From ce6be946d024aa55a15d576388d05f90be671cf2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Romain=20Gon=C3=A7alves?= <me@rgoncalves.se>
Date: Sat, 8 Oct 2022 12:40:19 +0200
Subject: Sat Oct  8 12:40:19 PM CEST 2022

---
 .bin/music | 174 ++++++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 104 insertions(+), 70 deletions(-)

(limited to '.bin/music')

diff --git a/.bin/music b/.bin/music
index 6ef5ef8..a14aae9 100755
--- a/.bin/music
+++ b/.bin/music
@@ -1,70 +1,104 @@
-#!/bin/sh
-
-
-MUSIC_DIR="${HOME}/music"
-MUSIC_LIST=
-MUSIC_FILE=
-MUSIC_YT_OPTIONS=
-
-log() {
-	echo "[${0}  ] ${@}"
-}
-
-main() {
-	# arguments
-	while getopts "c:" arg; do
-		case "${arg}" in
-			c)
-				MUSIC_FILE="${OPTARG}"
-				;;
-			h)
-				exit 0
-				;;
-		esac
-	done
-
-	# ensure parameters are correct
-	[ ! -f "${MUSIC_FILE}" ] && exit 1
-
-
-	while read -r line; do
-		
-		# skip comments
-		line=$(echo ${line} | grep -v -e "^$" -e "^#")
-		[ -z "${line}" ] && continue
-
-		# retrieve playlist params
-		url=$(echo "${line}" | cut -d " " -f 1)
-		dir=$(echo "${line}" | cut -d " " -f 2)
-
-		dir="${MUSIC_DIR}/${dir}"
-
-		[ -d "${dir}" ] &&
-			log "${dir}: directory already exists" &&
-			continue
-
-		mkdir "${dir}"
-		log "${dir} ${url}: download"
-
-		yt-dlp --rm-cache-dir >/dev/null
-		yt-dlp \
-			--extract-audio \
-			--audio-format mp3 \
-			--prefer-ffmpeg \
-			--audio-quality 0 \
-			--embed-thumbnail \
-			--metadata-from-title "%(artist)s - %(title)s" \
-			--no-warnings \
-			--ignore-errors \
-			--no-overwrites \
-			--continue \
-			--add-metadata \
-			--user-agent "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)" \
-			--output "${dir}/'%(title)s.%(ext)s'" \
-			"${url}"
-
-
-	done < "${MUSIC_FILE}"
-}
-
-main ${@}
+#!/usr/bin/python3
+
+import os
+import sys
+import yt_dlp
+from dataclasses import dataclass
+
+
+def _match_filter(info: dict, *, incomplete) -> str | None:
+    _duration = info.get("duration")
+    _duration_min = 60
+
+    if _duration and int(_duration) < _duration_min:
+        return "Duration too short: < _duration_min"
+
+    return None
+
+
+@dataclass(frozen=True)
+class Collection:
+    """A music collection."""
+
+    title: str
+    links: frozenset[str]
+
+    def __eq__(self, other) -> bool:
+        if isinstance(other, Collection):
+            return self.title == other.title
+        raise NotImplementedError
+
+
+def parse_raw_to_collections(raw_data: list[str]) -> frozenset[Collection]:
+    collections: set[Collection] = set()
+    _collection_data: list[str] = []
+
+    for index, line in enumerate(raw_data):
+        if line.startswith("#"):
+            continue
+        elif line == "" or index + 1 == len(raw_data):
+            if len(_collection_data) == 0:
+                continue
+
+            collections.add(
+                Collection(_collection_data[0], frozenset(_collection_data[1:]))
+            )
+            _collection_data.clear()
+        else:
+            _collection_data.append(line)
+
+    return frozenset(collections)
+
+
+def get_ytdlp_options(output_dir: str) -> dict:
+    return {
+        "format": "bestaudio/best",
+        "match_filter": _match_filter,
+        "postprocessors": [
+            {
+                "key": "FFmpegExtractAudio",
+                #"preferredcodec": "m4a",
+            },
+            {
+                "key": "FFmpegMetadata",
+                "add_metadata": True,
+            },
+            {
+                "key": "EmbedThumbnail",
+                "already_have_thumbnail": False,
+            },
+        ],
+        "outtmpl": f"{output_dir}/%(title)s.%(ext)s",
+        "restrictfilenames": True,
+        "ignoreerrors": True,
+    }
+
+
+def download_collection(collection: Collection, parent_dir: str) -> None:
+    output_dir = os.path.join(parent_dir, collection.title)
+
+    if os.path.isdir(output_dir):
+        return
+
+    os.makedirs(output_dir, exist_ok=True)
+
+    with yt_dlp.YoutubeDL(get_ytdlp_options(output_dir)) as downloader:
+        downloader.download(collection.links)
+
+
+def main() -> int:
+    # input handling
+    if len(sys.argv) != 2:
+        return 1
+
+    with open(sys.argv[1], "r") as file:
+        filedata = file.read().splitlines()
+
+    for collection in parse_raw_to_collections(filedata):
+        download_collection(collection, os.getcwd())
+
+    return 0
+
+
+if __name__ == "__main__":
+    exit(main())
-- 
cgit v1.2.3