music-kraken-core/src/music_kraken/pages/encyclopaedia_metallum.py

649 lines
23 KiB
Python
Raw Normal View History

from collections import defaultdict
2023-03-30 10:00:39 +00:00
from typing import List, Optional, Dict, Type, Union
2023-01-24 08:40:01 +00:00
from bs4 import BeautifulSoup
2023-02-01 12:18:09 +00:00
import pycountry
2023-03-30 10:00:39 +00:00
from urllib.parse import urlparse
2023-01-24 08:40:01 +00:00
2023-04-20 17:45:29 +00:00
from ..connection import Connection
2023-09-10 14:27:09 +00:00
from ..utils.config import logging_settings
2023-01-23 23:16:10 +00:00
from .abstract import Page
2023-04-18 10:00:25 +00:00
from ..utils.enums.source import SourcePages
2023-04-18 10:14:34 +00:00
from ..utils.enums.album import AlbumType
2023-05-23 11:59:24 +00:00
from ..utils.support_classes import Query
2023-03-02 15:23:02 +00:00
from ..objects import (
2023-03-28 06:57:50 +00:00
Lyrics,
2023-01-24 08:40:01 +00:00
Artist,
Source,
2023-01-24 11:09:47 +00:00
Song,
Album,
2023-02-06 08:16:28 +00:00
ID3Timestamp,
2023-03-02 15:23:02 +00:00
FormattedText,
2023-03-13 13:39:46 +00:00
Label,
Options,
2023-05-23 14:53:07 +00:00
DatabaseObject
)
2023-01-23 23:16:10 +00:00
2023-05-23 14:21:12 +00:00
ALBUM_TYPE_MAP: Dict[str, AlbumType] = defaultdict(lambda: AlbumType.OTHER, {
"Full-length": AlbumType.STUDIO_ALBUM,
"Single": AlbumType.SINGLE,
"EP": AlbumType.EP,
"Demo": AlbumType.DEMO,
"Video": AlbumType.OTHER,
"Live album": AlbumType.LIVE_ALBUM,
"Compilation": AlbumType.COMPILATION_ALBUM
})
2023-05-23 15:53:03 +00:00
def _song_from_json(artist_html=None, album_html=None, release_type=None, title=None, lyrics_html=None) -> Song:
2023-05-23 14:50:54 +00:00
song_id = None
if lyrics_html is not None:
soup = BeautifulSoup(lyrics_html, 'html.parser')
anchor = soup.find('a')
raw_song_id = anchor.get('id')
song_id = raw_song_id.replace("lyricsLink_", "")
return Song(
title=title,
main_artist_list=[
_artist_from_json(artist_html=artist_html)
],
album_list=[
_album_from_json(album_html=album_html, release_type=release_type, artist_html=artist_html)
],
source_list=[
Source(SourcePages.ENCYCLOPAEDIA_METALLUM, song_id)
]
)
def _artist_from_json(artist_html=None, genre=None, country=None) -> Artist:
"""
2023-05-23 15:53:03 +00:00
TODO parse the country to a standard
2023-05-23 14:50:54 +00:00
"""
# parse the html
# parse the html for the band name and link on metal-archives
soup = BeautifulSoup(artist_html, 'html.parser')
anchor = soup.find('a')
artist_name = anchor.text
artist_url = anchor.get('href')
artist_id = artist_url.split("/")[-1]
anchor.decompose()
strong = soup.find('strong')
if strong is not None:
strong.decompose()
akronyms_ = soup.text[2:-2].split(', ')
return Artist(
name=artist_name,
source_list=[
Source(SourcePages.ENCYCLOPAEDIA_METALLUM, artist_url)
]
)
def _album_from_json(album_html=None, release_type=None, artist_html=None) -> Album:
# parse the html
# <a href="https://www.metal-archives.com/albums/Ghost_Bath/Self_Loather/970834">Self Loather</a>'
soup = BeautifulSoup(album_html, 'html.parser')
anchor = soup.find('a')
album_name = anchor.text
album_url = anchor.get('href')
album_id = album_url.split("/")[-1]
album_type = ALBUM_TYPE_MAP[release_type.strip()]
