From cb221746576a32c59597d3cf0b7f60e2222a2f90 Mon Sep 17 00:00:00 2001
From: goon-foss <goon-foss@tutamail.com>
Date: Tue, 7 Jul 2026 23:21:59 +0200
Subject: [PATCH] fix(thumbnails): watchporn thumbs at ingest + backfill;
 SceneDetail uses live sxyprn thumb

Two bug-report clusters about missing thumbnails:

1. watchporn scenes had no thumbnail on the list, only appearing after opening
   SceneDetail (which auto-enriches og:image). Coverage was 1.3% (463/36,915).
   The browse scraper never captured a thumbnail. KVS stores the poster at a fixed
   derivable path (contents/videos_screenshots/<id//1000*1000>/<id>/preview.jpg,
   verified 8/8 loading). Scraper now sets thumbnail_url (og:image, else derived);
   backfilled 36,687 existing rows -> 100% coverage.

2. SceneDetail showed no thumb where the list showed one: the mobile detail picks
   the first source with a thumbnail_url (origin ASC often puts sxyprncom first),
   and sxyprn/trafficdeposit stored thumbs rot to 404. The list already swaps those
   for a live resolver (/proxy/sxyprn-thumb/), but the detail builder did not. It
   now applies the same live-resolver swap and nulls other rotting thumbs so the
   detail lands on a working image.

Both backend-only, no OTA needed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 app/api/scenes.py                           | 10 ++++++++++
 app/connectors/direct_scrapers/watchporn.py | 21 ++++++++++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/app/api/scenes.py b/app/api/scenes.py
index c6215f6..a364c7c 100644
--- a/app/api/scenes.py
+++ b/app/api/scenes.py
@@ -647,6 +647,16 @@ def _build_scenes_out_batch(
         ).scalars().all()
         for p in pb_rows:
             out = PlaybackSourceOut.model_validate(p)
+            # sxyprn/trafficdeposit stored thumb rotuje (404 po ~tygodniach). SceneDetail
+            # bierze PIERWSZE źródło z thumbem (origin ASC → sxyprncom często pierwsze), więc
+            # bez tego pokazywał martwy obraz mimo że LISTA używała żywej wersji (report:
+            # "na liście jest miniaturka, w scenie nie"). Podmieniamy na żywy resolver;
+            # inne martwe rotting-thumby zerujemy → mobile bierze kolejne źródło / placeholder.
+            sxy = _sxyprn_thumb_url(p.page_url)
+            if sxy:
+                out.thumbnail_url = sxy
+            elif out.thumbnail_url and _is_rotting_thumb(out.thumbnail_url):
+                out.thumbnail_url = None
             if out.thumbnail_url and _needs_proxy(out.thumbnail_url):
                 out.thumbnail_url = _wrap_image_proxy(out.thumbnail_url, p.page_url)
             if out.animated_thumbnail_url and _needs_proxy(out.animated_thumbnail_url):
diff --git a/app/connectors/direct_scrapers/watchporn.py b/app/connectors/direct_scrapers/watchporn.py
index b95b6e9..078ff69 100644
--- a/app/connectors/direct_scrapers/watchporn.py
+++ b/app/connectors/direct_scrapers/watchporn.py
@@ -34,6 +34,18 @@ _TAG_RE = re.compile(r'href="https://watchporn\.to/tags/([a-z0-9\-]+)/"[^>]*>([^
 _CAT_RE = re.compile(r'href="https://watchporn\.to/categories/([a-z0-9\-]+)/"[^>]*>([^<]+)', re.IGNORECASE)
 _DUR_RE = re.compile(r'"duration"\s*:\s*"([^"]+)"')
 _UPLOAD_RE = re.compile(r'"uploadDate"\s*:\s*"([^"]+)"')
+_VIDEO_ID_RE = re.compile(r"/video/(\d+)/")
+
+
+def _derive_thumb(scene_url: str) -> str | None:
+    """KVS trzyma poster pod stałym wzorem `contents/videos_screenshots/<id//1000*1000>/
+    <id>/preview.jpg` (zweryfikowane). Fallback gdy detail page nie ma og:image, żeby
+    kafelek na liście miał miniaturkę OD RAZU (bez czekania na auto-enrich w SceneDetail)."""
+    m = _VIDEO_ID_RE.search(scene_url)
+    if not m:
+        return None
+    vid = int(m.group(1))
+    return f"{_BASE}/contents/videos_screenshots/{vid // 1000 * 1000}/{vid}/preview.jpg"
 
 
 class WatchPornScraper(BaseBrowseScraper):
@@ -82,6 +94,10 @@ class WatchPornScraper(BaseBrowseScraper):
             seen_t.add(slug)
             tags.append(RawTag(external_id=f"{self.sitetag}:tag:{slug}", name=name, slug=slug))
 
+        thumbnail_url = (
+            meta_content(detail_html, property="og:image") or _derive_thumb(scene_url)
+        )
+
         studio: RawStudio | None = None
         cm = _CAT_RE.search(detail_html)
         if cm:
@@ -102,7 +118,10 @@ class WatchPornScraper(BaseBrowseScraper):
             tags=tags,
             playback_sources=[
                 RawPlaybackSource(
-                    origin=f"tube:{self.sitetag}", page_url=scene_url, duration_sec=duration_sec
+                    origin=f"tube:{self.sitetag}",
+                    page_url=scene_url,
+                    duration_sec=duration_sec,
+                    thumbnail_url=thumbnail_url,
                 )
             ],
         )