siftlode/backend/app/downloads/og.py

"""Server-rendered Open Graph tags for the public /watch/{token} page.

The watch page is a client-side SPA, so a social crawler (facebookexternalhit, Twitterbot, …) that
fetches /watch/{token} would otherwise only see the generic index.html — a blank/greyed link card.
This injects per-video OG/Twitter tags into the served HTML so a shared link unfurls with the
video's title, channel and thumbnail. Real browsers ignore the extra tags and hydrate the SPA as
usual. Password-protected / expired / invalid links fall back to the generic card (no metadata leak).
"""
import html
import re
from pathlib import Path

from sqlalchemy import select
from sqlalchemy.orm import Session

from app.config import settings
from app.downloads import links as linksmod
from app.models import DownloadJob, DownloadLink, MediaAsset

_OG_BLOCK = re.compile(r"<!--OG:START-->.*?<!--OG:END-->", re.DOTALL)


def _tag(prop: str, content: str, attr: str = "property") -> str:
    return f'<meta {attr}="{prop}" content="{html.escape(content, quote=True)}" />'


def _watch_tags(token: str, db: Session) -> str | None:
    """Build the OG/Twitter meta block for a watch token, or None to keep the generic card."""
    link = db.execute(
        select(DownloadLink).where(DownloadLink.token == token)
    ).scalar_one_or_none()
    if link is None or linksmod.is_expired(link):
        return None
    url = f"{settings.app_base}/watch/{token}"
    if link.password_hash:
        # Password-gated: don't leak the title/thumbnail in the unfurl.
        return "\n    ".join(
            [
                "<title>Siftlode</title>",
                _tag("og:title", "Password-protected video"),
                _tag("og:description", "Shared via Siftlode"),
                _tag("og:type", "video.other"),
                _tag("og:url", url),
                _tag("og:site_name", "Siftlode"),
            ]
        )
    job = db.get(DownloadJob, link.job_id)
    asset = db.get(MediaAsset, job.asset_id) if job and job.asset_id else None
    if job is None or asset is None or asset.status != "ready":
        return None
    title = (job.display_name or asset.title or "Video").strip()
    channel = (job.display_uploader or asset.uploader or "").strip()
    # Prefer our self-hosted poster for the link-preview image: a remote thumbnail (Facebook's
    # signed CDN URL especially) expires and isn't reliably fetchable cross-origin by the crawler.
    # (This block only runs for non-password links, so the poster needs no grant.) Fall back to the
    # remote thumbnail only if we somehow have no poster.
    image = (
        f"{settings.app_base}/api/public/watch/{token}/poster.jpg"
        if asset.poster_path
        else asset.thumbnail_url
    )
    tags = [
        f"<title>{html.escape(title)}</title>",
        _tag("og:title", title),
        _tag("og:description", channel or "Shared via Siftlode"),
        _tag("og:type", "video.other"),
        _tag("og:url", url),
        _tag("og:site_name", "Siftlode"),
        _tag("twitter:title", title, attr="name"),
    ]
    if channel:
        tags.append(_tag("twitter:description", channel, attr="name"))
    if image:
        # A real thumbnail → a large image card; without one, a plain (text) card is served.
        tags.append(_tag("og:image", image))
        tags.append(_tag("twitter:card", "summary_large_image", attr="name"))
        tags.append(_tag("twitter:image", image, attr="name"))
    else:
        tags.append(_tag("twitter:card", "summary", attr="name"))
    return "\n    ".join(tags)


def render_watch_html(token: str, index_html: Path, db: Session) -> str | None:
    """Return index.html with the OG block replaced for this watch token, or None to serve the
    generic page unchanged (invalid/expired/not-ready link, or a template without the markers)."""
    tags = _watch_tags(token, db)
    if tags is None:
        return None
    text = index_html.read_text(encoding="utf-8")
    if "<!--OG:START-->" not in text:
        return None
    # A function replacement avoids re.sub interpreting backslashes/group refs in `tags`.
    return _OG_BLOCK.sub(lambda _m: tags, text, count=1)