feat(downloads): store + show a canonical "downloaded from" source URL

Every download now records the clean source page URL and shows it on the
Downloads page (open in a new tab, or copy to clipboard). The worker stores
yt-dlp's canonical webpage_url on the asset (migration 0043 adds
media_assets.source_webpage_url); the serializer prefers it and falls back to a
URL derived from source_kind+source_ref, so YouTube, external YouTube links and
external URLs (e.g. Facebook reels) all get a correct reference, and queued/older
rows work before the worker fills it. Edit clips return null (a clip's source is
the user's own earlier download, not a web page). i18n en/hu/de.

backend/alembic/versions/0043_asset_source_url.py

@@ -0,0 +1,27 @@
+"""canonical source webpage URL on media assets
+
+Revision ID: 0043_asset_source_url
+Revises: 0042_download_links
+Create Date: 2026-07-04
+
+Stores yt-dlp's canonical `webpage_url` for a download's source, so the Downloads page can show a
+clean "downloaded from" reference (copyable + openable). Nullable — filled by the worker on
+extraction; existing/queued rows fall back to a URL derived from source_kind+source_ref.
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0043_asset_source_url"
+down_revision: Union[str, None] = "0042_download_links"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column("media_assets", sa.Column("source_webpage_url", sa.Text(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("media_assets", "source_webpage_url")

backend/app/models.py

@@ -741,6 +741,10 @@ class MediaAsset(Base, TimestampMixin):
     uploader: Mapped[str | None] = mapped_column(String(255))
     upload_date: Mapped[date | None] = mapped_column(Date)
     thumbnail_url: Mapped[str | None] = mapped_column(Text)
+    # yt-dlp's canonical page URL for the source (webpage_url) — the clean "downloaded from"
+    # reference shown on the Downloads page. Null until the worker extracts it (older/queued rows
+    # fall back to a URL derived from source_kind+source_ref).
+    source_webpage_url: Mapped[str | None] = mapped_column(Text)
     error: Mapped[str | None] = mapped_column(Text)
     ref_count: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
     last_access_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))

backend/app/routes/downloads.py

@@ -68,6 +68,20 @@ def resolve_source(raw: str) -> tuple[str, str]:
     raise HTTPException(status_code=400, detail="That doesn't look like a valid video link.")
 
 
+def _reference_url(job: DownloadJob, asset: MediaAsset | None) -> str | None:
+    """The clean "downloaded from" URL for the Downloads page: the canonical page URL yt-dlp
+    recorded, else one derived from source_kind+source_ref (covers queued/older rows before the
+    worker fills it). Returns None for edit derivatives — a clip's source is the user's own earlier
+    download, not a web page, so there's no meaningful external URL to show."""
+    if job.job_kind == "edit":
+        return None
+    if asset is not None and asset.source_webpage_url:
+        return asset.source_webpage_url
+    if job.source_kind in ("youtube", "url"):
+        return service.source_url(job.source_kind, job.source_ref)
+    return None
+
+
 def _serialize(job: DownloadJob, asset: MediaAsset | None) -> dict:
     ready = asset is not None and asset.status == "ready" and bool(asset.rel_path)
     return {
@@ -82,6 +96,7 @@ def _serialize(job: DownloadJob, asset: MediaAsset | None) -> dict:
         "created_at": job.created_at.isoformat() if job.created_at else None,
         "source_kind": job.source_kind,
         "source_ref": job.source_ref,
+        "source_url": _reference_url(job, asset),
         "profile_id": job.profile_id,
         "spec": job.profile_snapshot,
         "display_name": job.display_name,

backend/app/worker.py

@@ -221,6 +221,7 @@ def _fill_asset_meta_early(asset_id: int, info: dict) -> None:
         asset.thumbnail_url = info.get("thumbnail")
         asset.duration_s = int(info["duration"]) if info.get("duration") else None
         asset.upload_date = _parse_upload_date(info.get("upload_date"))
+        asset.source_webpage_url = info.get("webpage_url")
         db.commit()
 
 
@@ -409,6 +410,7 @@ def _download(job_id: int, asset_id: int, source_kind: str, source_ref: str, spe
                 asset.uploader = meta.uploader
                 asset.upload_date = meta.upload_date
                 asset.thumbnail_url = meta.thumbnail_url
+                asset.source_webpage_url = info.get("webpage_url")
                 asset.nfo_written = nfo_ok
                 asset.error = None
                 asset.last_access_at = datetime.now(timezone.utc)