import json, re, urllib.request, sys

UA = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36'


def get(url, raw=False):
    req = urllib.request.Request(url, headers={'User-Agent': UA, 'Accept-Language': 'en-US,en;q=0.9'})
    with urllib.request.urlopen(req, timeout=30) as r:
        data = r.read().decode('utf-8', 'replace')
    return data if raw else json.loads(data)


# SoundCloud addresses a set by the slug in its URL, so these cannot be renamed
# from here — renaming the sets on SoundCloud is what would change them. Every
# downstream file is keyed by the label instead, which is why no slug reaches
# sc_tracks.json, reference.txt or the harness.
SETS = {
    'chosic-playlist': 'set-0',
    'chosic-playlist-1': 'set-1',
    'chosic-playlist-2': 'set-2',
    'chosic-playlist-3': 'set-3',
    'chosic-playlist-4': 'set-4',
    'chosic-playlist-5': 'set-5',
}

page = get(f'https://soundcloud.com/dietrich/sets/{next(iter(SETS))}', raw=True)
scripts = re.findall(r'<script[^>]+src="(https://a-v2\.sndcdn\.com/assets/[^"]+\.js)"', page)
print('asset scripts:', len(scripts))

client_id = None
for src in reversed(scripts):
    try:
        js = get(src, raw=True)
    except Exception as e:
        continue
    m = re.search(r'client_id\s*[:=]\s*"([a-zA-Z0-9]{20,})"', js)
    if m:
        client_id = m.group(1)
        print('client_id found in', src.rsplit('/', 1)[-1])
        break

if not client_id:
    print('no client_id found'); sys.exit(1)

out = {}
for slug, label in SETS.items():
    url = f'https://api-v2.soundcloud.com/resolve?url=https://soundcloud.com/dietrich/sets/{slug}&client_id={client_id}'
    try:
        pl = get(url)
    except Exception as e:
        print(label, 'FAILED', e)
        continue
    tracks = pl.get('tracks', [])
    ids = [t['id'] for t in tracks]
    titled = [t for t in tracks if t.get('title')]
    # Tracks past the first ~5 come back as id-only stubs; fetch them in batches.
    missing = [t['id'] for t in tracks if not t.get('title')]
    for i in range(0, len(missing), 50):
        batch = ','.join(str(x) for x in missing[i:i + 50])
        try:
            more = get(f'https://api-v2.soundcloud.com/tracks?ids={batch}&client_id={client_id}')
            titled.extend(more)
        except Exception as e:
            print('  batch failed', e)
    out[label] = titled
    print(f'{label}: {pl.get("track_count")} tracks, resolved {len(titled)}')

with open('sc_tracks.json', 'w') as f:
    json.dump({k: [{'title': t.get('title'), 'user': (t.get('user') or {}).get('username'),
                    'publisher': t.get('publisher_metadata')} for t in v] for k, v in out.items()}, f, indent=1)
print('\nwrote sc_tracks.json')
for slug, v in out.items():
    print(f'\n{slug}:')
    for t in v[:8]:
        pm = t.get('publisher_metadata') or {}
        print('  ', pm.get('artist') or (t.get('user') or {}).get('username'), '::', t.get('title'))