main.py

import concurrent
import glob
import logging
import re
import shutil
from pathlib import Path

from txtdownloader import TXTDownloader
from ytdownloader import YTDownloader
from coverdownloader import CoverDownloader
from db import *

logging.basicConfig(level=logging.INFO)

class USDBDownloader:
    def __init__(self, rawdir: str, libdir: str, cache=True):
        self.rawdir = Path(rawdir)
        self.libdir = Path(libdir)
        self.db = USDB("USDB.xlsx")
        self.txt = TXTDownloader("nv0rb8ma82p37qrvduvch6j3f6", (self.rawdir / "txt").resolve(), cache)
        self.yt = YTDownloader((self.rawdir / "audio").resolve(), (self.rawdir / "video").resolve(), cache)
        self.cv = CoverDownloader((self.rawdir / "covers").resolve(), cache)

    def download(self):
        executor = concurrent.futures.ThreadPoolExecutor(24)
        futures = [executor.submit(self.download_song, song) for _, song in self.db.data.iterrows()]
        concurrent.futures.wait(futures)

    def download_sample(self):
        executor = concurrent.futures.ThreadPoolExecutor(24)
        futures = [executor.submit(self.download_song, song) for _, song in self.db.data.sample(5).iterrows()]
        concurrent.futures.wait(futures)

    def download_song(self, song: pandas.Series):
        try:
            usdb_url = get_usdb_url(song)
            cover_url = get_cover_image_url(song)
            yt_url = get_yt_video_url(song)
            song_name = get_song_name(song).replace("/", "")
            artist = get_artist_name(song).replace("/", "")
            spotify_uri = get_track_id(song)
            gap = get_gap(song)
            video_gap = get_video_gap(song)
            start = get_start(song)
            end = get_end(song)
            language = get_language(song)
            year = str(get_date(song).year)

            logging.info(f"Downloading: {artist} - {song_name}: {usdb_url}, {cover_url}, {type(yt_url)}")

            if type(usdb_url) == str and usdb_url != " " and usdb_url != "MISSING":
                self.txt.download(usdb_url, artist, song_name, spotify_uri, gap, video_gap, start, end, language, year)

            if type(cover_url) == str and cover_url != " " and cover_url != "MISSING":
                self.cv.download(cover_url, artist, song_name, spotify_uri)

            if type(yt_url) == str and yt_url != " " and yt_url != "MISSING":
                self.yt.download(yt_url, artist, song_name, spotify_uri)

        except Exception as e:
            logging.error(e)

    def build_library(self):
        for file in glob.glob(str(self.rawdir / "txt" / "*.txt")):
            file = Path(file).stem
            outdir = self.libdir / file
            Path(outdir).mkdir(parents=True, exist_ok=True)

            if (self.rawdir / "txt" / f"{file}.txt").is_file():
                shutil.copy2(self.rawdir / "txt" / f"{file}.txt", outdir)
            if (self.rawdir / "audio" / f"{file}.mp3").is_file():
                shutil.copy2(self.rawdir / "audio" / f"{file}.mp3", outdir)
            if (self.rawdir / "video" / f"{file}.mp4").is_file():
                shutil.copy2(self.rawdir / "video" / f"{file}.mp4", outdir)
            if (self.rawdir / "covers" / f"{file}.jpg").is_file():
                shutil.copy2(self.rawdir / "covers" / f"{file}.jpg", outdir)


if __name__ == '__main__':
    dl = USDBDownloader("./out", "./lib", True)
    dl.download_sample()
    dl.build_library()