2023-03-15 19:55:28 +00:00
|
|
|
from typing import List, Optional, Union
|
2023-03-13 14:47:38 +00:00
|
|
|
import requests
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
import pycountry
|
2023-03-14 13:48:03 +00:00
|
|
|
import time
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
from ..utils.shared import (
|
|
|
|
ENCYCLOPAEDIA_METALLUM_LOGGER as LOGGER
|
|
|
|
)
|
|
|
|
|
|
|
|
from .abstract import Page
|
|
|
|
from ..objects import (
|
|
|
|
MusicObject,
|
|
|
|
Artist,
|
|
|
|
Source,
|
|
|
|
SourcePages,
|
|
|
|
Song,
|
|
|
|
Album,
|
|
|
|
ID3Timestamp,
|
|
|
|
FormattedText,
|
|
|
|
Label,
|
|
|
|
Options
|
|
|
|
)
|
|
|
|
from ..utils import (
|
|
|
|
string_processing,
|
|
|
|
shared
|
|
|
|
)
|
2023-03-14 13:48:03 +00:00
|
|
|
from ..utils.shared import (
|
|
|
|
MUSIFY_LOGGER as LOGGER
|
|
|
|
)
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
|
2023-03-15 19:55:28 +00:00
|
|
|
class Musify(Page):
|
2023-03-13 14:47:38 +00:00
|
|
|
API_SESSION: requests.Session = requests.Session()
|
|
|
|
API_SESSION.headers = {
|
|
|
|
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:106.0) Gecko/20100101 Firefox/106.0",
|
|
|
|
"Connection": "keep-alive",
|
|
|
|
"Referer": "https://musify.club/"
|
|
|
|
}
|
|
|
|
API_SESSION.proxies = shared.proxies
|
|
|
|
|
|
|
|
SOURCE_TYPE = SourcePages.MUSIFY
|
2023-03-15 19:55:28 +00:00
|
|
|
|
|
|
|
HOST = "https://musify.club"
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def search_by_query(cls, query: str) -> Options:
|
|
|
|
query_obj = cls.Query(query)
|
|
|
|
|
|
|
|
if query_obj.is_raw:
|
2023-03-14 13:48:03 +00:00
|
|
|
return cls.plaintext_search(query_obj.query)
|
|
|
|
return cls.plaintext_search(cls.get_plaintext_query(query_obj))
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
@classmethod
|
2023-03-14 13:48:03 +00:00
|
|
|
def get_plaintext_query(cls, query: Page.Query) -> str:
|
|
|
|
if query.album is None:
|
|
|
|
return f"{query.artist or '*'} - {query.song or '*'}"
|
2023-03-16 13:36:49 +00:00
|
|
|
return f"{query.artist or '*'} - {query.album or '*'} - {query.song or '*'}"
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
@classmethod
|
2023-03-14 13:48:03 +00:00
|
|
|
def get_soup_of_search(cls, query: str, trie=0) -> Optional[BeautifulSoup]:
|
|
|
|
url = f"https://musify.club/search?searchText={query}"
|
|
|
|
LOGGER.debug(f"Trying to get soup from {url}")
|
|
|
|
try:
|
|
|
|
r = cls.API_SESSION.get(url, timeout=15)
|
|
|
|
except requests.exceptions.Timeout:
|
|
|
|
return None
|
|
|
|
if r.status_code != 200:
|
|
|
|
if r.status_code in [503] and trie < cls.TRIES:
|
|
|
|
LOGGER.warning(f"youtube blocked downloading. ({trie}-{cls.TRIES})")
|
|
|
|
LOGGER.warning(f"retrying in {cls.TIMEOUT} seconds again")
|
|
|
|
time.sleep(cls.TIMEOUT)
|
|
|
|
return cls.get_soup_of_search(query, trie=trie + 1)
|
|
|
|
|
|
|
|
LOGGER.warning("too many tries, returning")
|
|
|
|
return None
|
|
|
|
return BeautifulSoup(r.content, features="html.parser")
|
2023-03-14 13:58:54 +00:00
|
|
|
|
|
|
|
@classmethod
|
2023-03-15 19:55:28 +00:00
|
|
|
def parse_artist_contact(cls, contact: BeautifulSoup) -> Artist:
|
|
|
|
source_list: List[Source] = []
|
|
|
|
name = ""
|
|
|
|
_id = None
|
|
|
|
|
|
|
|
# source
|
|
|
|
anchor = contact.find("a")
|
|
|
|
if anchor is not None:
|
|
|
|
href = anchor.get("href")
|
|
