- embeds.py: provider detection/rewrite (YouTube, Vimeo, Figma, Maps, Docs, Loom, CodePen, Miro, Spotify, SoundCloud, Twitch, X/Twitter, Pinterest, Office) + resolve_embed/inline_kind/provider; POST /board/api/embed/resolve - editor resolves pasted URLs and caches embed_src (persisted); renderer, public pages and MD/HTML/PDF exports prefer embed_src - og_fetcher.py: robust meta parsing (any attribute order), favicon, injectable transport, network-safe fallback - image lightbox with keyboard nav (arrows/Esc) in editor and public pages - inline PDF/video/audio previews - cover (URL or upload) & page icon endpoints - fix broken editor API paths (/api/pages -> /board/api/pages) for cover, icon, versions, backlinks, import, move and OG metadata - 47 tests in tests/test_v55.py; full suite 444 green; ruff clean - version 5.11.2
279 lines
9.9 KiB
Python
279 lines
9.9 KiB
Python
"""FlowDeck — Media embeds (v5.5.0): provider detection + iframe rewriting.
|
|
|
|
Maps a raw http(s) URL to a provider-specific embed URL so that one generic
|
|
``embed`` block can render YouTube, Vimeo, Figma, Google Maps, Google
|
|
Docs/Sheets/Slides, Loom, CodePen, Miro, Spotify, SoundCloud, Twitch,
|
|
X/Twitter, Pinterest, Microsoft Office docs… exactly like Notion's universal
|
|
embed.
|
|
|
|
Unknown/showable URLs (PDF, images, direct video/audio files, plain http)
|
|
fall back to a plain iframe so the link is still visible inline.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
from urllib.parse import parse_qs, quote, urlparse
|
|
|
|
|
|
def _q(params, key):
|
|
vals = params.get(key)
|
|
return vals[0] if vals else ""
|
|
|
|
|
|
def _host_matches(netloc: str, host: str) -> bool:
|
|
"""True when ``netloc`` is ``host`` or one of its subdomains."""
|
|
netloc = (netloc or "").lower().split(":")[0]
|
|
host = host.lower()
|
|
return netloc == host or netloc.endswith("." + host)
|
|
|
|
|
|
def _embed_youtube(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(r"/(?:v|shorts|embed|live)/([A-Za-z0-9_-]{6,20})", path)
|
|
vid = m.group(1) if m else _q(params, "v")
|
|
if not vid:
|
|
# youtu.be/<id> (short link) — the id is the first path segment.
|
|
seg = path.strip("/").split("/")[0]
|
|
if re.fullmatch(r"[A-Za-z0-9_-]{6,20}", seg or ""):
|
|
vid = seg
|
|
if not vid:
|
|
return None
|
|
start = _q(params, "t") or _q(params, "start")
|
|
frag = f"?start={start}" if start else ""
|
|
return f"https://www.youtube.com/embed/{vid}{frag}"
|
|
|
|
|
|
def _embed_vimeo(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(r"/(\d{6,12})", path)
|
|
if not m:
|
|
return None
|
|
return f"https://player.vimeo.com/video/{m.group(1)}"
|
|
|
|
|
|
def _embed_loom(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(r"/(?:embed/|share/)?([0-9a-f]{32})", path)
|
|
if not m:
|
|
return None
|
|
return f"https://www.loom.com/embed/{m.group(1)}"
|
|
|
|
|
|
def _embed_figma(url: str, path: str, params, ctx: dict) -> str | None:
|
|
clean = url.split("?", 1)[0]
|
|
if "figma.com/file/" not in clean and "figma.com/proto/" not in clean and "figma.com/design/" not in clean:
|
|
return None
|
|
return "https://www.figma.com/embed?embed_host=flowdeck&url=" + quote(clean, safe="")
|
|
|
|
|
|
def _embed_map(url: str, path: str, params, ctx: dict) -> str | None:
|
|
if "google.com/maps" not in url and "maps.app.goo.gl" not in url:
