Les vraies SERP Google pour vos agents et vos LLM

{
  "searches_done": 6,
  "with_ai_overview": 5,
  "domains_total": 31,
  "domains": [
    {"domain": "ikea.com", "keywords_count": 2, "mentions": 3, "keywords": ["comment nettoyer un canapé en tissu", "quelle taille de canapé pour un salon"]},
    {"domain": "youtube.com", "keywords_count": 1, "mentions": 8, "keywords": ["comment choisir un matelas"]},
    {"domain": "maisonsdumonde.com", "keywords_count": 1, "mentions": 5, "keywords": ["comment nettoyer un canapé en tissu"]},
    {"domain": "monsieur-meuble.com", "keywords_count": 1, "mentions": 4, "keywords": ["comment nettoyer un canapé en tissu"]},
    {"domain": "maisondelaliterie.fr", "keywords_count": 1, "mentions": 3, "keywords": ["comment choisir un matelas"]}
  ]
}

import time
import requests

API = "https://api.semscraper.com/v1/serp"
HEADERS = {"Authorization": "Bearer API_KEY"}
question = "meilleur crm pour pme"

# 1. la SERP Google de la question
job = requests.post(API, headers=HEADERS, json=[{"search_engine": "google_search",
    "keyword": question, "device": "desktop", "location": "fr", "language": "fr", "depth": 1}]).json()
serp_id = job["data"][0]["id"]
serp = {"status": "pending"}
while serp["status"] != "done":
    time.sleep(10)
    serp = requests.get(API, headers=HEADERS, params={"ids": serp_id, "output": "json"}).json()["data"][0]

# 2. les sources que Google met en avant
urls = [item["url"] for block in serp["results"] if block["type"] == "organic" for item in block["items"][:3]]

# 3. leur contenu, lu par votre propre outil, puis votre LLM
pages = [fetch_page(url) for url in urls]
answer = llm.ask(question, context=pages, sources=urls)