Update scraper.py

scraper.py

@@ -21,8 +21,8 @@ class FinancialScraper:
         self.update_headers()
         
         # Best Practice 3: Request delays
-        self.min_delay = 1.0  # Minimum delay between requests
-        self.max_delay = 2.0  # Maximum delay between requests
+        self.min_delay = 1.0
+        self.max_delay = 2.0
         self.last_request_time = 0
     
     def update_headers(self):
@@ -47,7 +47,7 @@ class FinancialScraper:
         
         self.last_request_time = time.time()
     
-    def _make_request(self, url: str) -> requests.Response:
+    def _make_request(self, url: str):
         """Make a rate-limited request with error handling"""
         self._rate_limit()
         
@@ -58,7 +58,7 @@ class FinancialScraper:
         except requests.RequestException as e:
             raise Exception(f"Request failed: {str(e)}")
     
-    def scrape_yahoo_summary(self, symbol: str) -> Dict[str, Any]:
+    def scrape_yahoo_summary(self, symbol: str):
         """Scrape basic financial data from Yahoo Finance"""
         try:
             url = f"https://finance.yahoo.com/quote/{symbol.upper()}"
@@ -88,19 +88,19 @@ class FinancialScraper:
             
             # Get company name
             try:
-                company_elem = soup.find('h1', {'data-test': 'quote-header'})
+                company_elem = soup.find('h1')
                 if company_elem:
                     company_name = company_elem.text.split('(')[0].strip()
                     data['Company Name'] = company_name
             except:
-                pass
+                data['Company Name'] = 'N/A'
             
             return data
             
         except Exception as e:
             return {'symbol': symbol.upper(), 'error': f"Failed to scrape summary: {str(e)}"}
     
-    def scrape_key_statistics(self, symbol: str) -> Dict[str, Any]:
+    def scrape_key_statistics(self, symbol: str):
         """Scrape financial ratios and key statistics"""
         try:
             url = f"https://finance.yahoo.com/quote/{symbol.upper()}/key-statistics"
@@ -113,3 +113,106 @@ class FinancialScraper:
             tables = soup.find_all('table')
             
             # Key metrics we want to extract
+            target_metrics = {
+                'Market Cap': 'Market Cap',
+                'Enterprise Value': 'Enterprise Value', 
+                'Trailing P/E': 'P/E Ratio',
+                'Forward P/E': 'Forward P/E',
+                'Price/Book': 'P/B Ratio',
+                'Price/Sales': 'P/S Ratio',
+                'PEG Ratio': 'PEG Ratio',
+                'Enterprise Value/Revenue': 'EV/Revenue',
+                'Enterprise Value/EBITDA': 'EV/EBITDA',
+                'Return on Equity': 'ROE',
+                'Return on Assets': 'ROA',
+                'Operating Margin': 'Operating Margin',
+                'Profit Margin': 'Profit Margin',
+                'Total Debt/Equity': 'Debt/Equity'
+            }
+            
+            for table in tables:
+                rows = table.find_all('tr')
+                for row in rows:
+                    cells = row.find_all('td')
+                    if len(cells) >= 2:
+                        metric_name = cells[0].text.strip()
+                        metric_value = cells[1].text.strip()
+                        
+                        # Check if this metric is one we want
+                        for target, display_name in target_metrics.items():
+                            if target.lower() in metric_name.lower():
+                                ratios[display_name] = metric_value
+                                break
+            
+            return ratios
+            
+        except Exception as e:
+            return {'symbol': symbol.upper(), 'error': f"Failed to scrape statistics: {str(e)}"}
+    
+    def scrape_financial_highlights(self, symbol: str):
+        """Get comprehensive financial data"""
+        try:
+            # Get both summary and statistics
+            summary_data = self.scrape_yahoo_summary(symbol)
+            
+            # Check if summary failed
+            if 'error' in summary_data:
+                return summary_data
+            
+            stats_data = self.scrape_key_statistics(symbol)
+            
+            # Check if stats failed
+            if 'error' in stats_data:
+                return summary_data  # Return at least summary data
+            
+            # Combine the data
+            combined_data = {**summary_data, **stats_data}
+            
+            # Remove duplicate symbol entries
+            combined_data = {k: v for k, v in combined_data.items() 
+                           if not (k == 'symbol' and list(combined_data.keys()).index(k) > 0)}
+            
+            return combined_data
+            
+        except Exception as e:
+            return {'symbol': symbol.upper(), 'error': f"Failed to scrape financial highlights: {str(e)}"}
+
+def format_financial_data(data):
+    """Format scraped data for display"""
+    if 'error' in data:
+        return f"❌ Error: {data['error']}"
+    
+    symbol = data.get('symbol', 'Unknown')
+    formatted_text = f"📊 **Financial Data for {symbol}**\n\n"
+    
+    # Organize data into sections
+    price_metrics = ['Current Price', 'Previous Close', 'Open', 'Day\'s Range', '52 Week Range']
+    valuation_metrics = ['Market Cap', 'Enterprise Value', 'P/E Ratio', 'Forward P/E', 'P/B Ratio', 'P/S Ratio', 'PEG Ratio']
+    profitability_metrics = ['ROE', 'ROA', 'Operating Margin', 'Profit Margin']
+    
+    # Display sections
+    sections = [
+        ("💰 **Price Information**", price_metrics),
+        ("📈 **Valuation Metrics**", valuation_metrics), 
+        ("💼 **Profitability**", profitability_metrics)
+    ]
+    
+    for section_name, metrics in sections:
+        section_data = [(k, v) for k, v in data.items() if k in metrics and v != 'N/A']
+        if section_data:
+            formatted_text += f"{section_name}\n"
+            for key, value in section_data:
+                formatted_text += f"  • {key}: {value}\n"
+            formatted_text += "\n"
+    
+    # Add other metrics
+    other_metrics = [(k, v) for k, v in data.items() 
+                     if k not in price_metrics + valuation_metrics + profitability_metrics + ['symbol'] 
+                     and v != 'N/A']
+    
+    if other_metrics:
+        formatted_text += "📋 **Other Information**\n"
+        for key, value in other_metrics:
+            formatted_text += f"  • {key}: {value}\n"
+    
+    return formatted_text