Как разбирать и нормализовать URL профилей в соцсетях (Instagram, TikTok, YouTube, X)

Node.js

const HOSTS = {
  "instagram.com": "instagram",
  "tiktok.com": "tiktok",
  "youtube.com": "youtube",
  "x.com": "x",
  "twitter.com": "x",
};

const IG_RESERVED = new Set(["p", "reel", "reels", "tv", "stories", "explore", "accounts", "direct"]);
const X_RESERVED = new Set([
  "home", "explore", "search", "i", "settings", "notifications", "messages",
  "compose", "intent", "hashtag", "login", "signup", "logout", "tos", "privacy",
]);

const IG_HANDLE = /^[a-z0-9._]{1,30}$/;
const TIKTOK_HANDLE = /^[a-z0-9._]{2,24}$/;
const X_HANDLE = /^[a-z0-9_]{1,15}$/;
const YT_HANDLE = /^[\p{L}\p{M}\p{N}._\-·]{1,30}$/u;
const YT_CHANNEL_ID = /^UC[A-Za-z0-9_-]{22}$/;
const YT_LEGACY_NAME = /^[A-Za-z0-9._-]{1,100}$/;

export function parseProfileUrl(input) {
  if (typeof input !== "string") return null;
  let raw = input.trim().replace(/^<|>$/g, "");
  if (!raw) return null;
  if (!/^[a-z][a-z0-9+.-]*:\/\//i.test(raw)) raw = "https://" + raw;

  let url;
  try {
    url = new URL(raw);
  } catch {
    return null;
  }
  if (url.protocol !== "https:" && url.protocol !== "http:") return null;

  const host = url.hostname.toLowerCase().replace(/^(www|m|mobile)\./, "");
  const platform = HOSTS[host];
  if (!platform) return null;

  let segments;
  try {
    segments = url.pathname.split("/").filter(Boolean).map(decodeURIComponent);
  } catch {
    return null; // malformed percent-encoding
  }
  const [first = "", second] = segments;

  if (platform === "instagram") {
    const handle = first.toLowerCase();
    if (segments.length !== 1 || IG_RESERVED.has(handle) || !IG_HANDLE.test(handle)) return null;
    return { platform, handle, canonicalUrl: `https://www.instagram.com/${handle}/` };
  }

  if (platform === "tiktok") {
    if (segments.length !== 1 || !first.startsWith("@")) return null;
    const handle = first.slice(1).toLowerCase();
    if (!TIKTOK_HANDLE.test(handle) || handle.endsWith(".")) return null;
    return { platform, handle, canonicalUrl: `https://www.tiktok.com/@${handle}` };
  }

  if (platform === "x") {
    const handle = first.toLowerCase();
    if (segments.length !== 1 || X_RESERVED.has(handle) || !X_HANDLE.test(handle)) return null;
    return { platform, handle, canonicalUrl: `https://x.com/${handle}` };
  }

  // YouTube: /@handle[/tab], /channel/UC...[/tab], /user/name, /c/name
  if (first.startsWith("@")) {
    const handle = first.slice(1).toLowerCase();
    if (!YT_HANDLE.test(handle) || /^[._\-·]|[._\-·]$/.test(handle)) return null;
    return { platform, handle, canonicalUrl: `https://www.youtube.com/@${encodeURIComponent(handle)}` };
  }
  if (first === "channel" && second && YT_CHANNEL_ID.test(second)) {
    return { platform, channelId: second, canonicalUrl: `https://www.youtube.com/channel/${second}` };
  }
  if ((first === "user" || first === "c") && second && segments.length === 2 && YT_LEGACY_NAME.test(second)) {
    const key = first === "user" ? "username" : "customName";
    return { platform, [key]: second, canonicalUrl: `https://www.youtube.com/${first}/${second}` };
  }
  return null; // videos, shorts, playlists, search and anything else
}

const SHORT_HOSTS = new Set(["vm.tiktok.com", "vt.tiktok.com"]);

export function isShortLink(input) {
  try {
    const url = new URL(/^https?:\/\//i.test(input) ? input : "https://" + input);
    const host = url.hostname.toLowerCase();
    return SHORT_HOSTS.has(host) || (host.replace(/^www\./, "") === "tiktok.com" && url.pathname.startsWith("/t/"));
  } catch {
    return false;
  }
}

export async function resolveShortLink(input) {
  const res = await fetch(/^https?:\/\//i.test(input) ? input : "https://" + input, {
    redirect: "follow",
    signal: AbortSignal.timeout(10_000),
  });
  await res.body?.cancel();
  return res.url; // the final URL after every redirect
}

