import json
import sys
import urllib.parse
import urllib.request
UA = "mfe-player/0.2 (+https://github.com/omkargs/mfe-player)"
SEARCH = "https://archive.org/advancedsearch.php"
METADATA = "https://archive.org/metadata/{identifier}"
AUDIO_HINTS = ("mp3", "flac", "ogg", "opus", "m4a", "wav")
SKIP_HINTS = ("64kbps mono", "thumbnail")
def fail(message):
print(message, file=sys.stderr)
raise SystemExit(1)
def get(url):
request = urllib.request.Request(url, headers={"User-Agent": UA})
with urllib.request.urlopen(request, timeout=20) as response:
return json.load(response)
def seconds(length):
if not length or not isinstance(length, str):
return None
parts = length.split(":")
if not all(part.isdigit() for part in parts):
return None
total = 0
for part in parts:
total = total * 60 + int(part)
return total or None
def is_audio(info):
fmt = str(info.get("format") or info.get("name") or "").lower()
return any(hint in fmt for hint in AUDIO_HINTS) and not any(
hint in fmt for hint in SKIP_HINTS
)
def tracks_for(doc):
identifier = doc.get("identifier")
if not identifier:
return []
try:
data = get(METADATA.format(identifier=urllib.parse.quote(identifier)))
except Exception:
return []
collection_title = (doc.get("title") or "").strip()
creator = doc.get("creator")
if isinstance(creator, list):
creator = ", ".join(str(part) for part in creator)
creator = str(creator or "").strip()
artwork = None
for name in ("__ia_thumb.jpg", "itemimage.jpg", "thumbnail.jpg"):
if any(str(info.get("name")) == name for info in data.get("files") or []):
artwork = f"https://archive.org/download/{identifier}/{name}"
break
out, added = [], set()
for info in data.get("files") or []:
name = str(info.get("name") or "")
if not is_audio(info) or name in added:
continue
added.add(name)
title = str(info.get("title") or info.get("name") or "").strip()
if not title:
continue
out.append(
{
"id": f"ia:{identifier}/{name}",
"title": title,
"artist": creator or (str(doc.get("collection") or "").strip()),
"album": str(info.get("album") or collection_title).strip(),
"duration": seconds(info.get("length")),
"artwork": artwork,
"source": "internet-archive",
"year": str(doc.get("year") or "")[:4] or None,
}
)
if len(out) >= 6:
break
return out
def cmd_search(query):
params = {
"q": f"(mediatype:(audio)) AND (title:({query}) OR creator:({query}) OR description:({query}))",
"fl[]": ["identifier", "title", "creator", "year"],
"rows": "8",
"page": "1",
"output": "json",
"sort[]": "downloads desc",
}
url = f"{SEARCH}?{urllib.parse.urlencode(params, doseq=True)}"
docs = (get(url).get("response") or {}).get("docs") or []
tracks = []
for doc in docs:
tracks.extend(tracks_for(doc))
if len(tracks) >= 24:
break
artists = sorted({track["artist"] for track in tracks if track["artist"]})
return {"artists": [], "albums": [], "tracks": tracks, "_artists_seen": artists}
def main():
if len(sys.argv) < 3:
fail("usage: main.py search '<query>'")
command = sys.argv[1]
if command == "search":
print(json.dumps({"artists": [], "albums": [], **cmd_search(sys.argv[2])}))
else:
print(json.dumps({"artists": [], "albums": [], "tracks": []}))
if __name__ == "__main__":
main()