import json
import re
import urllib.parse
import urllib.request

VIDEO_ID_PATTERN = re.compile(r"^[\w-]{11}$")
YOUTUBE_HOSTS = {"youtube.com", "www.youtube.com", "m.youtube.com", "music.youtube.com", "youtu.be"}
PATH_PREFIXES = ("/shorts/", "/embed/", "/live/")


def video_id(text: str) -> str | None:
    text = text.strip()
    if VIDEO_ID_PATTERN.match(text):
        return text

    url = urllib.parse.urlparse(text if "://" in text else f"https://{text}")
    if url.hostname not in YOUTUBE_HOSTS:
        return None
    if url.hostname == "youtu.be":
        candidate = url.path.strip("/").split("/")[0]
    elif url.path == "/watch":
        candidate = urllib.parse.parse_qs(url.query).get("v", [""])[0]
    else:
        prefix = next((prefix for prefix in PATH_PREFIXES if url.path.startswith(prefix)), None)
        candidate = url.path[len(prefix):].split("/")[0] if prefix else ""
    return candidate if VIDEO_ID_PATTERN.match(candidate) else None


def watch_url(identifier: str) -> str:
    return f"https://music.youtube.com/watch?v={identifier}"


def video_title(identifier: str) -> str | None:
    query = urllib.parse.urlencode({"url": f"https://www.youtube.com/watch?v={identifier}", "format": "json"})
    try:
        with urllib.request.urlopen(f"https://www.youtube.com/oembed?{query}", timeout=10) as response:
            return json.load(response).get("title")
    except (OSError, ValueError):
        return None