Update tariff_scraper.py

tariff_scraper.py

@@ -3,14 +3,13 @@ from bs4 import BeautifulSoup
 
 def scrape_tariff_data(url="https://iesco.com.pk/index.php/customer-services/tariff-guide"):
     """
-    Scrapes tariff data from the IESCO tariff guide page.
+    Scrapes tariff rates from the IESCO tariff guide page.
     
     Parameters:
-        url (str): The URL of the tariff data page.
-                  Defaults to the IESCO Tariff Guide page.
+        url (str): The URL of the tariff guide page.
     
     Returns:
-        list: A list of rows containing tariff-related data as strings.
+        dict: A dictionary containing tariff rates for different categories.
         str: Error message if scraping fails.
     """
     try:
@@ -18,22 +17,30 @@ def scrape_tariff_data(url="https://iesco.com.pk/index.php/customer-services/tar
         response.raise_for_status()  # Raise error for bad responses
         soup = BeautifulSoup(response.text, 'html.parser')
 
-        # Assuming the tariff data is stored in table rows
-        table = soup.find("table")  # Locate the main table
+        # Locate the main table containing the tariff data
+        table = soup.find("table")
         if not table:
             return "No table found on the page. Please verify the URL."
 
-        table_rows = table.find_all("tr")  # Extract all table rows
-        scraped_data = []
-        
+        # Extract tariff data into a dictionary
+        tariff_rates = {}
+        table_rows = table.find_all("tr")  # Get all rows in the table
         for row in table_rows:
-            row_data = [cell.get_text(strip=True) for cell in row.find_all(["th", "td"])]
-            if row_data:  # Only add rows with data
-                scraped_data.append(" | ".join(row_data))
+            cells = row.find_all("td")
+            if len(cells) >= 2:  # Ensure row has enough columns (category and rate)
+                category = cells[0].get_text(strip=True)
+                rate = cells[1].get_text(strip=True)
+                
+                # Parse rate into a float
+                try:
+                    rate_value = float(rate.replace(",", "").split()[0])  # Clean and parse rate
+                    tariff_rates[category] = rate_value
+                except ValueError:
+                    continue  # Skip rows with invalid rate values
 
-        if not scraped_data:
-            return "No tariff data found in the table. Please check the page structure."
+        if not tariff_rates:
+            return "No valid tariff rates found in the table."
 
-        return scraped_data
+        return tariff_rates
     except Exception as e:
         return f"An error occurred while scraping: {e}"