leetcode/apps/cli/videos.ts

#!/usr/bin/env bun
/**
 * Find the NeetCode explanation video for every docs page that has none.
 *
 * A finished solution page carries frontmatter `video: <YouTube id>` —
 * NeetCode's walkthrough of the problem — which the docs MDX `wrapper`
 * (`apps/docs/components/ProblemBadges.astro`) renders as the red
 * "Explanation" badge beside the topic badges. `sync.ts` never writes that key
 * (it owns `icon:`, `topics:` and `## Solution`), so pages accumulate without
 * one. This script lists every numbered page lacking `video:` and looks each
 * up on NeetCode's two channels, main channel first, accepting only a title
 * that names the page's exact LC number (`… - Leetcode 226 - …`) and is not a
 * #short. No YouTube API key: the channel search page embeds its results as
 * `ytInitialData` JSON, which is all we parse. Ranking is the channel's own —
 * the first exact-number match wins.
 *
 *   bun apps/cli/videos.ts           # report: page → video (or "no match")
 *   bun apps/cli/videos.ts --write   # also add `video:` to the frontmatter
 *
 * --write inserts the key before `sidebar:`. A page with no match is left
 * untouched, so re-runs are no-ops once every page has its video.
 */
import { join } from "node:path";

import { printTable } from "./report.ts";
import { ROOT } from "./work.ts";

const DOCS = join(ROOT, "apps", "docs", "content");
const WRITE = process.argv.includes("--write");

/** Channel handles searched in order; the first exact match wins. */
const CHANNELS = ["NeetCode", "NeetCodeIO"] as const;

interface Video {
  id: string;
  title: string;
  channel: string;
}

// ── YouTube channel search (no API key) ──────────────────────────

const HEADERS = { "accept-language": "en-US,en;q=0.9", "user-agent": "Mozilla/5.0" };

/**
 * The `var ytInitialData = {…};</script>` blob of a YouTube page, parsed.
 * YouTube intermittently answers 200 with a page that lacks the blob or cuts
 * it short, so a bad page is retried a few times before it is an error.
 */
async function initialData(url: string): Promise<unknown> {
  let reason = "";
  for (let attempt = 0; attempt < 3; attempt++) {
    if (attempt) await Bun.sleep(500 * attempt);
    const res = await fetch(url, { headers: HEADERS });
    if (!res.ok) {
      reason = `status ${res.status}`;
      continue;
    }
    const html = await res.text();
    // Slice rather than regex: the blob is ~1 MB, and a lazy `.*?` across it
    // is what made the first cut of this script fail at random.
    const open = html.search(/ytInitialData\s*=\s*\{/);
    const close = open === -1 ? -1 : html.indexOf("</script>", open);
    if (close === -1) {
      reason = `no ytInitialData in ${html.length}-byte page`;
      continue;
    }
    try {
      return JSON.parse(html.slice(html.indexOf("{", open), close).replace(/;\s*$/, ""));
    } catch {
      reason = "truncated ytInitialData";
    }
  }
  throw new Error(`GET ${url} -> ${reason}`);
}

/** Every videoRenderer in a channel search page, in the page's own order. */
async function channelSearch(channel: string, query: string): Promise<Video[]> {
  const url = `https://www.youtube.com/@${channel}/search?query=${encodeURIComponent(query)}`;
  const data = await initialData(url);

  const videos: Video[] = [];
  const walk = (node: unknown): void => {
    if (!node || typeof node !== "object") return;
    if ("videoRenderer" in node) {
      const v = node.videoRenderer;
      if (v && typeof v === "object" && "videoId" in v && typeof v.videoId === "string") {
        const runs =
          "title" in v && v.title && typeof v.title === "object" && "runs" in v.title
            ? v.title.runs
            : undefined;
        const title = Array.isArray(runs)
          ? runs.map((r) => (r && typeof r === "object" && "text" in r ? String(r.text) : "")).join("")
          : "";
        videos.push({ id: v.videoId, title, channel });
      }
      return;
    }
    for (const child of Object.values(node)) walk(child);
  };
  walk(data);
  return videos;
}

/** The LC number a NeetCode title names (`… - Leetcode 226 - …`), if any. */
function titledNumber(title: string): number | undefined {
  const m = title.match(/\bleetcode\s*#?\s*(\d+)\b/i);
  return m ? Number(m[1]) : undefined;
}

async function findVideo(num: number): Promise<Video | undefined> {
  for (const channel of CHANNELS) {
    const hit = (await channelSearch(channel, `leetcode ${num}`)).find(
      (v) => titledNumber(v.title) === num && !/#shorts\b/i.test(v.title),
    );
    if (hit) return hit;
  }
  return undefined;
}

// ── docs pages ───────────────────────────────────────────────────

interface Page {
  num: number;
  rel: string;
  text: string;
}

/** The page's frontmatter block, `---` to `---`. */
const FRONTMATTER = /^---\n[\s\S]*?\n---/;

/** Numbered solution pages without a `video:` key, by LC number. */
async function pagesMissingVideo(): Promise<Page[]> {
  const pages: Page[] = [];
  for (const rel of await Array.fromAsync(new Bun.Glob("**/*.mdx").scan(DOCS))) {
    const text = await Bun.file(join(DOCS, rel)).text();
    const t = text.match(/^title: '(\d+)\./m);
    const fm = text.match(FRONTMATTER)?.[0] ?? "";
    if (t && !/^video:/m.test(fm)) pages.push({ num: Number(t[1]), rel, text });
  }
  return pages.sort((a, b) => a.num - b.num);
}

// ── main ─────────────────────────────────────────────────────────

const missing = await pagesMissingVideo();
if (missing.length === 0) {
  console.log("every solution page has a video");
  process.exit(0);
}

const rows: string[][] = [["docs page", "video", "title", WRITE ? "status" : ""]];
let found = 0;
for (const page of missing) {
  const video = await findVideo(page.num);
  if (!video) {
    rows.push([page.rel, "—", "no NeetCode match", WRITE ? "skipped" : ""]);
    continue;
  }
  found++;
  let status = "";
  if (WRITE) {
    const next = page.text.replace(FRONTMATTER, (fm) => fm.replace(/^sidebar:$/m, `video: ${JSON.stringify(video.id)}\nsidebar:`));
    await Bun.write(join(DOCS, page.rel), next);
    status = "written";
  }
  rows.push([page.rel, `https://youtu.be/${video.id}`, `${video.title} (${video.channel})`, status]);
}

if (!WRITE) for (const row of rows) row.pop();
printTable(rows);
console.log(`\n${found}/${missing.length} page(s) matched${WRITE ? `, ${found} written` : ""}`);