return Album(
title=album_name,
album_type=album_type,
source_list=[
Source(SourcePages.ENCYCLOPAEDIA_METALLUM, album_url)
],
artist_list=[
_artist_from_json(artist_html=artist_html)
]
2023-04-20 17:45:29 +00:00
)
2023-01-24 08:40:01 +00:00
2023-05-23 14:50:54 +00:00
class EncyclopaediaMetallum(Page):
2023-01-24 17:15:07 +00:00
SOURCE_TYPE = SourcePages.ENCYCLOPAEDIA_METALLUM
2023-09-10 14:27:09 +00:00
LOGGER = logging_settings["metal_archives_logger"]
2023-05-23 14:21:12 +00:00
2023-05-25 11:46:47 +00:00
def __init__(self, **kwargs):
2023-05-23 14:21:12 +00:00
self.connection: Connection = Connection(
host="https://www.metal-archives.com/",
2023-09-10 14:27:09 +00:00
logger=self.LOGGER
2023-05-23 14:21:12 +00:00
)
2023-05-23 14:30:35 +00:00
2023-05-25 11:46:47 +00:00
super().__init__(**kwargs)
2023-01-24 09:51:41 +00:00
2023-05-23 14:30:35 +00:00
def song_search(self, song: Song) -> List[Song]:
2023-01-30 22:54:21 +00:00
endpoint = "https://www.metal-archives.com/search/ajax-advanced/searching/songs/?songTitle={song}&bandName={" \
"artist}&releaseTitle={album}&lyrics=&genre=&sEcho=1&iColumns=5&sColumns=&iDisplayStart=0" \
"&iDisplayLength=200&mDataProp_0=0&mDataProp_1=1&mDataProp_2=2&mDataProp_3=3&mDataProp_4=4&_" \
"=1674550595663"
2023-05-23 14:30:35 +00:00
"""
The difficult question I am facing is, that if I try every artist, with every song, with every album,
I end up with a quadratic runtime complecety O(n^2), where every step means one web request.
This.
Is not good.
"""
2023-05-23 14:50:54 +00:00
song_title = song.title
album_titles = ["*"] if song.album_collection.empty else [album.title for album in song.album_collection]
artist_titles = ["*"] if song.main_artist_collection.empty else [artist.name for artist in song.main_artist_collection]
2023-01-24 09:51:41 +00:00
2023-05-23 14:50:54 +00:00
search_results = []
2023-01-24 09:51:41 +00:00
2023-05-23 14:50:54 +00:00
for artist in artist_titles:
for album in album_titles:
r = self.connection.get(
endpoint.format(song=song_title, artist=artist, album=album)
)
if r is None:
return []
search_results.extend(_song_from_json(
artist_html=raw_song[0],
album_html=raw_song[1],
release_type=raw_song[2],
title=raw_song[3],
lyrics_html=raw_song[4]
) for raw_song in r.json()['aaData'])
return search_results
def album_search(self, album: Album) -> List[Album]:
2023-01-30 22:54:21 +00:00
endpoint = "https://www.metal-archives.com/search/ajax-advanced/searching/albums/?bandName={" \
"artist}&releaseTitle={album}&releaseYearFrom=&releaseMonthFrom=&releaseYearTo=&releaseMonthTo" \
"=&country=&location=&releaseLabelName=&releaseCatalogNumber=&releaseIdentifiers" \
"=&releaseRecordingInfo=&releaseDescription=&releaseNotes=&genre=&sEcho=1&iColumns=3&sColumns" \
"=&iDisplayStart=0&iDisplayLength=200&mDataProp_0=0&mDataProp_1=1&mDataProp_2=2&_=1674563943747"
2023-01-24 13:29:23 +00:00
2023-05-23 14:50:54 +00:00
album_title = album.title
artist_titles = ["*"] if album.artist_collection.empty else [artist.name for artist in album.artist_collection]
2023-01-24 13:29:23 +00:00
2023-05-23 14:50:54 +00:00
search_results = []
for artist in artist_titles:
r = self.connection.get(endpoint.format(artist=artist, album=album_title))
