refactor(ingest): rename scraper Source name "pornapp" -> "tube-scraper"

The umbrella Source.name for all direct tube scrapers (deep-crawl, browse-latest,
performer-driven) was "pornapp" — a misleading leftover from the removed external
porn-app API. It read like a dependency on a third-party "pornapp" service; it is
not — these are our own scrapers hitting 25+ tubes directly (kind=scraper,
origin tube:<sitetag>). Renamed to "tube-scraper" via a single SCRAPER_SOURCE_NAME
constant; DB row renamed in place (UPDATE name, same id) so all ingest_runs +
external_records history stays linked. No behavior change — external_id keying
(sitetag:url) and dedup are unaffected.

NOTE: playback_sources.origin "pornapp:<sitetag>" prefix is a separate legacy
format (resolve_playback parses it) and is intentionally left untouched.

Verified on prod: row renamed (0 stray "pornapp"), new runs land on "tube-scraper".

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app/connectors/direct_scrapers/__init__.py

@@ -2,11 +2,15 @@
 
 Każdy scraper hit'uje tube bezpośrednio HTTPm — różne tube'y to różne rate limit
 budgets, więc mogą iść równolegle. Wszystkie feedują sceny do tej samej
-`Source(name='pornapp')` (legacy nazwa — kept for DB compat) z external_id
+`Source(name=SCRAPER_SOURCE_NAME)` z external_id `f"{sitetag}:{url}"`. Resolver
-`f"{sitetag}:{url}"`. Resolver mergeuje idempotentnie po tym kluczu.
+mergeuje idempotentnie po tym kluczu.
 
-Search-based ścieżka (per performer name); category browse'ng przez `categoriesUrl`
+Nazwa źródła: do 2026-06-07 brzmiała `"pornapp"` — myląca pozostałość po usuniętym
-overrides w pornapp connector był specyficzny dla porn-app API i zostanie usunięty.
+zewnętrznym porn-app API (sugerowała zależność od obcego serwisu, której NIE MA —
+to nasze własne direct-scrapery tubów). Przemianowana na `"tube-scraper"`; wiersz
+`sources` zaktualizowany w DB (UPDATE name) więc cała historia ingest_runs została.
+
+Search-based ścieżka (per performer name); category browse'ng przez `categoriesUrl`.
 
 UWAGA — speculative scrapers: większość aggregator + special tubes (xmoviesforyou,
 watchporn, siska, porn4days, porndish, xxxfreewatch, latestleaks, mypornerleak,
@@ -14,6 +18,11 @@ porndittcom, perverzija, fpoxxx, ...) ma URL templates + regex'y oparte na typow
 WordPress conventions. Wymagają post-deploy verification — gdy któryś nie zwraca
 wyników, sprawdź real search HTML + popraw template/regex w odpowiednim pliku.
 """
+# Umbrella Source.name dla wszystkich direct-scraperów (deep-crawl, browse-latest,
+# performer-driven). Rename z legacy "pornapp" 2026-06-07 (mylące — nie ma zależności
+# od zewnętrznego porn-app API).
+SCRAPER_SOURCE_NAME = "tube-scraper"
+
 from app.connectors.direct_scrapers._browse_base import BaseBrowseScraper
 from app.connectors.direct_scrapers.base import BaseDirectTubeScraper
 from app.connectors.direct_scrapers.eporner import EpornerScraper

app/connectors/direct_scrapers/base.py

@@ -8,7 +8,8 @@ from app.connectors.base import RawScene
 
 
 class BaseDirectTubeScraper(abc.ABC):
-    """Kontrakt direct scrapera. Wszystkie scrapery feedują do `Source(name='pornapp')`
+    """Kontrakt direct scrapera. Wszystkie scrapery feedują do
+    `Source(name=SCRAPER_SOURCE_NAME)` ("tube-scraper", rename z "pornapp" 2026-06-07)
     żeby dziedziczyć logikę resolvera + idempotent merge per external_id."""
 
