industry_research.py

import requests
from bs4 import BeautifulSoup
from transformers import pipeline
import re

# Initialize NLP model for text summarization
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

def get_company_info(url):
    try:
        response = requests.get(url, timeout=5)
        soup = BeautifulSoup(response.text, 'html.parser')
        
        mission = soup.find('div', {'class': 'mission'}).get_text(strip=True) if soup.find('div', {'class': 'mission'}) else "Mission not found"
        description = soup.find('meta', {'name': 'description'})['content'] if soup.find('meta', {'name': 'description'}) else "Description not found"
        
        summary = summarizer(description, max_length=30, min_length=10, do_sample=False)[0]['summary_text']
        
        industry = "Unknown"
        if re.search(r'\b(finance|banking|insurance)\b', summary, re.I):
            industry = "Finance"
        elif re.search(r'\b(retail|ecommerce|shopping)\b', summary, re.I):
            industry = "Retail"
        elif re.search(r'\b(manufacturing|production|supply chain)\b', summary, re.I):
            industry = "Manufacturing"
        
        focus_areas = []
        if "customer" in summary:
            focus_areas.append("customer experience")
        if "operation" in summary or "supply chain" in summary:
            focus_areas.append("operations")
        
        return {"mission": mission, "industry": industry, "focus_areas": focus_areas}
    
    except Exception as e:
        print(f"Error fetching company info: {e}")
        return {"mission": "N/A", "industry": "N/A", "focus_areas": []}