if r is None:
return []
search_results.extend(_album_from_json(
artist_html=raw_album[0],
album_html=raw_album[1],
release_type=raw_album[2]
) for raw_album in r.json()['aaData'])
def artist_search(self, artist: Artist) -> List[Artist]:
2023-03-27 15:48:06 +00:00
endpoint = "https://www.metal-archives.com/search/ajax-advanced/searching/bands/?bandName={" \
"artist}&genre=&country=&yearCreationFrom=&yearCreationTo=&bandNotes=&status=&themes=&location" \
"=&bandLabelName=&sEcho=1&iColumns=3&sColumns=&iDisplayStart=0&iDisplayLength=200&mDataProp_0=0" \
"&mDataProp_1=1&mDataProp_2=2&_=1674565459976"
2023-05-23 14:50:54 +00:00
r = self.connection.get(endpoint.format(artist=artist.name))
2023-04-05 07:20:25 +00:00
if r is None:
return []
2023-03-27 15:48:06 +00:00
data_key = 'aaData'
parsed_data = r.json()
if data_key not in parsed_data:
2023-01-24 13:29:23 +00:00
return []
return [
2023-05-23 14:50:54 +00:00
_artist_from_json(artist_html=raw_artist[0], genre=raw_artist[1], country=raw_artist[2])
2023-01-24 13:29:23 +00:00
for raw_artist in r.json()['aaData']
]
2023-05-23 14:53:07 +00:00
def general_search(self, query: str) -> List[DatabaseObject]:
2023-01-24 08:40:01 +00:00
"""
Searches the default endpoint from metal archives, which intern searches only
for bands, but it is the default, thus I am rolling with it
"""
endpoint = "https://www.metal-archives.com/search/ajax-band-search/?field=name&query={query}&sEcho=1&iColumns=3&sColumns=&iDisplayStart=0&iDisplayLength=200&mDataProp_0=0&mDataProp_1=1&mDataProp_2=2"
2023-05-23 14:53:07 +00:00
r = self.connection.get(endpoint.format(query=query))
2023-04-05 07:20:25 +00:00
if r is None:
2023-05-23 14:53:07 +00:00
return []
2023-01-24 08:40:01 +00:00
2023-05-23 14:53:07 +00:00
return [
_artist_from_json(artist_html=raw_artist[0], genre=raw_artist[1], country=raw_artist[2])
2023-01-24 09:51:41 +00:00
for raw_artist in r.json()['aaData']
2023-05-23 14:53:07 +00:00
]
2023-01-24 08:40:01 +00:00
2023-05-24 06:50:56 +00:00
def _fetch_artist_discography(self, ma_artist_id: str) -> List[Album]:
discography_url = "https://www.metal-archives.com/band/discography/id/{}/tab/all"
# make the request
2023-05-24 06:50:56 +00:00
r = self.connection.get(discography_url.format(ma_artist_id))
if r is None:
return []
2023-05-24 06:50:56 +00:00
soup = self.get_soup_from_response(r)
discography = []
tbody_soup = soup.find('tbody')
for tr_soup in tbody_soup.find_all('tr'):
td_list = tr_soup.findChildren(recursive=False)
album_soup = td_list[0]
album_name = album_soup.text
album_url = album_soup.find('a').get('href')
album_id = album_url.split('/')[-1]
raw_album_type = td_list[1].text
album_year = td_list[2].text
2023-02-08 16:14:51 +00:00
date_obj = None
try:
2023-02-08 16:14:51 +00:00
date_obj = ID3Timestamp(year=int(album_year))
except ValueError():
pass
discography.append(
2023-03-10 17:38:32 +00:00
Album(
title=album_name,
date=date_obj,
2023-05-24 06:50:56 +00:00
album_type=ALBUM_TYPE_MAP[raw_album_type],
source_list=[Source(self.SOURCE_TYPE, album_url)]
2023-03-10 17:38:32 +00:00
)
)
return discography
2023-05-24 06:50:56 +00:00
def _fetch_artist_sources(self, ma_artist_id: str) -> List[Source]:
