goon-foss/goon
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions 1

fix(watchporn): nowy motyw strony, obsada tylko z bloku castrow, studio z /sites/, chipy jako tagi

Browse source 
Stary globalny regex /models/ gubil prawdziwa obsade (nazwa w spanie, pusty tekst
linku) i dopinal performerow z kart related (srednio 12 na scene). Kategorie
to teraz gatunki, nie studio; tagi bez przedrostka #.
This commit is contained in:
goon-foss 2026-10-13 16:48:25 +02:00
parent cbec97fc79
commit 1ad16ceae9
1 changed files with 55 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
app/connectors/direct_scrapers/watchporn.py
View file

@ -32,6 +32,21 @@ _SCENE_URL_RE = re.compile(r'href="(https://watchporn\.to/video/\d+/[a-z0-9\-]+/
_MODEL_RE = re.compile(r'href="https://watchporn\.to/models/([a-z0-9\-]+)/"[^>]*>([^<]+)', re.IGNORECASE)
_TAG_RE = re.compile(r'href="https://watchporn\.to/tags/([a-z0-9\-]+)/"[^>]*>([^<]+)', re.IGNORECASE)
_CAT_RE = re.compile(r'href="https://watchporn\.to/categories/([a-z0-9\-]+)/"[^>]*>([^<]+)', re.IGNORECASE)
# Nowy motyw od ok. 2026-10-10 (prefiks klas `wp-`). Obsada sceny siedzi TYLKO w bloku
# `<div class="wp-castrow">`, nazwa w `<span class="wp-cast__n">` (nie w tekscie linku),
# a karty "related" ponizej maja wlasne linki `/models/` z nazwa w tekscie. Stary globalny
# regex gubil prawdziwa obsade (pusty tekst linku) i dokladal performerow z kart related:
# srednio 12,5 na scene zamiast 2 (10 do 13.10, 193 sceny). Kategorie to teraz gatunki
# (chipy `wp-vchip`), studio jest w linku `/sites/<slug>/` i w JSON-LD "publisher".
_NEW_THEME_MARK = 'class="wp-vi__panel"'
_CASTROW_RE = re.compile(r'<div class="wp-castrow">(.*?)</div>', re.IGNORECASE | re.DOTALL)
_CAST_RE = re.compile(
r'href="https://watchporn\.to/models/([a-z0-9\-]+)/"[^>]*>.*?<span class="wp-cast__n">([^<]+)</span>',
re.IGNORECASE | re.DOTALL,
)
_CHIPS_RE = re.compile(r'<div class="wp-chips">(.*?)</div>', re.IGNORECASE | re.DOTALL)
_SITE_RE = re.compile(r'href="https://watchporn\.to/sites/([a-z0-9\-]+)/"', re.IGNORECASE)
_PUBLISHER_RE = re.compile(r'"publisher"\s*:\s*\{[^}]*?"name"\s*:\s*"([^"]+)"', re.DOTALL)
_DUR_RE = re.compile(r'"duration"\s*:\s*"([^"]+)"')
_UPLOAD_RE = re.compile(r'"uploadDate"\s*:\s*"([^"]+)"')
_VIDEO_ID_RE = re.compile(r"/video/(\d+)/")
@ -74,9 +89,18 @@ class WatchPornScraper(BaseBrowseScraper):
um = _UPLOAD_RE.search(detail_html)
release_date = _parse_iso_date(um.group(1)) if um else None
new_theme = _NEW_THEME_MARK in detail_html
performers: list[RawPerformer] = []
seen_p: set[str] = set()
for m in _MODEL_RE.finditer(detail_html):
if new_theme:
# Tylko blok obsady; brak bloku = scena bez obsady, NIE wracamy do globalnego
# regexu, bo ten zbiera karty related.
crm = _CASTROW_RE.search(detail_html)
cast_iter = _CAST_RE.finditer(crm.group(1)) if crm else iter(())
else:
cast_iter = _MODEL_RE.finditer(detail_html)
for m in cast_iter:
slug = m.group(1)
name = html.unescape(m.group(2)).strip()
if slug.isdigit() or slug in seen_p or not name:
@ -86,19 +110,38 @@ class WatchPornScraper(BaseBrowseScraper):
tags: list[RawTag] = []
seen_t: set[str] = set()
for m in _TAG_RE.finditer(detail_html):
slug = m.group(1)
name = html.unescape(m.group(2)).strip()
def _add_tag(slug: str, raw_name: str) -> None:
name = html.unescape(raw_name).strip().lstrip("#").strip()
if slug in seen_t or not name:
continue
return
seen_t.add(slug)
tags.append(RawTag(external_id=f"{self.sitetag}:tag:{slug}", name=name, slug=slug))
for m in _TAG_RE.finditer(detail_html):
_add_tag(m.group(1), m.group(2))
if new_theme:
# Kategorie-chipy sceny (Blowjob, MILF...) to gatunki, ida do tagow.
chm = _CHIPS_RE.search(detail_html)
if chm:
for m in _CAT_RE.finditer(chm.group(1)):
_add_tag(m.group(1), m.group(2))
thumbnail_url = (
meta_content(detail_html, property="og:image") or _derive_thumb(scene_url)
)
studio: RawStudio | None = None
if new_theme:
sm = _SITE_RE.search(detail_html)
if sm:
pm = _PUBLISHER_RE.search(detail_html)
cname = html.unescape(pm.group(1)).strip() if pm else sm.group(1).replace("-", " ").title()
if cname:
studio = RawStudio(
external_id=f"{self.sitetag}:studio:{slugify(cname)}", name=cname, slug=slugify(cname)
)
else:
cm = _CAT_RE.search(detail_html)
if cm:
cname = html.unescape(cm.group(2)).strip()