网易云音乐歌单下载，保留 ID3 属性

netease_music_dl.py

from bs4 import BeautifulSoup
from pathlib import Path
from dataclasses import dataclass
import urllib.request
import re
from unicodedata import normalize
from mutagen.mp3 import EasyMP3


DOWNLOAD_TEMPLATE = "http://music.163.com/song/media/outer/url?id=%s.mp3"
ROOT = Path(__file__).parent


@dataclass
class Music:
    id: str
    title: str
    filename: str
    artist: str
    album: str


def download_mp3(music: Music):
    mp3file = ROOT / "mp3" / f"{music.filename}.mp3"
    if mp3file.exists():
        print(f"{music.title} is already download")
        return

    url = DOWNLOAD_TEMPLATE % music.id
    print(f"Downloading {music.title}")
    data = urllib.request.urlopen(
        urllib.request.Request(
            url,
            headers={
                "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36"
            },
        )
    ).read()
    if len(data) < 1000:
        print("Error:", data)
        return

    with open(mp3file, "wb") as f:
        f.write(data)

    mp3meta = EasyMP3(mp3file)
    mp3meta["album"] = music.album
    mp3meta["albumartist"] = music.artist
    mp3meta["artist"] = music.artist
    mp3meta["title"] = music.title
    mp3meta.save()


def create_filename(title):
    title = re.sub(r"\(.*\)$", "", title).strip()
    title = re.sub(r"[\\/:*\"<>?|]", " ", title).strip(' -.')
    return title


def main(html):
    soup = BeautifulSoup(html, "html.parser")

    for tr in soup.find_all("tr"):
        id, title, _, artist, album = tr.find_all("td")
        music = Music(
            id=id.span["data-res-id"],
            title=normalize("NFKD", title.b["title"]),
            filename=normalize("NFKD", create_filename(title.b["title"])),
            artist=normalize("NFKD", artist.span["title"]),
            album=normalize("NFKD", album.a["title"]),
        )
        download_mp3(music)
        # print(music)


if __name__ == "__main__":
    (ROOT / "mp3").mkdir(exist_ok=True)
    main(input("> ))

requirements.txt

mutagen
beautifulsoup4

~instruction.md

1. 在歌单页面打开控制台，输入 frames[0].document.getElementsByTagName('tbody')[0].innerHTML 复制 HTML
2. 安装库并运行 Python 脚本，粘贴 HTML 回车