import os
import re
import uuid
import magic
import mimetypes
import httpx
from urllib.parse import urlparse

class FileInfo:
    def __init__(self, filename, extension, mimetype, size):
        self.filename = filename
        self.extension = extension
        self.mimetype = mimetype
        self.size = size

def guess_file_info_from_response(response: httpx.Response):
    url = str(response.url)
    # Try to extract filename from URL
    parsed_url = urlparse(url)
    url_path = parsed_url.path
    filename = os.path.basename(url_path)

    # If filename couldn't be extracted, use Content-Disposition header
    if not filename:
        content_disposition = response.headers.get("Content-Disposition")
        if content_disposition:
            filename_match = re.search(r'filename="?(.+)"?', content_disposition)
            if filename_match:
                filename = filename_match.group(1)

    # If still no filename, generate a unique one
    if not filename:
        unique_name = str(uuid.uuid4())
        filename = f"{unique_name}"

    # Guess MIME type from filename first, then URL
    mimetype, _ = mimetypes.guess_type(filename)
    if mimetype is None:
        mimetype, _ = mimetypes.guess_type(url)
    if mimetype is None:
        # If guessing fails, use Content-Type from response headers
        mimetype = response.headers.get("Content-Type", "application/octet-stream")

    # Use python-magic to guess MIME type if still unknown or generic
    if mimetype == "application/octet-stream":
        magic_mime = magic.Magic(mime=True)
        file_content = response.content[:2048]  # Read the first 2048 bytes
        mimetype = magic_mime.from_buffer(file_content)

    # Ensure filename has an extension
    extension = os.path.splitext(filename)[1]
    if not extension:
        extension = mimetypes.guess_extension(mimetype) or ".bin"
        if extension == ".bin" and mimetype == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
            extension = ".docx"
        filename = f"{os.path.splitext(filename)[0]}{extension}"

    return FileInfo(
        filename=filename,
        extension=extension,
        mimetype=mimetype,
        size=int(response.headers.get("Content-Length", -1)),
    )

# Example request
url = "https://oss.xxx.com/bucket-test4/20250109/8b9f011bd7eb43cdb88f49d9f811b440.docx"
response = httpx.get(url)

if response.status_code == 200:
    file_info = guess_file_info_from_response(response)
    print(file_info.__dict__)
else:
    print(f"Request failed, status code: {response.status_code}")