Python

import re
import unicodedata
import urllib.request
from urllib.parse import quote, unquote, urlsplit

HOSTS = {
    "instagram.com": "instagram",
    "tiktok.com": "tiktok",
    "youtube.com": "youtube",
    "x.com": "x",
    "twitter.com": "x",
}

IG_RESERVED = {"p", "reel", "reels", "tv", "stories", "explore", "accounts", "direct"}
X_RESERVED = {
    "home", "explore", "search", "i", "settings", "notifications", "messages",
    "compose", "intent", "hashtag", "login", "signup", "logout", "tos", "privacy",
}

IG_HANDLE = re.compile(r"[a-z0-9._]{1,30}")
TIKTOK_HANDLE = re.compile(r"[a-z0-9._]{2,24}")
X_HANDLE = re.compile(r"[a-z0-9_]{1,15}")
YT_CHANNEL_ID = re.compile(r"UC[A-Za-z0-9_-]{22}")
YT_LEGACY_NAME = re.compile(r"[A-Za-z0-9._-]{1,100}")
YT_PUNCT = "._-·"


def _is_youtube_handle(handle):
    if not 1 <= len(handle) <= 30 or handle[0] in YT_PUNCT or handle[-1] in YT_PUNCT:
        return False
    return all(
        ch.isalnum() or ch in YT_PUNCT or unicodedata.category(ch).startswith("M")
        for ch in handle
    )


def parse_profile_url(value):
    if not isinstance(value, str):
        return None
    raw = value.strip().strip("<>")
    if not raw:
        return None
    if not re.match(r"^[a-z][a-z0-9+.-]*://", raw, re.I):
        raw = "https://" + raw

    try:
        url = urlsplit(raw)
        host = (url.hostname or "").lower()
    except ValueError:
        return None
    if url.scheme.lower() not in ("http", "https"):
        return None

    host = re.sub(r"^(www|m|mobile)\.", "", host)
    platform = HOSTS.get(host)
    if not platform:
        return None

    try:
        segments = [unquote(s, errors="strict") for s in url.path.split("/") if s]
    except UnicodeDecodeError:
        return None  # malformed percent-encoding
    first = segments[0] if segments else ""
    second = segments[1] if len(segments) > 1 else None

    if platform == "instagram":
        handle = first.lower()
        if len(segments) != 1 or handle in IG_RESERVED or not IG_HANDLE.fullmatch(handle):
            return None
        return {"platform": platform, "handle": handle,
                "canonicalUrl": f"https://www.instagram.com/{handle}/"}

    if platform == "tiktok":
        if len(segments) != 1 or not first.startswith("@"):
            return None
        handle = first[1:].lower()
        if not TIKTOK_HANDLE.fullmatch(handle) or handle.endswith("."):
            return None
        return {"platform": platform, "handle": handle,
                "canonicalUrl": f"https://www.tiktok.com/@{handle}"}

    if platform == "x":
        handle = first.lower()
        if len(segments) != 1 or handle in X_RESERVED or not X_HANDLE.fullmatch(handle):
            return None
        return {"platform": platform, "handle": handle, "canonicalUrl": f"https://x.com/{handle}"}

    # YouTube: /@handle[/tab], /channel/UC...[/tab], /user/name, /c/name
    if first.startswith("@"):
        handle = first[1:].lower()
        if not _is_youtube_handle(handle):
            return None
        return {"platform": platform, "handle": handle,
                "canonicalUrl": f"https://www.youtube.com/@{quote(handle, safe='._-')}"}
    if first == "channel" and second and YT_CHANNEL_ID.fullmatch(second):
        return {"platform": platform, "channelId": second,
                "canonicalUrl": f"https://www.youtube.com/channel/{second}"}
    if first in ("user", "c") and second and len(segments) == 2 and YT_LEGACY_NAME.fullmatch(second):
        key = "username" if first == "user" else "customName"
        return {"platform": platform, key: second,
                "canonicalUrl": f"https://www.youtube.com/{first}/{second}"}
    return None  # videos, shorts, playlists, search and anything else


