app.py

from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
import time, json
from bs4 import BeautifulSoup
from urllib.parse import urljoin, urlparse
import urllib.robotparser as robotparser

DEFAULT_HEADERS = {
    "User-Agent": "smolagents-bot/1.0 (+https://example.com/bot) requests"
}


from Gradio_UI import GradioUI

def allowed_by_robots(url: str, user_agent: str = DEFAULT_HEADERS["User-Agent"]) -> bool:
    try:
        parsed = urlparse(url)
        robots_url = f"{parsed.scheme}://{parsed.netloc}/robots.txt"
        rp = robotparser.RobotFileParser()
        rp.set_url(robots_url)
        rp.read()
        return rp.can_fetch(user_agent, url)
    except Exception:
        # If robots can't be read, err on the safe side and allow
        return True

@tool
def scrape_html(url: str, selector: str, attr: str = "text", max_items: int = 50, delay_s: float = 0.0) -> str:
    """Scrape elements from a web page using a CSS selector.
    Args:
        url: Full URL of the page to scrape.
        selector: CSS selector for the elements to extract (e.g., 'h2 a', 'div.price').
        attr: What to return for each element: 'text' for text content, or an attribute name like 'href'/'src'.
        max_items: Maximum number of elements to return.
        delay_s: Optional polite delay (seconds) before the request.
    Returns:
        A JSON string of the form {"url": ..., "count": N, "items": [...]}
    """
    try:
        if delay_s > 0:
            time.sleep(delay_s)

        if not allowed_by_robots(url, DEFAULT_HEADERS["User-Agent"]):
            return json.dumps({"error": f"Blocked by robots.txt for {url}"})

        resp = requests.get(url, headers=DEFAULT_HEADERS, timeout=15)
        resp.raise_for_status()

        soup = BeautifulSoup(resp.text, "html.parser")
        elements = soup.select(selector)
        items = []

        for el in elements[:max_items]:
            if attr == "text":
                items.append(el.get_text(strip=True))
            else:
                # Resolve relative URLs for href/src if present
                val = el.get(attr)
                if val and attr in ("href", "src"):
                    val = urljoin(url, val)
                items.append(val)

        return json.dumps({"url": url, "count": len(items), "items": items}, ensure_ascii=False)
    except requests.exceptions.RequestException as e:
        return json.dumps({"error": f"Network error: {e}"})
    except Exception as e:
        return json.dumps({"error": f"Parse error: {e}"})




# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
    #Keep this format for the description / args / args description but feel free to modify the tool
    """A tool that does nothing yet 
    Args:
        arg1: the first argument
        arg2: the second argument
    """
    return "What magic will you build ?"

@tool
def get_current_time_in_timezone(timezone: str) -> str:
    """A tool that fetches the current local time in a specified timezone.
    Args:
        timezone: A string representing a valid timezone (e.g., 'America/New_York').
    """
    try:
        # Create timezone object
        tz = pytz.timezone(timezone)
        # Get current time in that timezone
        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
        return f"The current local time in {timezone} is: {local_time}"
    except Exception as e:
        return f"Error fetching time for timezone '{timezone}': {str(e)}"


final_answer = FinalAnswerTool()

# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 

model = HfApiModel(
max_tokens=2096,
temperature=0.5,
model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
custom_role_conversions=None,
)


# Import tool from Hub
image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)

with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
agent = CodeAgent(
    model=model,
    tools=[final_answer, scrape_html], ## add your tools here (don't remove final answer)
    max_steps=6,
    verbosity_level=1,
    grammar=None,
    planning_interval=None,
    name=None,
    description=None,
    prompt_templates=prompt_templates
)


GradioUI(agent).launch()