import hashlib
import re
import subprocess
import gdown
import os
import tempfile
from pathlib import Path

import requests

def get_duration(path: str) -> float:
    return float(subprocess.check_output(
        f'ffprobe -v error -show_entries format=duration -of csv=p=0 "{path}"',
        shell=True).decode().strip())

def is_url(string: str) -> bool:
    return string.startswith("http://") or string.startswith("https://")

def detect_id(url) -> str | None:
    m = re.search(r"(?:d/|folders/)([\w-]+)", url)
    if m:
        return m.group(1)
    return None

def download_by_id(id, output) -> None:
    if not Path(output).exists():
        gdown.download(id=id, output=output)
    return output


def download(url, output) -> str:
    if Path(output).exists():
        return output
    
    if 'drive.google.com' in url:
        gdown.download(url, output=output)
        return output
    
    res = requests.get(url, stream=True)
    res.raise_for_status()
    with open(output, 'wb') as f:
        for chunk in res.iter_content(chunk_size=8192):
            f.write(chunk)
            
    return output
    
    
    

def download_drive_file(url: str, output: str) -> str:
    id = detect_id(url)
    if not id:
        raise ValueError("Link invalid")
    return download_by_id(id, output)

def md5(s: str) -> str:
    return hashlib.md5(s.encode()).hexdigest()