tabletopaudio_dl.py

tabletopaudio_dl.py

#!/usr/bin/env python3

import requests
import argparse
import re
import json

from pathlib import Path
from bs4 import BeautifulSoup
from dataclasses import dataclass


BASE_URL = "https://tabletopaudio.com"
SOUND_BASE_URL = "https://sounds.tabletopaudio.com"
PICO_MIXER_ROOT_DIR = Path.home() / "code" / "pico-mixer"
PICO_MIXER_CONFIG_PATH = PICO_MIXER_ROOT_DIR / "config.json"
PICO_MIXER_SOUNDS_DIR = PICO_MIXER_ROOT_DIR / "pico_mixer_web" / "assets" / "sounds"


@dataclass
class Track:
    filename: str
    url: str
    tags: list[str]


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description=f"Download tracks from {BASE_URL} by name"
    )
    parser.add_argument(
        "--tracks",
        nargs="+",
        help=f"The name of the tracks to download, as displayed on {BASE_URL}",
        required=True,
    )
    return parser.parse_args()


def download_file(url: str, local_filename: Path):
    with requests.get(url, stream=True) as r:
        r.raise_for_status()
        with open(local_filename, "wb") as f:
            for chunk in r.iter_content(chunk_size=8192):
                f.write(chunk)


def parse_homepage() -> BeautifulSoup:
    html = requests.get(BASE_URL).text
    return BeautifulSoup(html, features="html.parser")


def sanitize_track_filename(filename: str) -> str:
    filename = re.sub(r"^\d+", "", filename)
    return filename.replace("_", " ").strip()


def parse_track_details(soup: BeautifulSoup, track_name: str) -> str:
    track_title_divs = soup.find_all("div", class_="track_title")
    for track_title_div in track_title_divs:
        h3 = track_title_div.find("h3")
        if not h3:
            continue
        if h3.text == track_name:
            break
    else:
        msg = f"Track {track_name} not found"
        raise ValueError(msg)
    track_download_link = track_title_div.find_next("span", class_="saveButton").find(
        "a"
    )
    track_name = re.search(
        r"saveAs\('(\w+)'\)", track_download_link.attrs["onclick"]
    ).group(1)
    track_filename = sanitize_track_filename(f"{track_name}.mp3")
    track_url = f"{SOUND_BASE_URL}/{track_name}.mp3"
    tags_div = track_title_div.find_previous("div")
    tags = [tag for tag in tags_div.attrs["class"] if tag != "col-md-3"]
    return Track(filename=track_filename, url=track_url, tags=tags)


def download_track(track_details: Track):
    local_track_file_path = PICO_MIXER_SOUNDS_DIR / Path(track_details.filename)
    if local_track_file_path.exists():
        print(f"{local_track_file_path} already exists. Skipping download")
    else:
        print(f"Downloading track {track_details.filename}")
        download_file(track_details.url, local_track_file_path)


def add_track_to_pico_mixer_config_file(track_details: Track):
    config = json.load(open(PICO_MIXER_CONFIG_PATH))
    for entry in config:
        if entry["title"] == track_details.filename:
            break
    else:
        print(f"Registering track {track_details.filename} to pico mixer config")
        config.append({"title": track_details.filename, "tags": track_details.tags})
        with open(PICO_MIXER_CONFIG_PATH, "w") as out:
            json.dump(config, out, indent=2)


def main():
    args = parse_args()
    soup = parse_homepage()
    for track in args.tracks:
        track_details = parse_track_details(soup, track.strip())
        download_track(track_details)
        add_track_to_pico_mixer_config_file(track_details)


if __name__ == "__main__":
    main()