feat: detecting url type

This commit is contained in:
Hazel 2024-05-21 15:57:09 +02:00
parent f6caee41a8
commit e4fd9faf12
2 changed files with 8 additions and 61 deletions

View File

@ -6,9 +6,8 @@ logging.getLogger().setLevel(logging.DEBUG)
if __name__ == "__main__":
commands = [
"s: #a I'm in a coffin",
"0",
"d: 0",
"s: #a Crystal F",
"10",
]

View File

@ -49,7 +49,12 @@ class Genius(Page):
def get_source_type(self, source: Source) -> Optional[Type[DatabaseObject]]:
path = source.parsed_url.path.replace("/", "")
return super().get_source_type(source)
if path.startswith("artists"):
return Artist
if path.startswith("albums"):
return Album
return Song
def add_to_artwork(self, artwork: Artwork, url: str):
if url is None:
@ -158,63 +163,6 @@ class Genius(Page):
return results
def fetch_label(self, source: Source, stop_at_level: int = 1) -> Label:
return Label()
def _parse_artist_details(self, soup: BeautifulSoup) -> Artist:
name: str = None
source_list: List[Source] = []
contact_list: List[Contact] = []
band_name_location: BeautifulSoup = soup.find("p", {"id": "band-name-location"})
if band_name_location is not None:
title_span = band_name_location.find("span", {"class": "title"})
if title_span is not None:
name = title_span.text.strip()
link_container: BeautifulSoup = soup.find("ol", {"id": "band-links"})
if link_container is not None:
li: BeautifulSoup
for li in link_container.find_all("a"):
if li is None and li['href'] is not None:
continue
source_list.append(Source.match_url(_parse_artist_url(li['href']), referrer_page=self.SOURCE_TYPE))
return Artist(
name=name,
source_list=source_list
)
def _parse_album(self, soup: BeautifulSoup, initial_source: Source) -> List[Album]:
title = None
source_list: List[Source] = []
a = soup.find("a")
if a is not None and a["href"] is not None:
source_list.append(Source(self.SOURCE_TYPE, _get_host(initial_source) + a["href"]))
title_p = soup.find("p", {"class": "title"})
if title_p is not None:
title = title_p.text.strip()
return Album(title=title, source_list=source_list)
def _parse_artist_data_blob(self, data_blob: dict, artist_url: str):
parsed_artist_url = urlparse(artist_url)
album_list: List[Album] = []
for album_json in data_blob.get("buyfulldisco", {}).get("tralbums", []):
album_list.append(Album(
title=album_json["title"].strip(),
source_list=[Source(
self.SOURCE_TYPE,
urlunparse((parsed_artist_url.scheme, parsed_artist_url.netloc, album_json["page_url"], "", "", ""))
)]
))
return album_list
def fetch_artist(self, source: Source, stop_at_level: int = 1) -> Artist:
artist = Artist()