     sitetag: str

app/scheduler/browse_latest.py

@@ -20,7 +20,7 @@ import logging
 import time
 from dataclasses import dataclass
 
-from app.connectors.direct_scrapers import ALL_BROWSE_SCRAPERS
+from app.connectors.direct_scrapers import ALL_BROWSE_SCRAPERS, SCRAPER_SOURCE_NAME
 from app.models.source import SourceKind
 from app.scheduler.performer_driven import _ingest_iter_into_run
 
@@ -46,7 +46,7 @@ def run_browse_latest(*, max_pages: int = 5) -> BrowseCounters:
         try:
             c = _ingest_iter_into_run(
                 source_kind=SourceKind.scraper,
-                source_name="pornapp",
+                source_name=SCRAPER_SOURCE_NAME,
                 run_label=f"browse-latest:{scraper.sitetag}",
                 iterator_factory=lambda s=scraper, mp=max_pages: s.latest_scenes(
                     max_pages=mp

app/scheduler/deep_crawl.py

@@ -22,7 +22,7 @@ import time
 from pathlib import Path
 
 from app.config import get_settings
-from app.connectors.direct_scrapers import ALL_BROWSE_SCRAPERS
+from app.connectors.direct_scrapers import ALL_BROWSE_SCRAPERS, SCRAPER_SOURCE_NAME
 from app.db import session_scope
 from app.ingest import _process_scene, get_or_create_source
 from app.models.source import SourceKind
@@ -112,7 +112,7 @@ def run_deep_crawl(*, pages_per_run: int = 60, sitetags: list[str] | None = None
         end = min(end, cap)
 
     with session_scope() as session:
-        src = get_or_create_source(session, kind=SourceKind.scraper, name="pornapp")
+        src = get_or_create_source(session, kind=SourceKind.scraper, name=SCRAPER_SOURCE_NAME)
         source_id = src.id
 
     counters = {"seen": 0, "new": 0, "updated": 0, "skipped": 0, "errors": 0}

app/scheduler/performer_driven.py

@@ -156,7 +156,7 @@ def run_performer_driven(
         # feedują do `Source(name='pornapp')` (legacy nazwa kept for DB compat) z
         # external_id `f"{sitetag}:{url}"` — resolver mergeuje idempotentnie cross-source.
         if not skip_tubes:
-            from app.connectors.direct_scrapers import ALL_DIRECT_SCRAPERS
+            from app.connectors.direct_scrapers import ALL_DIRECT_SCRAPERS, SCRAPER_SOURCE_NAME
 
             sitetag_filter = set(sitetags or []) or None
             scrapers = [
@@ -168,13 +168,13 @@ def run_performer_driven(
                 scraper = scraper_cls()
                 c = _ingest_iter_into_run(
                     source_kind=SourceKind.scraper,
-                    source_name="pornapp",
+                    source_name=SCRAPER_SOURCE_NAME,
                     run_label=f"performer-driven:direct:{scraper.sitetag}:{target.canonical_name}",
                     iterator_factory=lambda s=scraper, t=target: s.search(
                         t.canonical_name, page=1, limit=50
                     ),
                 )
-                counters.merge("pornapp", c)
+                counters.merge(SCRAPER_SOURCE_NAME, c)
 
         counters.performers_processed += 1
 

scripts/pilot_porndoe_deepcrawl.py

@@ -32,7 +32,8 @@ def main() -> int:
 
     s = PornDoeScraper()
     with session_scope() as session:
-        src = get_or_create_source(session, kind=SourceKind.scraper, name="pornapp")
+        from app.connectors.direct_scrapers import SCRAPER_SOURCE_NAME
+        src = get_or_create_source(session, kind=SourceKind.scraper, name=SCRAPER_SOURCE_NAME)
         source_id = src.id
 
     counters = {"seen": 0, "new": 0, "updated": 0, "skipped": 0, "errors": 0}

scripts/studio_retrofix.py

@@ -80,7 +80,7 @@ def main() -> int:
                     JOIN scenes sc ON sc.id = ser.scene_id
                     JOIN sources s ON s.id = ser.source_id
                     LEFT JOIN studios st ON st.id = sc.studio_id
-                    WHERE s.name = 'pornapp'
+                    WHERE s.name = 'tube-scraper'
                       AND ser.external_id LIKE :prefix
                     ORDER BY sc.id
                     LIMIT :lim