app.py

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
import httpx
import json
import asyncio
from datetime import datetime, timedelta

app = FastAPI()

app.add_middleware(
    CORSMiddleware,
    allow_origins=["https://collectionsdarchitectes.fr"],
    allow_methods=["GET"],
    allow_headers=["*"],
)

TRUSTPILOT_URL = "https://www.trustpilot.com/review/collectionsdarchitectes.fr"
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"

cache = {"data": None, "expires": None}


async def fetch_reviews():
    now = datetime.utcnow()
    if cache["data"] and cache["expires"] and now < cache["expires"]:
        return cache["data"]

    async with httpx.AsyncClient() as client:
        r = await client.get(TRUSTPILOT_URL, headers={"User-Agent": USER_AGENT}, follow_redirects=True)

    html = r.text
    marker = '__NEXT_DATA__'
    start = html.find(marker)
    if start == -1:
        return cache.get("data") or {"error": "Could not parse Trustpilot page"}

    start = html.find('>', start) + 1
    end = html.find('</script>', start)
    raw = html[start:end]

    data = json.loads(raw)
    props = data.get("props", {}).get("pageProps", {})
    biz = props.get("businessUnit", {})
    reviews = props.get("reviews", [])

    result = {
        "score": biz.get("trustScore"),
        "total": biz.get("numberOfReviews"),
        "reviews": [
            {
                "id": r.get("id"),
                "stars": r.get("rating"),
                "title": r.get("title"),
                "text": r.get("text"),
                "author": r.get("consumer", {}).get("displayName"),
                "date": r.get("dates", {}).get("publishedDate"),
            }
            for r in reviews
        ],
    }

    cache["data"] = result
    cache["expires"] = now + timedelta(hours=24)
    return result


@app.get("/reviews")
async def get_reviews():
    return await fetch_reviews()