|
|
return None
|
|
return "https://maps.google.com/maps?q=" + quote(url, safe="") + "&output=embed"
|
|
|
|
|
|
def _embed_gdocs(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(
|
|
r"docs\.google\.com/(document|spreadsheets|presentation|forms)/d/([A-Za-z0-9_-]+)", url
|
|
)
|
|
if not m:
|
|
return None
|
|
kind, doc_id = m.group(1), m.group(2)
|
|
if kind == "forms":
|
|
return f"https://docs.google.com/forms/d/{doc_id}/viewform?embedded=true"
|
|
return f"https://docs.google.com/{kind}/d/{doc_id}/preview"
|
|
|
|
|
|
def _embed_codepen(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(r"codepen\.io/([^/]+)/pen/([^/?#]+)", url)
|
|
if not m:
|
|
return None
|
|
return f"https://codepen.io/{m.group(1)}/embed/{m.group(2)}?default-tab=result"
|
|
|
|
|
|
def _embed_miro(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(r"miro\.com/app/(?:board|live-embed)/([^/?#]+)", url)
|
|
if not m:
|
|
return None
|
|
return f"https://miro.com/app/live-embed/{m.group(1)}"
|
|
|
|
|
|
def _embed_spotify(url: str, path: str, params, ctx: dict) -> str | None:
|
|
m = re.search(r"/(track|playlist|album|episode|show|artist)/([A-Za-z0-9]+)", url)
|
|
if not m:
|
|
return None
|
|
return f"https://open.spotify.com/embed/{m.group(1)}/{m.group(2)}"
|
|
|
|
|
|
def _embed_soundcloud(url: str, path: str, params, ctx: dict) -> str | None:
|
|
if "soundcloud.com" not in url:
|
|
return None
|
|
return "https://w.soundcloud.com/player/?url=" + quote(url, safe="") + "&color=%2300aaff"
|
|
|
|
|
|
def _embed_twitch(url: str, path: str, params, ctx: dict) -> str | None:
|
|
if "twitch.tv" not in url:
|
|
return None
|
|
parent = (ctx.get("parent") or "localhost").replace("https://", "").replace("http://", "").split("/")[0]
|
|
video = re.search(r"twitch\.tv/videos/(\d+)", url)
|
|
if video:
|
|
return f"https://player.twitch.tv/?video={video.group(1)}&parent={parent}"
|
|
m = re.search(r"twitch\.tv/([^/?#]+)", url)
|
|
if not m or m.group(1) in ("videos", "directory"):
|
|
return None
|
|
return f"https://player.twitch.tv/?channel={m.group(1)}&parent={parent}"
|
|
|
|
|
|
def _embed_twitter(url: str, path: str, params, ctx: dict) -> str | None:
|
|
if "twitter.com" not in url and "x.com" not in url:
|
|
return None
|
|
m = re.search(r"/status(?:es)?/(\d+)", url)
|
|
if not m:
|
|
return f"https://platform.twitter.com/embed/Tweet.html?url={quote(url, safe='')}"
|
|
return f"https://platform.twitter.com/embed/Tweet.html?id={m.group(1)}"
|
|
|
|
|
|
def _embed_pinterest(url: str, path: str, params, ctx: dict) -> str | None:
|
|
if "pinterest" not in url:
|
|
return None
|
|
return f"https://pinterest.com/pin/embed?url={quote(url, safe='')}"
|
|
|
|
|
|
def _embed_office(url: str, path: str, params, ctx: dict) -> str | None:
|
|
low = url.lower().split("?", 1)[0]
|
|
if low.endswith((".doc", ".docx", ".xls", ".xlsx", ".ppt", ".pptx", ".odt", ".ods", ".odp")):
|
|
return "https://view.officeapps.live.com/op/embed.aspx?src=" + quote(url, safe="")
|
|
if "officeapps.live.com" in low or "sharepoint.com" in low or "1drv.ms" in low:
|
|
return "https://view.officeapps.live.com/op/embed.aspx?src=" + quote(url, safe="")
|
|
return None
|
|
|
|
|
|
def _embed_files(url: str, path: str, params, ctx: dict) -> str | None:
|
|
"""Direct media: PDF/images/videos/audio can live in a plain iframe."""
