antisocial/src/platforms/tiktok.ts

import type { Page } from 'playwright';
import { ChallengeError, ResolveError, oneSegment, type Media, type Post } from '../types.ts';
import { cookieHeaderFor } from '../browser/pool.ts';
import { CHALLENGE_SELECTORS, park } from '../challenge/registry.ts';
import { config } from '../config.ts';
import { readInlineJson, readOpenGraph } from '../browser/capture.ts';
import { hostMatcher } from './url.ts';
import type { PlatformSpec, ResolveContext } from './types.ts';

const REFERER = 'https://www.tiktok.com/';

type UrlList = { UrlList?: string[] };

type ItemStruct = {
  id?: string;
  desc?: string;
  createTime?: number | string;
  author?: { uniqueId?: string; nickname?: string; avatarMedium?: string; avatarLarger?: string };
  video?: {
    playAddr?: string;
    downloadAddr?: string;
    cover?: string;
    duration?: number;
    width?: number;
    height?: number;
    bitrateInfo?: Array<{ Bitrate?: number; PlayAddr?: UrlList }>;
  };
  imagePost?: {
    images?: Array<{ imageURL?: UrlList; imageWidth?: number; imageHeight?: number }>;
  };
};

type Rehydration = {
  __DEFAULT_SCOPE__?: Record<string, { itemInfo?: { itemStruct?: ItemStruct } } | undefined>;
};

/**
 * The post lives under `webapp.video-detail` for a video and a different key
 * for a photo post, so take whichever scope actually carries one rather than
 * naming them.
 */
function findItemStruct(data: Rehydration | undefined): ItemStruct | undefined {
  for (const scope of Object.values(data?.__DEFAULT_SCOPE__ ?? {})) {
    const item = scope?.itemInfo?.itemStruct;
    if (item) return item;
  }
  return undefined;
}

/**
 * TikTok's CDN checks the referrer and, for some regions, the session
 * cookies the page was served with. The proxy replays both.
 */
async function tiktokHeaders(url: string): Promise<Record<string, string>> {
  const cookie = await cookieHeaderFor(url);
  return {
    Referer: REFERER,
    ...(cookie ? { Cookie: cookie } : {}),
  };
}

/** Shared TikTok links lead with the author, e.g. `@user/video/123`. */
function handleFrom(url: string): string | undefined {
  const match = /tiktok\.com\/(@[\w.-]+)\//.exec(url);
  return match?.[1];
}

function bestPlayAddr(video: NonNullable<ItemStruct['video']>): string | undefined {
  const ranked = (video.bitrateInfo ?? [])
    .filter((entry) => entry.PlayAddr?.UrlList?.length)
    .sort((a, b) => (b.Bitrate ?? 0) - (a.Bitrate ?? 0))[0];
  return ranked?.PlayAddr?.UrlList?.[0] ?? video.playAddr ?? video.downloadAddr;
}

export async function mediaFromItem(item: ItemStruct): Promise<Media[]> {
  // A TikTok photo post carries no video at all.
  const photos = item.imagePost?.images;
  if (photos?.length) {
    const results: Media[] = [];
    for (const photo of photos) {
      const url = photo.imageURL?.UrlList?.[0];
      if (!url) continue;
      results.push({
        kind: 'image',
        url,
        fetchHeaders: await tiktokHeaders(url),
        ...(photo.imageWidth ? { width: photo.imageWidth } : {}),
        ...(photo.imageHeight ? { height: photo.imageHeight } : {}),
      });
    }
    return results;
  }

  const video = item.video;
  const src = video ? bestPlayAddr(video) : undefined;
  if (!video || !src) return [];

  return [{
    kind: 'video',
    url: src,
    fetchHeaders: await tiktokHeaders(src),
    ...(video.cover
      ? { poster: { url: video.cover, fetchHeaders: await tiktokHeaders(video.cover) } }
      : {}),
    ...(video.duration ? { durationSec: video.duration } : {}),
    ...(video.width ? { width: video.width } : {}),
    ...(video.height ? { height: video.height } : {}),
  }];
}

