feat: implemented parsing of tracklist of album

This commit is contained in:
Hellow 2023-09-12 20:18:51 +02:00
parent e9e9e61e7c
commit 6a37351da1
3 changed files with 51 additions and 10 deletions

View File

@ -29,8 +29,8 @@ if __name__ == "__main__":
]
youtube_music_test = [
"s: #a Only Smile",
"0"
"s: #a Only Smile #r Your best friend",
"8"
]
music_kraken.cli.download(genre="test", command_list=youtube_music_test, process_metadata_anyway=True)

View File

@ -467,7 +467,8 @@ class Artist(MainObject):
"formed_in": ID3Timestamp(),
"notes": FormattedText(),
"lyrical_themes": [],
"general_genre": ""
"general_genre": "",
"unformated_location": None,
}
DOWNWARDS_COLLECTION_ATTRIBUTES = ("feature_song_collection", "main_album_collection")
@ -489,6 +490,7 @@ class Artist(MainObject):
country: CountryTyping = None,
formed_in: ID3Timestamp = None,
label_list: List['Label'] = None,
unformated_location: str = None,
**kwargs
):
MainObject.__init__(self, _id=_id, dynamic=dynamic, **kwargs)
@ -520,6 +522,8 @@ class Artist(MainObject):
self.contact_collection: Collection[Label] = Collection(data=contact_list, element_type=Contact)
self.unformated_location: Optional[str] = unformated_location
def _add_other_db_objects(self, object_type: Type["DatabaseObject"], object_list: List["DatabaseObject"]):
if object_type is Song:
# this doesn't really make sense

View File

@ -1,6 +1,6 @@
from typing import List, Optional, Type
from urllib.parse import urlparse
import logging
import json
from enum import Enum
from bs4 import BeautifulSoup
@ -146,6 +146,10 @@ class Bandcamp(Page):
def song_search(self, song: Song) -> List[Song]:
return self.general_search(song.title, filter_string="t")
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] = []
@ -203,15 +207,48 @@ class Bandcamp(Page):
return artist
def _parse_track_element(self, track: dict) -> Optional[Song]:
return Song(
title=track["item"]["name"],
source_list=[Source(self.SOURCE_TYPE, track["item"]["mainEntityOfPage"])],
tracksort=track["position"]
)
def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
print(source)
album = Album()
r = self.connection.get(source.url)
if r is None:
return album
soup = self.get_soup_from_response(r)
if DEBUG:
# dump_to_file("album_page.html", r.text, exit_after_dump=False)
pass
data_container = soup.find("script", {"type": "application/ld+json"})
if DEBUG:
dump_to_file("album_data.json", data_container.text, is_json=True, exit_after_dump=False)
data = json.loads(data_container.text)
for i, track_json in enumerate(data.get("track", {}).get("itemListElement", [])):
if DEBUG:
dump_to_file(f"album_track_{i}.json", json.dumps(track_json), is_json=True, exit_after_dump=False)
try:
album.song_collection.append(self._parse_track_element(track_json))
except KeyError:
continue
return album
def fetch_song(self, source: Source, stop_at_level: int = 1) -> Song:
print(source)
return Song()
def fetch_album(self, source: Source, stop_at_level: int = 1) -> Album:
return Album()
def fetch_label(self, source: Source, stop_at_level: int = 1) -> Label:
return Label()
def download_song_to_target(self, source: Source, target: Target, desc: str = None) -> DownloadResult:
return DownloadResult()