|
|
return url
|
|
|
|
|
|
# (host, handler) — order matters: more specific hosts first.
|
|
_HANDLERS = (
|
|
("youtube.com", _embed_youtube),
|
|
("youtu.be", _embed_youtube),
|
|
("vimeo.com", _embed_vimeo),
|
|
("loom.com", _embed_loom),
|
|
("figma.com", _embed_figma),
|
|
("docs.google.com", _embed_gdocs),
|
|
("google.com/maps", _embed_map),
|
|
("maps.app.goo.gl", _embed_map),
|
|
("codepen.io", _embed_codepen),
|
|
("miro.com", _embed_miro),
|
|
("open.spotify.com", _embed_spotify),
|
|
("spotify.com", _embed_spotify),
|
|
("soundcloud.com", _embed_soundcloud),
|
|
("twitch.tv", _embed_twitch),
|
|
("twitter.com", _embed_twitter),
|
|
("x.com", _embed_twitter),
|
|
("pinterest.", _embed_pinterest),
|
|
("office.com", _embed_office),
|
|
("officeapps.live.com", _embed_office),
|
|
("sharepoint.com", _embed_office),
|
|
("1drv.ms", _embed_office),
|
|
)
|
|
|
|
|
|
_SCHEME_RE = re.compile(r"^([a-zA-Z][a-zA-Z0-9+.-]*):")
|
|
|
|
|
|
def _parse(url: str):
|
|
raw = url.strip()
|
|
if not raw:
|
|
return None, None, None
|
|
m = _SCHEME_RE.match(raw)
|
|
if m:
|
|
if m.group(1).lower() not in ("http", "https"):
|
|
return None, None, None # mailto:, tel:, javascript:, data:…
|
|
else:
|
|
raw = "https://" + raw
|
|
u = urlparse(raw)
|
|
if u.scheme not in ("http", "https") or not u.netloc:
|
|
return None, None, None
|
|
host = u.hostname or ""
|
|
if "." not in host and host != "localhost":
|
|
return None, None, None # a bare word is not a URL
|
|
return raw, u, parse_qs(u.query)
|
|
|
|
|
|
def embed_src(url: str, *, parent: str = "") -> str | None:
|
|
"""Return the embeddable iframe src for a URL, or None if it can't embed."""
|
|
raw, u, params = _parse(url)
|
|
if raw is None:
|
|
return None
|
|
ctx = {"parent": parent}
|
|
netloc = (u.netloc or "").lower()
|
|
for needle, handler in _HANDLERS:
|
|
if "/" in needle or needle.endswith("."):
|
|
if needle in raw.lower():
|
|
return handler(raw, u.path, params, ctx)
|
|
elif _host_matches(netloc, needle):
|
|
return handler(raw, u.path, params, ctx)
|
|
# Office documents hosted on arbitrary domains.
|
|
office = _embed_office(raw, u.path, params, ctx)
|
|
if office:
|
|
return office
|
|
return _embed_files(raw, u.path, params, ctx)
|
|
|
|
|
|
_IMAGE_EXT = re.compile(r"\.(png|jpe?g|gif|webp|svg|bmp|ico|avif)$", re.I)
|
|
_PDF_EXT = re.compile(r"\.pdf$", re.I)
|
|
_VIDEO_EXT = re.compile(r"\.(mp4|webm|ogg|ogv|mov|m4v)$", re.I)
|
|
_AUDIO_EXT = re.compile(r"\.(mp3|wav|ogg|oga|m4a|flac|aac)$", re.I)
|
|
|
|
|
|
def inline_kind(url: str) -> str | None:
|
|
"""Best inline renderer for a URL: 'iframe' | 'image' | 'pdf' | 'video'
|
|
| 'audio'. Returns None when the URL should open in a new tab."""
|
|
raw, u, _params = _parse(url)
|
|
if raw is None:
|
|
return None
|
|
path = u.path or ""
|
|
if _IMAGE_EXT.search(path):
|
|
return "image"
|
|
if _PDF_EXT.search(path):
|
|
return "pdf"
|
|
if _VIDEO_EXT.search(path):
|
|
return "video"
|
|
if _AUDIO_EXT.search(path):
|
|
return "audio"
|
|
return "iframe"
|
|
|
|
|
|
def provider(url: str) -> str:
|
|
"""Human-readable provider name for a URL (used by the editor)."""
|
|
raw, u, _params = _parse(url)
|
|
if raw is None:
|
|
return ""
|
|
netloc = (u.netloc or "").lower()
|
|
for needle, _handler in _HANDLERS:
|
|
if "/" in needle or needle.endswith("."):
|
|
if needle in raw.lower():
|
|
return needle.split(".")[0].rstrip(".")
|
|
elif _host_matches(netloc, needle):
|
|
name = needle.split(".")[0]
|
|
return "youtube" if name == "youtu" else name
|
|
return ""
|
|
|
|
|
|
def resolve_embed(url: str, *, parent: str = "") -> dict:
|
|
"""Resolve a URL to ``{src, kind, provider}`` for the generic embed block."""
|
|
kind = inline_kind(url)
|
|
return {
|
|
"src": embed_src(url, parent=parent) or "",
|
|
"kind": kind or "",
|
|
"provider": provider(url),
|
|
}
|
|
|
|
|
|
def embed_html(src: str, *, height: int = 520) -> str:
|
|
"""A responsive, borderless iframe for a provider embed URL."""
|
|
return (
|
|
f'<iframe src="{src}" loading="lazy" '
|
|
f'style="width:100%;height:{height}px;border:none;border-radius:8px;background:#000;" '
|
|
f'allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; '
|
|
f'picture-in-picture" allowfullscreen></iframe>'
|
|
)
|