sources_url = "https://www.metal-archives.com/link/ajax-list/type/band/id/{}"
2023-05-24 06:50:56 +00:00
r = self.connection.get(sources_url.format(ma_artist_id))
if r is None:
return []
2023-05-24 06:50:56 +00:00
soup = self.get_soup_from_response(r)
if soup.find("span", {"id": "noLinks"}) is not None:
return []
2023-02-09 14:05:49 +00:00
artist_source = soup.find("div", {"id": "band_links_Official"})
"""
TODO
add a Label object to add the label sources from
TODO
maybe do merchandice stuff
"""
merchandice_source = soup.find("div", {"id": "band_links_Official_merchandise"})
label_source = soup.find("div", {"id": "band_links_Labels"})
source_list = []
2023-03-02 15:23:02 +00:00
if artist_source is not None:
for tr in artist_source.find_all("td"):
a = tr.find("a")
url = a.get("href")
if url is None:
2023-03-02 15:23:02 +00:00
continue
2023-05-24 06:50:56 +00:00
source_list.append(Source.match_url(url, referer_page=self.SOURCE_TYPE))
return source_list
2023-05-24 06:50:56 +00:00
def _parse_artist_attributes(self, artist_soup: BeautifulSoup) -> Artist:
2023-03-27 18:02:17 +00:00
name: str = None
2023-02-01 12:18:09 +00:00
country: pycountry.Countrie = None
formed_in_year: int = None
genre: str = None
lyrical_themes: List[str] = []
label_name: str = None
label_url: str = None
2023-03-27 18:02:17 +00:00
source_list: List[Source] = []
title_soup: BeautifulSoup = artist_soup.find("title")
if title_soup is not None:
bad_name_substring = " - Encyclopaedia Metallum: The Metal Archives"
title_text = title_soup.get_text()
if title_text.count(bad_name_substring) == 1:
name = title_text.replace(bad_name_substring, "")
else:
2023-05-24 06:50:56 +00:00
self.LOGGER.debug(f"the title of the page is \"{title_text}\"")
2023-03-27 18:02:17 +00:00
"""
TODO
Implement the bandpictures and logos that can be gotten with the elements
<a class="image" id="photo" title="Ghost Bath"...
<a class="image" id="logo" title="Ghost Bath"...
where the titles are the band name
"""
image_container_soup: BeautifulSoup = artist_soup.find(id="band_sidebar")
if image_container_soup is not None:
logo_soup = image_container_soup.find(id="logo")
if logo_soup is not None:
logo_title = logo_soup.get("title")
if logo_title is not None:
name = logo_title.strip()
band_pictures = image_container_soup.find(id="photo")
if band_pictures is not None:
band_picture_title = logo_soup.get("title")
if band_picture_title is not None:
name = band_picture_title.strip()
for h1_band_name_soup in artist_soup.find_all("h1", {"class": "band_name"}):
anchor: BeautifulSoup = h1_band_name_soup.find("a")
if anchor is None:
continue
href = anchor.get("href")
if href is not None:
2023-05-24 06:50:56 +00:00
source_list.append(Source(self.SOURCE_TYPE, href))
2023-03-27 18:02:17 +00:00
name = anchor.get_text(strip=True)
2023-03-27 16:41:50 +00:00
band_stat_soup = artist_soup.find("div", {"id": "band_stats"})
2023-02-01 12:18:09 +00:00
for dl_soup in band_stat_soup.find_all("dl"):
for title, data in zip(dl_soup.find_all("dt"), dl_soup.find_all("dd")):
title_text = title.text
if "Country of origin:" == title_text:
href = data.find('a').get('href')
country = pycountry.countries.get(alpha_2=href.split("/")[-1])
continue
