from flask import Flask, request, jsonifyapp = Flask(__name__)@app.route("/webhook/browse-ai", methods=["POST"])
def handle_webhook():
    event = request.json    if event.get("event") != "taskFinishedSuccessfully":
        return jsonify({"status": "ignored"}), 200    task = event.get("task", {})
    captured_data = task.get("capturedTexts", {})    # Process with your chosen LLM (see provider examples below)
    result = process_with_llm(captured_data)    # Do something with the result
    save_result(task.get("id"), result)    return jsonify({"status": "processed"}), 200if __name__ == "__main__":
    app.run(port=5000)

# pip install openai
from openai import OpenAI
import jsonclient = OpenAI(api_key="your-openai-api-key")def process_with_llm(data):
    response = client.chat.completions.create(
        model="gpt-4o",  # or "gpt-4o-mini" for faster/cheaper
        messages=[
            {"role": "system", "content": "You are a data analysis assistant. Respond with valid JSON only."},
            {"role": "user", "content": f"""Analyze this scraped data and return:
{{"summary": "one sentence", "category": "category", "sentiment": "positive|neutral|negative"}}Data: {json.dumps(data)}"""}
        ],
        response_format={"type": "json_object"}  # Enforces JSON output
    )
    return json.loads(response.choices[0].message.content)

# pip install google-generativeai
import google.generativeai as genai
import jsongenai.configure(api_key="your-gemini-api-key")
model = genai.GenerativeModel("gemini-2.0-flash")def process_with_llm(data):
    response = model.generate_content(
        f"""Analyze this scraped data and return a JSON object with:
- "summary": one sentence summary
- "category": primary category
- "sentiment": positive, neutral, or negativeRespond with valid JSON only, no other text.Data: {json.dumps(data)}"""
    )
    return json.loads(response.text)

# pip install mistralai
from mistralai import Mistral
import jsonclient = Mistral(api_key="your-mistral-api-key")def process_with_llm(data):
    response = client.chat.complete(
        model="mistral-large-latest",  # or "mistral-small-latest" for faster/cheaper
        messages=[
            {"role": "system", "content": "You are a data analysis assistant. Respond with valid JSON only."},
            {"role": "user", "content": f"""Analyze this scraped data and return:
{{"summary": "one sentence", "category": "category", "sentiment": "positive|neutral|negative"}}Data: {json.dumps(data)}"""}
        ],
        response_format={"type": "json_object"}
    )
    return json.loads(response.choices[0].message.content)

# pip install groq
from groq import Groq
import jsonclient = Groq(api_key="your-groq-api-key")def process_with_llm(data):
    response = client.chat.completions.create(
        model="llama-3.3-70b-versatile",
        messages=[
            {"role": "system", "content": "You are a data analysis assistant. Respond with valid JSON only."},
            {"role": "user", "content": f"""Analyze this scraped data and return:
{{"summary": "one sentence", "category": "category", "sentiment": "positive|neutral|negative"}}Data: {json.dumps(data)}"""}
        ],
        response_format={"type": "json_object"}
    )
    return json.loads(response.choices[0].message.content)

import requests, json, timeBROWSE_AI_API_KEY = "your-browse-ai-api-key"
ROBOT_ID = "your-robot-id"def get_recent_tasks(robot_id):
    response = requests.get(
        f"https://api.browse.ai/v2/robots/{robot_id}/tasks",
        headers={"Authorization": f"Bearer {BROWSE_AI_API_KEY}"},
        params={"page": 1}
    )
    return response.json().get("result", {}).get("robotTasks", {}).get("items", [])def batch_process():
    tasks = get_recent_tasks(ROBOT_ID)
    results = []    for task in tasks:
        if task.get("status") != "successful":
            continue        captured = task.get("capturedTexts", {})
        if not captured:
            continue        # Use any provider's process_with_llm function here
        result = process_with_llm(captured)
        results.append({"task_id": task["id"], "result": result})        time.sleep(1)  # Respect rate limits    return resultsresults = batch_process()
for r in results:
    print(f"Task {r['task_id']}: {r['result']}")