goon/app/extractors/tubes/freshporno.py
https://github.com/goon-foss/goon 642f1ab8b8 Mobile 0.1.9: OTA enable, WebView cookie-dismiss fix, porndoe connector
Mobile / OTA:
- Enable Expo Updates (app.json + AndroidManifest) → api.goon-foss.org
- Bump 0.1.6 → 0.1.9 (build.gradle, app.json, appVersion.ts, main.py /version)
- backend.ts: default public backend auto-connect (no manual login)

WebView fallback fix (PlayerScreen INJECTED_JS):
- Auto-dismiss cookie/consent gates (hqporner et al. blocked kt_player init)
- Context-scoped: only clicks consent buttons inside cookie/gdpr containers
- Retry window for <source>.src polling raised 5→15 ticks (post-dismiss init)

Resolver:
- Series-position + modifier mismatch detector (Episode 2≠4, BTS/unedited)
  → composite_score hard-reject / cap; wired into scene_score + bulk_dedup
- aggregator-mode candidate query: LIMIT 500 + title-match ordering

Connectors:
- porndoe.com browse scraper (JSON-LD VideoObject) — theporndude audit pilot

landing: APK links → goon-v0.1.9.apk

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-22 11:20:57 +02:00

71 lines
2.6 KiB
Python

"""freshporno.org — KVS engine, BEZ `<source>` tagów.
Page używa kt_player (KVS Flash + JS legacy player) — URLs są wewnątrz JavaScript
flashvars JSON (`video_url: 'function/0/<URL>'`) i w `<a href="...?download=true">`
linkach z labelem "MP4 720p" / "MP4 480p".
Bierzemy anchor pattern bo ma WSZYSTKIE quality z explicit labelem (vs flashvars
ma tylko main+alt, max 2 jakości). `<a href="...get_file/...mp4/?download=true...">MP4 <q>p, ...`
Sidebar suggested videos używają `data-preview="...get_file/.../<id>_preview.mp4"` —
inny pattern (nie `<a href>`), więc anchor regex je naturalnie pomija.
CDN token IP-bound do VPS — mobile dostanie 403 na direct, fallback proxy działa.
get_file 302 → `cdn4.freshporno.org/remote_control.php?...&file=<path>` direct mp4
(nie HLS). Type='mp4'.
"""
from __future__ import annotations
import logging
import re
from app.extractors._fetch import fetch_tube_html
from app.extractors._models import StreamSource
log = logging.getLogger(__name__)
# `<a href="<URL>?download=true...">MP4 <quality>p, <size>` — main + alt streams.
_ANCHOR_QUALITY_RE = re.compile(
r'<a\s+[^>]*href="(?P<url>https?://[^"]+/get_file/[^"]+\.mp4/)\?download=true[^"]*"'
r'[^>]*>\s*MP4\s+(?P<q>\d{3,4}p)',
re.IGNORECASE,
)
def extract(page_url: str, *, timeout: float = 60.0) -> list[StreamSource] | None:
html = fetch_tube_html(page_url, timeout=timeout)
seen_keys: set[str] = set()
result: list[StreamSource] = []
for m in _ANCHOR_QUALITY_RE.finditer(html):
url = m.group("url")
quality = m.group("q")
# Dedupe po basename (path bez query string).
basename = url.rstrip("/").split("/")[-1]
if basename in seen_keys:
continue
seen_keys.add(basename)
# `force_proxy=True` (2026-05-20): freshporno get_file 302 → cdn4.freshporno.org
# IP-bound (cv= HMAC token). Mobile direct = 403/SSL fail → fallback proxy
# generuje "mrugnięcie" (user bug 743eefbf "najpierw strona potem video").
# Force_proxy wymusza mobile użycie proxied URL od razu — bez flickera +
# natywny ExoPlayer + quality picker zachowane.
result.append(StreamSource(
link=url, type="mp4", quality=quality,
raw={"force_proxy": True},
))
if not result:
log.info("freshporno: no MP4 anchor matches on %s", page_url)
return None
def _quality_key(s: StreamSource) -> int:
if not s.quality:
return -1
try:
return int(s.quality.rstrip("p"))
except ValueError:
return -1
result.sort(key=_quality_key, reverse=True)
return result