2023-02-01 12:18:09 +00:00
# not needed: Location: Minot, North Dakota
"""
TODO
status: active
need to do enums for that and add it to object
"""
if "Formed in:" == title_text:
2023-02-09 14:05:49 +00:00
if not data.text.isnumeric():
continue
2023-02-01 12:18:09 +00:00
formed_in_year = int(data.text)
continue
if "Genre:" == title_text:
genre = data.text
continue
if "Lyrical themes:" == title_text:
lyrical_themes = data.text.split(", ")
continue
if "Current label:" == title_text:
label_name = data.text
2023-02-09 14:05:49 +00:00
label_anchor = data.find("a")
label_url = None
if label_anchor is not None:
label_url = label_anchor.get("href")
2023-03-10 17:38:32 +00:00
label_id = None
if type(label_url) is str and "/" in label_url:
label_id = label_url.split("/")[-1]
2023-02-01 12:18:09 +00:00
"""
2023-03-27 16:41:50 +00:00
TODO
2023-02-01 12:18:09 +00:00
years active: 2012-present
process this and add field to class
"""
2023-03-27 16:41:50 +00:00
return Artist(
2023-03-27 18:02:17 +00:00
name=name,
2023-03-27 16:41:50 +00:00
country=country,
formed_in=ID3Timestamp(year=formed_in_year),
general_genre=genre,
lyrical_themes=lyrical_themes,
label_list=[
Label(
name=label_name,
source_list=[
2023-05-24 06:50:56 +00:00
Source(self.SOURCE_TYPE, label_url)
2023-03-27 16:41:50 +00:00
]
)
2023-03-27 18:02:17 +00:00
],
source_list=source_list
2023-03-27 16:41:50 +00:00
)
2023-05-24 06:50:56 +00:00
def _fetch_artist_attributes(self, url: str) -> Artist:
r = self.connection.get(url)
2023-03-27 16:41:50 +00:00
if r is None:
return Artist()
2023-05-24 06:50:56 +00:00
soup: BeautifulSoup = self.get_soup_from_response(r)
2023-03-27 16:41:50 +00:00
2023-05-24 06:50:56 +00:00
return self._parse_artist_attributes(artist_soup=soup)
2023-02-01 08:18:06 +00:00
2023-05-24 06:50:56 +00:00
def _fetch_band_notes(self, ma_artist_id: str) -> Optional[FormattedText]:
2023-02-06 08:16:28 +00:00
endpoint = "https://www.metal-archives.com/band/read-more/id/{}"
# make the request
2023-05-24 06:50:56 +00:00
r = self.connection.get(endpoint.format(ma_artist_id))
if r is None:
return FormattedText()
2023-02-06 08:16:28 +00:00
return FormattedText(html=r.text)
2023-02-06 08:16:28 +00:00
2023-05-24 06:50:56 +00:00
def fetch_artist(self, source: Source, stop_at_level: int = 1) -> Artist:
2023-03-27 16:41:50 +00:00
"""
What it could fetch, and what is implemented:
[x] https://www.metal-archives.com/bands/Ghost_Bath/3540372489
[x] https://www.metal-archives.com/band/discography/id/3540372489/tab/all
[] reviews: https://www.metal-archives.com/review/ajax-list-band/id/3540372489/json/1?sEcho=1&iColumns=4&sColumns=&iDisplayStart=0&iDisplayLength=200&mDataProp_0=0&mDataProp_1=1&mDataProp_2=2&mDataProp_3=3&iSortCol_0=3&sSortDir_0=desc&iSortingCols=1&bSortable_0=true&bSortable_1=true&bSortable_2=true&bSortable_3=true&_=1675155257133
[] simmilar: https://www.metal-archives.com/band/ajax-recommendations/id/3540372489
[x] sources: https://www.metal-archives.com/link/ajax-list/type/band/id/3540372489
[x] band notes: https://www.metal-archives.com/band/read-more/id/3540372489
"""
2023-05-24 06:50:56 +00:00
artist = self._fetch_artist_attributes(source.url)
2023-03-27 16:41:50 +00:00
