core/stock_analysis.py

# core/stock_analysis.py

import requests
import json
from datetime import datetime, timedelta
from tradingview_ta import TA_Handler, Interval
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.documents.base import Document
from bs4 import BeautifulSoup
from GoogleNews import GoogleNews
from langchain_core.prompts import PromptTemplate
# New, correct imports:
from langchain.chains import LLMChain
from langchain.chains.combine_documents.stuff import StuffDocumentsChain

def clean_google_news_url(url: str):
    for ext in [".html", ".cms"]:
        if ext in url:
            return url.split(ext)[0] + ext
    return url.split("&")[0]

def get_google_news_documents(query: str, max_articles: int = 10, timeout: int = 10):
    googlenews = GoogleNews(lang="en")
    end_date = datetime.today()
    start_date = end_date - timedelta(days=2)
    googlenews.set_time_range(start_date.strftime("%m/%d/%Y"), end_date.strftime("%m/%d/%Y"))
    googlenews.search(query)
    articles = googlenews.result()

    documents = []
    for article in articles[:max_articles]:
        url = clean_google_news_url(article.get("link"))
        try:
            response = requests.get(url, timeout=timeout, headers={"User-Agent": "Mozilla/5.0"})
            response.raise_for_status()
            soup = BeautifulSoup(response.text, "html.parser")
            paragraphs = soup.find_all("p")
            content = "\n".join([p.get_text(strip=True) for p in paragraphs if p.get_text(strip=True)])
            if content and len(content) > 200:
                doc = Document(
                    page_content=content,
                    metadata={
                        "source": "Google News",
                        "title": article.get("title", ""),
                        "published": article.get("date", ""),
                        "link": url,
                    }
                )
                documents.append(doc)
        except Exception:
            continue
    return documents

def analyze_stock(ticker, llm):
    try:
        handler = TA_Handler(symbol=ticker, screener="india", exchange="NSE", interval=Interval.INTERVAL_1_DAY)
        summary = handler.get_analysis().summary
    except Exception:
        return {"error": "Invalid ticker or failed to fetch trading data"}

    urls = [
        f"https://www.google.com/finance/quote/{ticker}:NSE?hl=en",
        f"https://in.tradingview.com/symbols/NSE-{ticker}/",
        f"https://in.tradingview.com/symbols/NSE-{ticker}/news/",
        f"https://in.tradingview.com/symbols/NSE-{ticker}/minds/"
    ]

    loader = WebBaseLoader(urls)
    web_docs = loader.load()

    news_docs = get_google_news_documents(f"Trending News for {ticker}", max_articles=10)
    docs = web_docs + news_docs

    prompt_template = """You are an expert Stock Market Trader specializing in stock market insights derived from fundamental analysis, analytical trends, profit-based evaluations, news indicators from different sites and detailed company financials. 
    Using your expertise, please analyze the stock based on the provided context below.
    
    Context:
    {input_documents}
    
    Task:
    Summarize the stock based on its historical and current data. Keep it CONCISE & BRIEF.
    Evaluate the stock on the following parameters:
    1. Company Fundamentals: Assess the stock's intrinsic value, growth potential, and financial health.
    2. Current & Future Price Trends: Analyze historical price movements and current price trends.
    3. News and Sentiment: Review recent news articles, press releases, and social media sentiment.
    4. Red Flags: Identify any potential risks or warning signs.
    5. Provide a rating for the stock on a scale of 1 to 10.
    6. Advise if the stock is a good buy for the next 1,5, 10 weeks.
    7. Suggest at what price we need to buy and hold or sell the stock

    PROVIDE THE DETAILS based on just the FACTS present in the document
    PROVIDE THE DETAILS IN an JSON Object. Stick to the below JSON object
    MAKE 100% SURE THAT THE "ticker" value is a valid ticker symbol from the documents from NSE India
    {{
      "stock_summary": {{
        "company_name": "",
        "ticker": "",
        "exchange": "",
        "description": "",
        "current_price": "",
        "market_cap": "",
        "historical_performance": {{
          "5_day": "",
          "1_month": "",
          "6_months": "",
          "1_year": "",
          "5_years": ""
        }}
      }},
      "evaluation_parameters": {{
        "company_fundamentals": {{
          "assessment": "",
          "key_metrics": {{
            "pe_ratio": "",
            "volume":"",
            "revenue_growth_yoy": "",
            "net_income_growth_yoy": "",
            "eps_growth_yoy": "",
            "dividend_yield": "",
            "balance_sheet": "",
            "return_on_capital": ""
          }}
        }},
        "current_and_future_price_trends": {{
          "assessment": "",
          "historical_trends": "",
          "current_trends": "",
          "technical_analysis_notes": "",
          "technical_indicators":""
        }},
        "news_and_sentiment": {{
          "assessment": "",
          "positive_sentiment": [
            "",
            "",
            ""
          ],
          "negative_sentiment": [
            "",
            "",
            ""
          ]
        }},
        "red_flags": [
          {{
            "flag": "",
            "details": ""
          }},
          {{
            "flag": "",
            "details": ""
          }},
          {{
            "flag": "",
            "details": ""
          }}
        ]
      }},
      "overall_rating": {{
        "rating": "ranging from 1 to 10, 1 being low rated, 10 being highly rated",
        "justification": ""
      }},
      "investment_advice": {{
        "next_1_weeks_outlook": "",
        "next_5_weeks_outlook": "",
        "next_10_weeks_outlook": "",
        "price_action_suggestions": {{
          "buy": "",
          "hold": "",
          "sell": ""
        }}
      }}
    }}
    """

    prompt = PromptTemplate.from_template(prompt_template)
    chain = StuffDocumentsChain(llm_chain=LLMChain(llm=llm, prompt=prompt), document_variable_name="input_documents")
    response = chain.invoke({"input_documents": docs})
    raw = response["output_text"].strip()

    # Clean code block markdown if present
    if raw.startswith("```json"):
        raw = raw[len("```json"):]
    if raw.endswith("```"):
        raw = raw[:-3]

    try:
        return json.loads(raw.strip())
    except json.JSONDecodeError:
        return {"error": "Failed to parse model output", "raw": raw}