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.
68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
"""fullmovies.xxx — direct mp4 sources extractor.
|
|
|
|
Detail page ma `<video class="video-js">` z multiple `<source>` (per quality):
|
|
`<source src='https://www.fullmovies.xxx/get_file/<token>/<dir>/<id>/<id>_2160m.mp4/' type='video/mp4' label="2160p" selected="true">`
|
|
`<source src='.../<id>_720m.mp4/' type='video/mp4' label="720p">`
|
|
`<source src='.../<id>_480m.mp4/' type='video/mp4' label="480p">`
|
|
|
|
URL pattern: `https://www.fullmovies.xxx/get_file/<signed_token>/<dir>/<id>/<id>_<q>m.mp4/`
|
|
- Trailing slash — server odsyła 302 na CDN.
|
|
- `<signed_token>` IP-bound do requester (jak HQPorner /get_file/). Mobile direct = 403.
|
|
- force_proxy=True wymusza wszystko przez goon proxy (proxy follows redirect na CDN).
|
|
|
|
Quality labels: 2160p / 1080p / 720p / 480p / 360p.
|
|
"""
|
|
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__)
|
|
|
|
# Single-quoted attribute (apostrophes inside src=). Quality from `label="<q>"`.
|
|
_SOURCE_RE = re.compile(
|
|
r"""<source\s+src=['"](?P<url>https?://[^'"]+\.mp4/?)['"]"""
|
|
r"""\s+type=['"]video/mp4['"]"""
|
|
r"""\s+label=['"](?P<q>[^'"]+)['"]""",
|
|
re.IGNORECASE,
|
|
)
|
|
|
|
|
|
def extract(page_url: str, *, timeout: float = 60.0) -> list[StreamSource] | None:
|
|
html = fetch_tube_html(page_url, timeout=timeout)
|
|
seen: set[str] = set()
|
|
result: list[StreamSource] = []
|
|
# fullmovies /get_file/ URL ma signed token IP-bound do requester. Bez force_proxy
|
|
# mobile dostaje 403. Proxy follows 302 na CDN.
|
|
proxy_flag = {"force_proxy": True}
|
|
for m in _SOURCE_RE.finditer(html):
|
|
url = m.group("url")
|
|
if url in seen:
|
|
continue
|
|
seen.add(url)
|
|
result.append(
|
|
StreamSource(
|
|
link=url,
|
|
type="mp4",
|
|
quality=m.group("q"),
|
|
referer=f"{page_url}",
|
|
raw=proxy_flag,
|
|
)
|
|
)
|
|
|
|
if not result:
|
|
log.info("fullmovies: no <source> tags on %s", page_url)
|
|
return None
|
|
|
|
# Sort by quality desc (2160p > 1080p > 720p > 480p > 360p)
|
|
def _q(s: StreamSource) -> int:
|
|
try:
|
|
return int((s.quality or "0").rstrip("p"))
|
|
except ValueError:
|
|
return 0
|
|
|
|
result.sort(key=_q, reverse=True)
|
|
return result
|