|
|
name = anchor.get("title")
|
|
|
|
|
|
|
|
if "-" in href:
|
|
|
|
_id = href.split("-")[-1]
|
|
|
|
|
|
|
|
source_list.append(Source(cls.SOURCE_TYPE, cls.HOST + href))
|
|
|
|
|
|
|
|
# artist image
|
|
|
|
image_soup = contact.find("img")
|
|
|
|
if image_soup is not None:
|
|
|
|
alt = image_soup.get("alt")
|
|
|
|
if alt is not None:
|
|
|
|
name = alt
|
|
|
|
|
|
|
|
artist_thumbnail = image_soup.get("src")
|
|
|
|
|
|
|
|
return Artist(
|
|
|
|
_id=_id,
|
|
|
|
name=name,
|
|
|
|
source_list=source_list
|
|
|
|
)
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def parse_album_contact(cls, contact: BeautifulSoup) -> Album:
|
2023-03-16 13:36:49 +00:00
|
|
|
"""
|
|
|
|
parsing following html:
|
|
|
|
|
|
|
|
```html
|
|
|
|
<div class="contacts__item">
|
|
|
|
<a href="/release/ghost-bath-ghost-bath-2013-602489" title="Ghost Bath - 2013">
|
|
|
|
|
|
|
|
<div class="contacts__img release">
|
|
|
|
<img alt="Ghost Bath" class="lozad" data-src="https://37s.musify.club/img/69/9060265/24178833.jpg"/>
|
|
|
|
<noscript><img alt="Ghost Bath" src="https://37s.musify.club/img/69/9060265/24178833.jpg"/></noscript>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<div class="contacts__info">
|
|
|
|
<strong>Ghost Bath - 2013</strong>
|
|
|
|
<small>Ghost Bath</small>
|
|
|
|
<small>Треков: 4</small> <!--tracks-->
|
|
|
|
<small><i class="zmdi zmdi-star zmdi-hc-fw"></i> 9,04</small>
|
|
|
|
</div>
|
|
|
|
</a>
|
|
|
|
</div>
|
|
|
|
```
|
|
|
|
"""
|
|
|
|
|
|
|
|
source_list: List[Source] = []
|
|
|
|
title = ""
|
|
|
|
_id = None
|
|
|
|
year = None
|
|
|
|
artist_list: List[Artist] = []
|
|
|
|
|
|
|
|
def parse_title_date(title_date: Optional[str], delimiter: str = " - "):
|
|
|
|
if title_date is None:
|
|
|
|
return
|
|
|
|
|
|
|
|
title_date = title_date.strip()
|
|
|
|
split_attr = title_date.split(delimiter)
|
|
|
|
|
|
|
|
if len(split_attr) < 2:
|
|
|
|
return
|
|
|
|
if not split_attr[-1].isdigit():
|
|
|
|
return
|
|
|
|
|
|
|
|
year = int(split_attr[-1])
|
|
|
|
title = delimiter.join(split_attr[:-1])
|
|
|
|
|
|
|
|
# source
|
|
|
|
anchor = contact.find("a")
|
|
|
|
if anchor is not None:
|
|
|
|
href = anchor.get("href")
|
|
|
|
|
|
|
|
# get the title and year
|
|
|
|
parse_title_date(anchor.get("title"))
|
|
|
|
|
|
|
|
|
|
|
|
if "-" in href:
|
|
|
|
_id = href.split("-")[-1]
|
|
|
|
|
|
|
|
source_list.append(Source(cls.SOURCE_TYPE, cls.HOST + href))
|
|
|
|
|
|
|
|
# cover art
|
|
|
|
image_soup = contact.find("img")
|
|
|
|
if image_soup is not None:
|
|
|
|
alt = image_soup.get("alt")
|
|
|
|
if alt is not None:
|
|
|
|
title = alt
|
|
|
|
|
|
|
|
cover_art = image_soup.get("src")
|
|
|
|
|
|
|
|
contact_info_soup = contact.find("div", {"class": "contacts__info"})
|
|
|
|
if contact_info_soup is not None:
|
|
|
|
"""
|
|
|
|
<strong>Ghost Bath - 2013</strong>
|
|
|
|
<small>Ghost Bath</small>
|
|
|
|
<small>Треков: 4</small> <!--tracks-->
|
|
|
|
<small><i class="zmdi zmdi-star zmdi-hc-fw"></i> 9,04</small>
|
|
|
|
"""
|
|
|
|
|
|
|
|
title_soup = contact_info_soup.find("strong")
|
|
|
|
if title_soup is None:
|
|
|
|
parse_title_date(title_soup)
|
|
|
|
|
|
|
|
small_list = contact_info_soup.find_all("small")
|
|
|
|
if len(small_list) == 3:
|
|
|
|
# artist
|
|
|
|
artist_soup: BeautifulSoup = small_list[0]
|
|
|
|
raw_artist_str = artist_soup.text
|
|
|
|
|
|
|
|
