import json
import sys
import urllib.parse
import urllib.request
UA = "mfe-player/0.2 (+https://github.com/omkargs/mfe-player)"
DOWNLOAD = "https://archive.org/download/{identifier}/{name}"
SEARCH = "https://archive.org/advancedsearch.php"
METADATA = "https://archive.org/metadata/{identifier}"
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 first_audio(identifier):
data = get(METADATA.format(identifier=urllib.parse.quote(identifier)))
for info in data.get("files") or []:
fmt = str(info.get("format") or info.get("name") or "").lower()
name = str(info.get("name") or "")
if any(hint in fmt for hint in ("mp3", "flac", "ogg", "opus")) and name:
return name
return None
def search_for(track):
query = " - ".join(
part for part in (track.get("artist"), track.get("title")) if part
)
params = {
"q": f"(mediatype:(audio)) AND (title:({query}) OR description:({query}))",
"fl[]": ["identifier"],
"rows": "3",
"page": "1",
"output": "json",
}
docs = (get(f"{SEARCH}?{urllib.parse.urlencode(params, doseq=True)}").get(
"response", {}
).get("docs") or [])
for doc in docs:
identifier = doc.get("identifier")
if not identifier:
continue
name = first_audio(identifier)
if name:
return identifier, name
return None, None
def main():
if len(sys.argv) < 3 or sys.argv[1] != "resolve":
fail("usage: main.py resolve '<track-json>'")
try:
track = json.loads(sys.argv[2])
except json.JSONDecodeError as exc:
fail(f"invalid track JSON: {exc}")
identifier = name = None
track_id = str(track.get("id") or "")
if track_id.startswith("ia:"):
identifier, _, name = track_id[3:].partition("/")
if not identifier or not name:
try:
identifier, name = search_for(track)
except Exception as exc:
fail(f"internet archive lookup failed: {exc}")
if not identifier or not name:
fail("no Internet Archive copy of that track was found")
url = DOWNLOAD.format(
identifier=urllib.parse.quote(identifier), name=urllib.parse.quote(name)
)
print(
json.dumps(
{
"url": url,
"webpage_url": f"https://archive.org/details/{identifier}",
"title": track.get("title"),
"duration": track.get("duration"),
"extractor": "Internet Archive",
}
)
)
if __name__ == "__main__":
main()