#!/usr/bin/env python

""" Check if an item on archive.org has an acoustid.

Usage:
./check_for_acoustid.py {item}

Usage with GNU Parallel:
cat itemlist.txt | parallel --max-procs=8 --group './check_for_acoustid.py {}'

"""
import sys
import json
import urllib

 
def get_iterable(x):
    return (x,) if not isinstance(x, (tuple, list)) else x

def iter_contains_prefix(iter, prefix):
    for s in iter:
        if s.startswith(prefix):
            return True
    return False

def get_url(url):
    f = urllib.urlopen(url)
    c = f.read()
    f.close()
    return c

def get_meta(item):
    j = get_url("http://archive.org/metadata/" + item)
    yield json.loads(j);

def item_iterator():
    filename = 'items'
    f = open("items")
    for line in f:
      yield line.strip()

def file_has_audio(file):
    if (file.get('source') == 'original' and
        file['format'] in ('VBR MP3', 'AIFF', '24bit Flac', 'Flac',
                           'Apple Lossless Audio', 'Advanced Audio Coding')):
        return True

item = sys.argv[1]
for metadata in get_meta(item):
    files = metadata.get('files')
    if not files:
        continue
    for file in files:
        if file_has_audio(file):
            fexts = file.get('external-identifier', [])
            found_accoustid = iter_contains_prefix(get_iterable(fexts),
                                                   'urn:acoustid')
            if not found_accoustid:
                print metadata['metadata']['identifier']
                break