/**
 * TikTok sometimes answers with a slider puzzle instead of the post.
 *
 * It renders a moment after the document is ready, so this waits rather than
 * looking once — checking too early reports a broken adapter when the real
 * answer is "there is a puzzle in the way".
 */
async function isChallenged(page: Page): Promise<boolean> {
  const appeared = await page
    .waitForSelector(CHALLENGE_SELECTORS, { state: 'visible', timeout: 5_000 })
    .then(() => true)
    .catch(() => false);
  if (appeared) return true;

  return page
    .evaluate(() => /drag the slider|verify to continue/i.test(document.body?.innerText ?? ''))
    .catch(() => false);
}

async function resolve(ctx: ResolveContext): Promise<Post> {
  const { page, originalUrl, detach } = ctx;

  // Short links (`vm.`/`vt.`) are redirect stubs; loading one lands on the
  // real post, and `page.url()` is then the canonical address.
  await page.goto(originalUrl, { waitUntil: 'domcontentloaded' });
  const landed = page.url();

  const data = await readInlineJson<Rehydration>(
    page,
    'script#__UNIVERSAL_DATA_FOR_REHYDRATION__',
    config.navigationTimeoutMs,
  );
  const item = findItemStruct(data);

  if (item) {
    const media = await mediaFromItem(item);
    if (media.length > 0) {
      const handle = item.author?.uniqueId ?? 'tiktok';
      const avatar = item.author?.avatarLarger ?? item.author?.avatarMedium;
      const created = Number(item.createTime);
      return {
        platform: 'tiktok',
        platformLabel: 'TikTok',
        originalUrl: landed.startsWith('https://www.tiktok.com/') ? landed : originalUrl,
        author: {
          handle: `@${handle}`,
          ...(item.author?.nickname ? { displayName: item.author.nickname } : {}),
          ...(avatar ? { avatar: { url: avatar, fetchHeaders: await tiktokHeaders(avatar) } } : {}),
        },
        textPosition: 'below',
        segments: oneSegment({
          ...(item.desc ? { text: item.desc } : {}),
          media,
          ...(Number.isFinite(created) && created > 0
            ? { postedAt: new Date(created * 1000).toISOString() }
            : {}),
        }),
      };
    }
  }

  // Fall back to the link preview, which at least gets a poster on screen.
  if (await isChallenged(page)) {
    // Keep the page open and hand the puzzle to whoever is reading. Solving
    // it deposits the cookie in the shared browser context, so the retry
    // afterwards is an ordinary request.
    detach();
    const id = await park({
      page,
      platform: 'tiktok',
      platformLabel: 'TikTok',
      originalUrl,
    });
    throw new ChallengeError(id, 'tiktok', originalUrl);
  }

  const og = await readOpenGraph(page);
  if (og['og:video'] ?? og['og:image']) {
    const url = og['og:video'] ?? (og['og:image'] as string);
    return {
      platform: 'tiktok',
      platformLabel: 'TikTok',
      originalUrl,
      author: { handle: handleFrom(landed) ?? handleFrom(originalUrl) ?? '@tiktok' },
      textPosition: 'below',
      segments: oneSegment({
        ...(og['og:description'] ? { text: og['og:description'] } : {}),
        media: [{
          kind: og['og:video'] ? 'video' : 'image',
          url,
          fetchHeaders: await tiktokHeaders(url),
        }],
      }),
    };
  }

  throw new ResolveError('TikTok would not return that post', 'tiktok', originalUrl);
}

export const tiktok: PlatformSpec = {
  id: 'tiktok',
  label: 'TikTok',
  prefix: 'tiktok',
  canonicalHost: 'www.tiktok.com',
  textPosition: 'below',
  matchesHost: hostMatcher('tiktok.com'),
  // A single opaque segment is a `vm.`/`vt.` share code, not a post path.
  buildOriginalUrl: (rest, search) =>
    /^[A-Za-z0-9]+\/?$/.test(rest)
      ? `https://vm.tiktok.com/${rest.replace(/\/$/, '')}/`
      : `https://www.tiktok.com/${rest}${search}`,
  resolve,
};