SHORT_HOSTS = {"vm.tiktok.com", "vt.tiktok.com"}


def is_short_link(value):
    url = urlsplit(value if re.match(r"^https?://", value, re.I) else "https://" + value)
    host = (url.hostname or "").lower()
    return host in SHORT_HOSTS or (
        re.sub(r"^www\.", "", host) == "tiktok.com" and url.path.startswith("/t/")
    )


def resolve_short_link(value, timeout=10):
    if not re.match(r"^https?://", value, re.I):
        value = "https://" + value
    request = urllib.request.Request(value, headers={"User-Agent": "Mozilla/5.0"})
    with urllib.request.urlopen(request, timeout=timeout) as response:
        return response.geturl()  # the final URL after every redirect

Тест на Node.js

import assert from "node:assert/strict";
import { parseProfileUrl } from "./parse.mjs";

const cases = [
  ["instagram.com/NatGeo?igsh=MWQ1ZGUxMzBkMA==", { platform: "instagram", handle: "natgeo", canonicalUrl: "https://www.instagram.com/natgeo/" }],
  ["https://www.instagram.com/reel/C9xYzAbCdEf/", null],
  ["https://www.instagram.com/explore/", null],
  ["tiktok.com/@Khaby.Lame/", { platform: "tiktok", handle: "khaby.lame", canonicalUrl: "https://www.tiktok.com/@khaby.lame" }],
  ["https://www.tiktok.com/@khaby.lame/video/7106594312292453675", null],
  ["https://vm.tiktok.com/ZMabc123/", null],
  ["https://m.youtube.com/@GoogleDevelopers/videos", { platform: "youtube", handle: "googledevelopers", canonicalUrl: "https://www.youtube.com/@googledevelopers" }],
  ["https://www.youtube.com/channel/UC_x5XG1OV2P6uZZ5FSM9Ttw/featured", { platform: "youtube", channelId: "UC_x5XG1OV2P6uZZ5FSM9Ttw", canonicalUrl: "https://www.youtube.com/channel/UC_x5XG1OV2P6uZZ5FSM9Ttw" }],
  ["https://www.youtube.com/user/GoogleDevelopers", { platform: "youtube", username: "GoogleDevelopers", canonicalUrl: "https://www.youtube.com/user/GoogleDevelopers" }],
  ["https://youtu.be/dQw4w9WgXcQ", null],
  ["https://twitter.com/Jack/", { platform: "x", handle: "jack", canonicalUrl: "https://x.com/jack" }],
  ["https://mobile.twitter.com/jack?s=21", { platform: "x", handle: "jack", canonicalUrl: "https://x.com/jack" }],
  ["https://x.com/jack/status/20", null],
  ["https://x.com/i/flow/login", null],
  ["https://instagram.com.evil.com/natgeo", null],
];

for (const [input, expected] of cases) {
  assert.deepEqual(parseProfileUrl(input), expected, input);
}
console.log(`${cases.length} cases passed`);

Тест на Python

from parse_profile import parse_profile_url

CASES = [
    ("instagram.com/NatGeo?igsh=MWQ1ZGUxMzBkMA==", {"platform": "instagram", "handle": "natgeo", "canonicalUrl": "https://www.instagram.com/natgeo/"}),
    ("https://www.instagram.com/reel/C9xYzAbCdEf/", None),
    ("tiktok.com/@Khaby.Lame/", {"platform": "tiktok", "handle": "khaby.lame", "canonicalUrl": "https://www.tiktok.com/@khaby.lame"}),
    ("https://vm.tiktok.com/ZMabc123/", None),
    ("https://m.youtube.com/@GoogleDevelopers/videos", {"platform": "youtube", "handle": "googledevelopers", "canonicalUrl": "https://www.youtube.com/@googledevelopers"}),
    ("https://www.youtube.com/channel/UC_x5XG1OV2P6uZZ5FSM9Ttw/featured", {"platform": "youtube", "channelId": "UC_x5XG1OV2P6uZZ5FSM9Ttw", "canonicalUrl": "https://www.youtube.com/channel/UC_x5XG1OV2P6uZZ5FSM9Ttw"}),
    ("https://youtu.be/dQw4w9WgXcQ", None),
    ("https://twitter.com/Jack/", {"platform": "x", "handle": "jack", "canonicalUrl": "https://x.com/jack"}),
    ("https://x.com/i/flow/login", None),
    ("https://instagram.com.evil.com/natgeo", None),
]

for value, expected in CASES:
    assert parse_profile_url(value) == expected, value
print(f"{len(CASES)} cases passed")