artist_id = source.url.split("/")[-1]
2023-05-24 06:50:56 +00:00
artist_sources = self._fetch_artist_sources(artist_id)
artist.source_collection.extend(artist_sources)
2023-05-24 06:50:56 +00:00
band_notes = self._fetch_band_notes(artist_id)
if band_notes is not None:
artist.notes = band_notes
2023-05-24 06:50:56 +00:00
discography: List[Album] = self._fetch_artist_discography(artist_id)
if stop_at_level > 1:
for album in discography:
2023-05-24 06:50:56 +00:00
for source in album.source_collection.get_sources_from_page(self.SOURCE_TYPE):
album.merge(self._fetch_album_from_source(source, stop_at_level=stop_at_level-1))
artist.main_album_collection.extend(discography)
2023-02-06 08:16:28 +00:00
return artist
2023-02-06 14:06:38 +00:00
2023-05-24 06:50:56 +00:00
def _parse_album_track_row(self, track_row: BeautifulSoup) -> Song:
"""
<tr class="even">
<td width="20"><a class="anchor" name="5948442"> </a>1.</td> # id and tracksort
<td class="wrapWords">Convince Me to Bleed</td> # name
<td align="right">03:40</td> # length
<td nowrap="nowrap"> 
<a href="#5948442" id="lyricsButton5948442" onclick="toggleLyrics('5948442'); return false;">Show lyrics</a>
</td>
</tr>
"""
row_list = track_row.find_all(recursive=False)
2023-03-28 06:57:50 +00:00
source_list: List[Source] = []
track_sort_soup = row_list[0]
track_sort = int(track_sort_soup.text[:-1])
2023-03-28 06:57:50 +00:00
track_id = track_sort_soup.find("a").get("name").strip()
if track_row.find("a", {"href": f"#{track_id}"}) is not None:
2023-05-24 06:50:56 +00:00
source_list.append(Source(self.SOURCE_TYPE, track_id))
title = row_list[1].text.strip()
length = None
duration_stamp = row_list[2].text
if ":" in duration_stamp:
minutes, seconds = duration_stamp.split(":")
length = (int(minutes) * 60 + int(seconds)) * 1000 # in milliseconds
return Song(
title=title,
length=length,
tracksort=track_sort,
2023-03-28 06:57:50 +00:00
source_list=source_list
)
2023-05-24 06:50:56 +00:00
def _parse_album_attributes(self, album_soup: BeautifulSoup, stop_at_level: int = 1) -> Album:
tracklist: List[Song] = []
artist_list = []
album_name: str = None
source_list: List[Source] = []
def _parse_album_info(album_info_soup: BeautifulSoup):
nonlocal artist_list
nonlocal album_name
nonlocal source_list
if album_info_soup is None:
return
album_soup_list = album_info_soup.find_all("h1", {"class": "album_name"})
if len(album_soup_list) == 1:
anchor: BeautifulSoup = album_soup_list[0].find("a")
href = anchor.get("href")
if href is not None:
2023-05-24 06:50:56 +00:00
source_list.append(Source(self.SOURCE_TYPE, href.strip()))
album_name = anchor.get_text(strip=True)
elif len(album_soup_list) > 1:
2023-05-24 06:50:56 +00:00
self.LOGGER.debug("there are more than 1 album soups")
artist_soup_list = album_info_soup.find_all("h2", {"class": "band_name"})
if len(artist_soup_list) == 1:
for anchor in artist_soup_list[0].find_all("a"):
artist_sources: List[Source] = []
href = anchor.get("href")
if href is not None:
2023-05-24 06:50:56 +00:00
artist_sources.append(Source(self.SOURCE_TYPE, href.strip()))
artist_name = anchor.get_text(strip=True)
artist_list.append(Artist(
name=artist_name,
source_list=artist_sources
))
elif len(artist_soup_list) > 1:
