from __future__ import annotations from pathlib import PurePosixPath from urllib.parse import unquote, urlsplit IMAGE_EXTENSIONS = { ".png", ".jpg", ".jpeg", ".webp", ".bmp", ".svg", } GIF_EXTENSIONS = {".gif"} AUDIO_EXTENSIONS = { ".mp3", ".wav", ".ogg", ".m4a", ".flac", } VIDEO_EXTENSIONS = { ".mp4", ".webm", ".mov", ".avi", ".mkv", } MARKDOWN_EXTENSIONS = {".md", ".markdown"} WEBPAGE_EXTENSIONS = {".html", ".htm", ".xhtml"} MEDIA_MIME_TYPES = { ".mp3": "audio/mpeg", ".wav": "audio/wav", ".ogg": "audio/ogg", ".m4a": "audio/mp4", ".flac": "audio/flac", ".mp4": "video/mp4", ".webm": "video/webm", ".mov": "video/quicktime", ".avi": "video/x-msvideo", ".mkv": "video/x-matroska", } def extension_from_url(url: str) -> str: path = unquote(urlsplit(url).path) return PurePosixPath(path).suffix.lower() def media_kind(url: str) -> str | None: ext = extension_from_url(url) if ext in GIF_EXTENSIONS: return "gif" if ext in IMAGE_EXTENSIONS: return "image" if ext in AUDIO_EXTENSIONS: return "audio" if ext in VIDEO_EXTENSIONS: return "video" return None def is_markdown_url(url: str) -> bool: return extension_from_url(url) in MARKDOWN_EXTENSIONS def is_webpage_url(url: str) -> bool: return extension_from_url(url) in WEBPAGE_EXTENSIONS def media_mime_type(url: str) -> str: return MEDIA_MIME_TYPES.get(extension_from_url(url), "")