Last active
August 19, 2020 22:54
-
-
Save lvm/e8f89de2cb1b20f73e3ce37aea16d879 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import re | |
import eyed3 | |
import shlex | |
import string | |
import argparse | |
import youtube_dl | |
import subprocess as sp | |
from pathlib import Path | |
from youtube_dl.utils import sanitize_filename | |
USER_AGENT = "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)" | |
BAND_ALBUM_RE = ( | |
f"(?P<band>[{string.printable} ]+)( — | ▲ | - )(?P<song>[{string.printable}]+)" | |
) | |
def ffmpeg(args: list) -> None: | |
"Base ffmpeg call." | |
sp.call(shlex.split(f"ffmpeg -v quiet -y {args}")) | |
def sanitize_album(album: str) -> str: | |
clean_these = [ | |
"full album", # from youtube probably" | |
"\d{4}", # year | |
"(\[|\().*(\]|\))", | |
"HD", | |
] | |
album = re.sub("|".join(clean_these), "", album, flags=re.IGNORECASE).strip() | |
return album | |
def guess_band_song(audio_title: str) -> dict: | |
"Guesses the band / album based on the (non-sliced) filename" | |
dct = {"band":"", "song":""} | |
result = re.search(BAND_ALBUM_RE, audio_title) | |
if result: | |
dct = result.groupdict() | |
dct["band"] = dct.get("band").strip() | |
dct["song"] = sanitize_album(dct.get("song")) | |
else: | |
dct["band"] = "Various artists" | |
dct["song"] = audio_title | |
return dct | |
def save_id3(title:str, audio_file:str) -> None: | |
gbs = guess_band_song(title) | |
audiofile = eyed3.load(audio_file) | |
audiofile.tag.artist = gbs.get("band") | |
audiofile.tag.album = gbs.get("album") | |
audiofile.tag.album_artist = gbs.get("band") | |
audiofile.tag.title = gbs.get("song") | |
audiofile.tag.save() | |
def save_mp3(video_url): | |
"Get video info, save it as mp3 and save id3 tag" | |
assert video_url, "Missing video, can't continue" | |
title = "" | |
YTDL_OPTS = { | |
"quiet": True, | |
# "restrictfilenames": True, | |
"writethumbnail": False, | |
"ignoreerrors": True, | |
"geo_bypass": True, | |
"format": "mp4", | |
"outtmpl": f"%(title)s.%(ext)s", | |
"format": "bestaudio/best", | |
"postprocessors": [ | |
{ | |
"key": "FFmpegExtractAudio", | |
"preferredcodec": "mp3", | |
"preferredquality": "192", | |
} | |
] | |
} | |
with youtube_dl.YoutubeDL(YTDL_OPTS) as ydl: | |
youtube_dl.utils.std_headers["User-Agent"] = USER_AGENT | |
ytdl_info = ydl.extract_info(video_url, download=False) | |
ydl.download([video_url]) | |
title = ytdl_info.get("title") | |
audio_file = sanitize_filename(title, False, False) | |
audio_file = f"{audio_file}.mp3" | |
save_id3(title, audio_file) | |
return title, audio_file | |
if __name__ == "__main__": | |
parser = argparse.ArgumentParser() | |
parser.add_argument("video", type=str, default="", help="Video URL") | |
args = parser.parse_args() | |
if args.video: | |
video = ( | |
args.video | |
if args.video.startswith("https://") | |
else f"https://www.youtube.com/watch?v={args.video}" | |
) | |
title, output = save_mp3(video) | |
print (f"Title: {title}\nFile: {output}") | |
else: | |
parser.print_help() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment