ToCode: post #6033 — TG.ME

async def run(count: int) -> None:
    DATA_DIR.mkdir(parents=True, exist_ok=True)
    semaphore = asyncio.Semaphore(MAX_CONCURRENCY)

    async with httpx.AsyncClient(
        headers={"User-Agent": USER_AGENT},
        follow_redirects=True,
        timeout=30.0,
    ) as client:
        slugs = await collect_slugs(client, count, semaphore)
        if len(slugs) < count:
            print(f"warning: only {len(slugs)} posts found (requested {count})")

        # The slug list is the download queue; the semaphore enforces at most
        # MAX_CONCURRENCY concurrent requests.
        await asyncio.gather(
            *[download_post(client, slug, semaphore) for slug in slugs]
        )

    print(f"done: downloaded {len(slugs)} posts to {DATA_DIR}/")

def build_documents() -> list[dict[str, str]]:
    """Read every ``.md`` file in ``data`` and build Meilisearch documents."""
    docs: list[dict[str, str]] = []
    for path in sorted(DATA_DIR.glob("*.md")):
        content = path.read_text(encoding="utf-8")
        docs.append(
            {
                "id": path.stem,
                "filename": path.name,
                "title": _extract_title(content),