dvt81's picture
Adding a custom tool to scrape the top news result from the ZeroHedge News feed
25c685e verified
raw
history blame
3.69 kB
from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
from Gradio_UI import GradioUI
from selenium import webdriver
@tool
def get_zh_top_news() -> tuple[str, str]:
"""A tool that retrieves the current top news article's title and URL from www.zerohedge.com.
Returns:
tuple[str, str]: A tuple containing the article title (str) and its URL (str).
Raises:
Exception: If the page fails to load or the expected element is not found.
"""
# Set up Chrome options for headless browsing (optional, improves performance)
chrome_options = Options()
chrome_options.add_argument("--headless") # Run without opening a browser window
chrome_options.add_argument("--disable-gpu") # Disable GPU acceleration in headless mode
# Initialize the Selenium WebDriver (assumes chromedriver is in PATH or specify path via Service)
driver = webdriver.Chrome(options=chrome_options)
try:
# Navigate to ZeroHedge homepage
driver.get("https://www.zerohedge.com")
# Find the top article element using a CSS selector
# Based on ZeroHedge's structure, the top headline is typically the first prominent article
top_article = driver.find_element(By.CSS_SELECTOR, "article .ArticleTeaser_titleLink__mK4rX")
# Extract the title from the text content of the link
article_title = top_article.text.strip()
# Extract the URL from the href attribute
article_link = top_article.get_attribute("href")
# Ensure the link is absolute (ZeroHedge uses relative URLs)
if not article_link.startswith("http"):
article_link = f"https://www.zerohedge.com{article_link}"
return article_title, article_link
except Exception as e:
return "Error: Headline not found", "https://www.zerohedge.com"
finally:
# Always close the browser session to free resources
driver.quit()
@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=[get_zh_top_news,get_current_time_in_timezone,final_answer], ## 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()