8c0edbdf7b
Two bug-report fixes (2026-06-07): - sxyprn returns HTTP 200 "Post Not Found" for deleted posts (soft-404), so the extractor returned None → resolve treated it as transient and never marked the source dead, leaving a dead link offered forever. Now raise HosterDead on the marker so resolve marks it dead. - Scene playback sources were ordered alphabetically by origin, so a WebView- fallback hoster (fpoxxx, IP-bound + ad-heavy) ranked above a working native source (freshporno) on the same scene. Add is_vps_blocked_fallback() and sort native-resolve origins ahead of WebView-fallback ones. Verified on prod: sxyprn dead URL → HosterDead; scene sources reorder freshpornoorg before fpoxxx. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
91 lines
3.1 KiB
Python
91 lines
3.1 KiB
Python
"""sxyprn.com — direct stream extractor.
|
|
|
|
Page → `data-vnfo` JSON → URL transform algorytmem boo/ssut51/preda → .vid mp4.
|
|
|
|
Sxyprn URL'e w `data-vnfo` mają format `/cdn/c8/<seg3>/<seg4>/<ts>/<seg6>/<seg7>.vid`
|
|
który wymaga rebuildu zanim CDN zaserwuje video bytes (bez tego endpoint zwraca tylko
|
|
pojedynczy timestamp 10B jako placeholder/probe response). Algorytm z `main2.js`:
|
|
|
|
tmp[1] += "8/" + base64url("<ssut51(tmp[6])>-sxyprn.com-<ssut51(tmp[7])>")
|
|
tmp[5] -= ssut51(tmp[6]) + ssut51(tmp[7]) # preda
|
|
|
|
gdzie ssut51 sumuje cyfry w stringu. Po tym joinujemy → finalny URL serwujący mp4.
|
|
|
|
Każdy fetch strony zwraca FRESH signed URL (różne tokeny i timestamp).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
import json
|
|
import logging
|
|
import re
|
|
|
|
from app.extractors._fetch import fetch_tube_html
|
|
from app.extractors._models import HosterDead, StreamSource
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
|
|
_VNFO_RE = re.compile(r"data-vnfo='([^']+)'")
|
|
|
|
|
|
def _ssut51(s: str) -> int:
|
|
"""Sumuje wszystkie cyfry w stringu."""
|
|
return sum(int(c) for c in s if c.isdigit())
|
|
|
|
|
|
def _boo(ss: int, es: int) -> str:
|
|
"""base64url-safe `<ss>-sxyprn.com-<es>` z `=`→`.`."""
|
|
raw = f"{ss}-sxyprn.com-{es}".encode()
|
|
return (
|
|
base64.b64encode(raw)
|
|
.decode()
|
|
.replace("+", "-")
|
|
.replace("/", "_")
|
|
.replace("=", ".")
|
|
)
|
|
|
|
|
|
def extract(page_url: str, *, timeout: float = 60.0) -> list[StreamSource] | None:
|
|
html = fetch_tube_html(page_url, timeout=timeout)
|
|
# sxyprn soft-404: usunięty post zwraca HTTP 200 ze stroną "Post Not Found"
|
|
# (nie 404), więc bez tego extractor zwracał None → resolve traktował jako
|
|
# transient i NIGDY nie oznaczał źródła dead → user wciąż dostawał martwy link
|
|
# (bug-report 2026-06-07, scena 75aa3316). Raise HosterDead → resolve mark-dead.
|
|
if "Post Not Found" in html:
|
|
raise HosterDead(f"sxyprn {page_url}: post deleted (Post Not Found)")
|
|
m = _VNFO_RE.search(html)
|
|
if not m:
|
|
log.warning("sxyprn: no data-vnfo in %s", page_url)
|
|
return None
|
|
try:
|
|
vnfo = json.loads(m.group(1))
|
|
except json.JSONDecodeError:
|
|
log.warning("sxyprn: bad vnfo JSON in %s", page_url)
|
|
return None
|
|
if not isinstance(vnfo, dict) or not vnfo:
|
|
return None
|
|
|
|
sources: list[StreamSource] = []
|
|
for _pid, src in vnfo.items():
|
|
if not isinstance(src, str) or not src.startswith("/cdn/"):
|
|
continue
|
|
tmp = src.split("/")
|
|
if len(tmp) < 8:
|
|
log.warning("sxyprn: short path (%d segs) %s", len(tmp), src)
|
|
continue
|
|
try:
|
|
s6 = _ssut51(tmp[6])
|
|
s7 = _ssut51(tmp[7])
|
|
tmp[1] += "8" + "/" + _boo(s6, s7)
|
|
tmp[5] = str(int(tmp[5]) - s6 - s7)
|
|
except (ValueError, IndexError) as e:
|
|
log.warning("sxyprn: transform failed for %s: %s", src, e)
|
|
continue
|
|
final_path = "/".join(tmp)
|
|
full = "https://sxyprn.com" + final_path
|
|
sources.append(StreamSource(link=full, type="mp4"))
|
|
|
|
if not sources:
|
|
return None
|
|
return sources
|