SearchResults: def search(self, query: Query) -> SearchResults:
result = SearchResults() result = SearchResults()
for page_type in self.pages: for page in get_pages():
result.add( result.add(
page=page_type, page=type(page),
search_result=self._page_instances[page_type].search(query=query) search_result=page.search(query=query)
) )
return result return result
def fetch_details(self, data_object: DataObject, stop_at_level: int = 1, **kwargs) -> DataObject: def fetch_details(self, data_object: DataObject, stop_at_level: int = 1, **kwargs) -> DataObject:
if not isinstance(data_object, INDEPENDENT_DB_OBJECTS):
return data_object
source: Source source: Source
for source in data_object.source_collection.get_sources(source_type_sorting={ for source in data_object.source_collection.get_sources(source_type_sorting={
"only_with_page": True, "only_with_page": True,
@ -317,12 +257,10 @@ class Pages:
tmp.delete() tmp.delete()
return r return r
def fetch_url(self, url: str, stop_at_level: int = 2) -> Tuple[Type[Page], DataObject]: def fetch_url(self, url: str, **kwargs) -> DataObject:
source = Source.match_url(url, ALL_SOURCE_TYPES.MANUAL) source = Source.match_url(url, ALL_SOURCE_TYPES.MANUAL)
if source is None: if source is None or source.page is None:
raise UrlNotFoundException(url=url) raise UrlNotFoundException(url=url)
_actual_page = self._source_to_page[source.source_type] return source.page.fetch_object_from_source(source=source, **kwargs)
return _actual_page, self._page_instances[_actual_page].fetch_object_from_source(source=source, stop_at_level=stop_at_level)