Files
ohm_streaming/app/scrapers/http.py
T
Roman 41566ab5fb v0.1.0 — Réécriture complète de OhmStreaming
Nouvelle version réécrite de zéro : recherche multi-sources (Vostfree,
French-Manga), extraction 2 niveaux, proxy vidéo intégré, streaming/téléchargement
HLS, métadonnées Kitsu, bibliothèque locale, comptes JWT + administration,
découverte fusionnée, indexeur Torznab (Sonarr/Prowlarr).
2026-09-22 10:05:47 +00:00

64 lines
1.8 KiB
Python

"""Client HTTP partagé pour le scraping (httpx async, headers navigateur, retries)."""
import asyncio
import logging
import httpx
from bs4 import BeautifulSoup
from app.config import get_settings
from app.scrapers.base import ScrapeError
logger = logging.getLogger(__name__)
_client: httpx.AsyncClient | None = None
def get_client() -> httpx.AsyncClient:
global _client
if _client is None:
settings = get_settings()
_client = httpx.AsyncClient(
timeout=settings.http_timeout,
follow_redirects=True,
headers={
"User-Agent": settings.user_agent,
"Accept-Language": "fr-FR,fr;q=0.9,en;q=0.8",
},
)
return _client
async def close_client() -> None:
global _client
if _client is not None:
await _client.aclose()
_client = None
async def fetch(
url: str,
*,
referer: str | None = None,
retries: int = 2,
) -> str:
"""GET d'une page avec retries ; lève ScrapeError en cas d'échec définitif."""
headers = {"Referer": referer} if referer else {}
last_error: Exception | None = None
for attempt in range(retries + 1):
try:
response = await get_client().get(url, headers=headers)
response.raise_for_status()
return response.text
except (httpx.HTTPError, httpx.InvalidURL) as exc:
last_error = exc
logger.warning("fetch %s — tentative %d/%d : %s", url, attempt + 1, retries + 1, exc)
if attempt < retries:
await asyncio.sleep(1.0 * (attempt + 1))
raise ScrapeError(f"Échec de récupération de {url} : {last_error}")
async def fetch_soup(url: str, *, referer: str | None = None) -> BeautifulSoup:
html = await fetch(url, referer=referer)
return BeautifulSoup(html, "lxml")