2023-05-24 06:50:56 +00:00
self.LOGGER.debug("there are more than 1 artist soups")
_parse_album_info(album_info_soup=album_soup.find(id="album_info"))
tracklist_soup = album_soup.find("table", {"class": "table_lyrics"}).find("tbody")
for track_soup in tracklist_soup.find_all("tr", {"class": ["even", "odd"]}):
2023-05-24 06:50:56 +00:00
tracklist.append(self._parse_album_track_row(track_row=track_soup))
return Album(
title=album_name,
source_list=source_list,
artist_list=artist_list,
song_list=tracklist
)
2023-05-24 06:50:56 +00:00
def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
"""
I am preeeety sure I can get way more data than... nothing from there
:param source:
:param stop_at_level:
:return:
"""
2023-02-06 14:06:38 +00:00
# <table class="display table_lyrics
2023-05-24 06:50:56 +00:00
r = self.connection.get(source.url)
if r is None:
return Album()
2023-02-06 14:06:38 +00:00
2023-05-24 06:50:56 +00:00
soup = self.get_soup_from_response(r)
2023-05-24 06:50:56 +00:00
album = self._parse_album_attributes(soup, stop_at_level=stop_at_level)
if stop_at_level > 1:
for song in album.song_collection:
2023-05-24 06:50:56 +00:00
for source in song.source_collection.get_sources_from_page(self.SOURCE_TYPE):
song.merge(self._fetch_song_from_source(source=source, stop_at_level=stop_at_level-1))
2023-02-06 14:06:38 +00:00
return album
2023-03-28 06:57:50 +00:00
2023-05-24 06:50:56 +00:00
def _fetch_lyrics(self, song_id: str) -> Optional[Lyrics]:
2023-03-28 06:57:50 +00:00
"""
function toggleLyrics(songId) {
var lyricsRow = $('#song' + songId);
lyricsRow.toggle();
var lyrics = $('#lyrics_' + songId);
if (lyrics.html() == '(loading lyrics...)') {
var realId = songId;
if(!$.isNumeric(songId.substring(songId.length -1, songId.length))) {
realId = songId.substring(0, songId.length -1);
}
lyrics.load(URL_SITE + "release/ajax-view-lyrics/id/" + realId);
}
// toggle link
var linkLabel = "lyrics";
$("#lyricsButton" + songId).text(lyricsRow.css("display") == "none" ? "Show " + linkLabel : "Hide " + linkLabel);
return false;
}
"""
if song_id is None:
return None
endpoint = "https://www.metal-archives.com/release/ajax-view-lyrics/id/{id}".format(id=song_id)
2023-05-24 06:50:56 +00:00
r = self.connection.get(endpoint)
2023-03-28 06:57:50 +00:00
if r is None:
return None
return Lyrics(
text=FormattedText(html=r.text),
language=pycountry.languages.get(alpha_2="en"),
source_list=[
2023-05-24 06:50:56 +00:00
Source(self.SOURCE_TYPE, endpoint)
2023-03-28 06:57:50 +00:00
]
)
2023-05-24 06:50:56 +00:00
def fetch_song(self, source: Source, stop_at_level: int = 1) -> Song:
2023-03-28 06:57:50 +00:00
song_id = source.url
return Song(
lyrics_list=[
2023-05-24 06:50:56 +00:00
self._fetch_lyrics(song_id=song_id)
2023-03-28 06:57:50 +00:00
]
)
2023-03-30 10:00:39 +00:00
2023-05-24 06:50:56 +00:00
def get_source_type(self, source: Source):
if self.SOURCE_TYPE != source.page_enum:
return None
url = source.url
if url is None:
return None
2023-03-30 10:00:39 +00:00
parsed_url = urlparse(url)
path: List[str] = parsed_url.path.split("/")
if "band" in path:
return Artist
if "bands" in path:
return Artist
if "albums" in path:
return Album
if "labels" in path:
return Label
return None