sentiment_analyzer.py

import openai
import requests
import json
import os
from bs4 import BeautifulSoup
from IPython.display import Markdown


api_key= os.getenv("OPENAI_API_KEY")
# OpenAI API Key (Load from environment variable for security)
openai.api_key = api_key  # Replace with your API key or load from env

# User-Agent Headers
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36"
}
class Website:
    """A utility class to scrape and process a website."""

    def __init__(self, url):
        self.url = url
        response = requests.get(url, headers=HEADERS)
        self.body = response.content
        soup = BeautifulSoup(self.body, 'html.parser')
        self.title = soup.title.string if soup.title else "No title found"
        
        if soup.body:
            for irrelevant in soup.body(["script", "style", "img", "input"]):
                irrelevant.decompose()
            self.text = soup.body.get_text(separator="\n", strip=True)
        else:
            self.text = ""
        
        links = [link.get('href') for link in soup.find_all('a')]
        self.links = [link for link in links if link]

    def get_contents(self):
        return f"Webpage Title:\n{self.title}\nWebpage Contents:\n{self.text}\n\n"

link_system_prompt = """
You are provided with a list of links found on a webpage. 
You will decide which links are present trading opportunities. 
Respond in JSON format like this:
{
    "links": [
        {"type": "news article", "url": "https://example.com/news1"},
        {"type": "news article", "url": "https://example.com/news2"}
    ]
}
"""

def get_links_user_prompt(website):
    """Generate a prompt for filtering news article links."""
    user_prompt = f"Here are the links found on {website.url}. Extract only news articles:\n"
    user_prompt += "\n".join(website.links)
    return user_prompt

def get_links(url):
    """Fetch and filter news article links from a webpage."""
    website = Website(url)
    response = openai.chat.completions.create(
        model='gpt-4o-mini',
        messages=[
            {"role": "system", "content": link_system_prompt},
            {"role": "user", "content": get_links_user_prompt(website)}
        ],
        response_format={"type": "json_object"}
    )
    result = response.choices[0].message.content
    return json.loads(result)

def get_all_details(url):
    """Retrieve content from the main page and its news article links."""
    result = f"Landing page:\n{Website(url).get_contents()}\n"
    links = get_links(url)

    for link in links["links"]:
        result += f"\n\n{link['type']}\n"
        result += Website(link["url"]).get_contents()
    
    return result

system_prompt = "You are great at analyzing overall market sentiment."

def get_market_sentiment_prompt(url):
    """Generate a prompt for summarizing recent news articles."""
    user_prompt = '''You are able to gauge the overall market sentiment.for example is overall market is risk off,'the market sentiment is generally riskoff'. here comes the news articles below\n'''
    user_prompt += "Here are the page contents:\n"
    user_prompt += get_all_details(url)
    return user_prompt

def get_sentiment(url):
    """Generate a markdown-formatted news summary."""
    response = openai.chat.completions.create(
        model='gpt-4o-mini',
        messages=[
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": get_market_sentiment_prompt(url)}
        ]
    )
    result = response.choices[0].message.content
    return result  # Return markdown text

# Function to call externally
def fetch_market_sentiment(url):
    """Fetch a summarized news report from a given URL."""
    return get_sentiment(url)