for artist_str in raw_artist_str.split("&\r\n"):
|
|
|
|
artist_str = artist_str.rstrip("& ...\r\n")
|
|
|
|
artist_str = artist_str.strip()
|
|
|
|
|
|
|
|
artist_list.append(Artist(name=artist_str))
|
|
|
|
|
|
|
|
track_count_soup: BeautifulSoup = small_list[1]
|
|
|
|
rating_soup: BeautifulSoup = small_list[2]
|
|
|
|
else:
|
|
|
|
LOGGER.warning("got an unequal ammount than 3 small elements")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
return Album(
|
|
|
|
_id=_id,
|
|
|
|
title=title,
|
|
|
|
source_list=source_list,
|
|
|
|
date=ID3Timestamp(year=year),
|
|
|
|
artist_list=artist_list
|
|
|
|
)
|
2023-03-15 19:55:28 +00:00
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def parse_contact_container(cls, contact_container_soup: BeautifulSoup) -> List[Union[Artist, Album]]:
|
2023-03-16 13:36:49 +00:00
|
|
|
#print(contact_container_soup.prettify)
|
2023-03-15 19:55:28 +00:00
|
|
|
contacts = []
|
|
|
|
|
|
|
|
# print(contact_container_soup)
|
|
|
|
|
|
|
|
contact: BeautifulSoup
|
|
|
|
for contact in contact_container_soup.find_all("div", {"class": "contacts__item"}):
|
|
|
|
|
|
|
|
anchor_soup = contact.find("a")
|
2023-03-16 13:36:49 +00:00
|
|
|
|
2023-03-15 19:55:28 +00:00
|
|
|
if anchor_soup is not None:
|
|
|
|
url = anchor_soup.get("href")
|
2023-03-16 13:36:49 +00:00
|
|
|
|
2023-03-15 19:55:28 +00:00
|
|
|
if url is not None:
|
2023-03-16 13:36:49 +00:00
|
|
|
#print(url)
|
2023-03-15 19:55:28 +00:00
|
|
|
if "artist" in url:
|
|
|
|
contacts.append(cls.parse_artist_contact(contact))
|
|
|
|
elif "release" in url:
|
|
|
|
contacts.append(cls.parse_album_contact(contact))
|
|
|
|
return contacts
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def parse_playlist_soup(cls, playlist_soup: BeautifulSoup) -> List[Song]:
|
|
|
|
# print(playlist_soup.prettify)
|
|
|
|
return []
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
@classmethod
|
2023-03-16 13:36:49 +00:00
|
|
|
def plaintext_search(cls, query: str) -> Options:
|
2023-03-15 19:55:28 +00:00
|
|
|
search_results = []
|
|
|
|
|
2023-03-14 13:48:03 +00:00
|
|
|
search_soup = cls.get_soup_of_search(query=query)
|
|
|
|
if search_soup is None:
|
|
|
|
return None
|
|
|
|
|
|
|
|
# album and songs
|
|
|
|
# child of div class: contacts row
|
2023-03-15 19:55:28 +00:00
|
|
|
for contact_container_soup in search_soup.find_all("div", {"class": "contacts"}):
|
|
|
|
search_results.extend(cls.parse_contact_container(contact_container_soup))
|
2023-03-14 13:48:03 +00:00
|
|
|
|
|
|
|
# song
|
|
|
|
# div class: playlist__item
|
|
|
|
for playlist_soup in search_soup.find_all("div", {"class": "playlist"}):
|
2023-03-15 19:55:28 +00:00
|
|
|
search_results.extend(cls.parse_playlist_soup(playlist_soup))
|
2023-03-14 13:48:03 +00:00
|
|
|
|
2023-03-16 13:36:49 +00:00
|
|
|
return Options(search_results)
|
2023-03-13 14:47:38 +00:00
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def fetch_album_details(cls, album: Album, flat: bool = False) -> Album:
|
|
|
|
|
|
|
|
return album
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def fetch_song_details(cls, song: Song, flat: bool = False) -> Song:
|
|
|
|
source_list = song.source_collection.get_sources_from_page(cls.SOURCE_TYPE)
|
|
|
|
if len(source_list) == 0:
|
|
|
|
return song
|
|
|
|
|
|
|
|
"""
|
|
|
|
TODO
|
|
|
|
lyrics
|
|
|
|
"""
|
|
|
|
|
|
|
|
return song
|