ad0284585b
Goon — self-hosted aggregator for adult-content scene metadata. Indexes scenes from TPDB, StashDB, and 30+ public adult tube sites. Cross-source deduplication via perceptual hash + Levenshtein distance. FastAPI backend + APScheduler worker + React Native (Expo) mobile client. FOSS, ad-free, donation-funded. See README for details.
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
"""PornTrex.com — direct HTML scrape search results.
|
|
|
|
Search: `https://www.porntrex.com/search/<q>/` (single page, brak ?page=).
|
|
Scene URL: `https://www.porntrex.com/video/<id>/<slug>/`
|
|
|
|
Porntrex pagination niespójne między widokami — używamy `?from=<offset>` gdy page>1.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
from app.connectors.direct_scrapers._search_base import BaseSearchScraper
|
|
|
|
|
|
class PornTrexScraper(BaseSearchScraper):
|
|
sitetag = "porntrexcom"
|
|
_search_url_template = "https://www.porntrex.com/search/{query}/"
|
|
_scene_url_re = re.compile(
|
|
r'href="(?P<url>https://www\.porntrex\.com/video/\d+/(?P<slug>[a-z0-9_\-]+))/?"',
|
|
re.IGNORECASE,
|
|
)
|
|
|
|
def search(self, query, *, page=1, limit=None):
|
|
# Porntrex używa offset w URL gdy page > 1: `/search/<q>/?from_videos=<page>`
|
|
if page > 1:
|
|
original = self._search_url_template
|
|
self._search_url_template = f"{original.rstrip('/')}/?from_videos={page}"
|
|
try:
|
|
yield from super().search(query, page=page, limit=limit)
|
|
finally:
|
|
self._search_url_template = original
|
|
else:
|
|
yield from super().search(query, page=page, limit=limit)
|