Update tariff_scraper.py

tariff_scraper.py

@@ -1,46 +1,31 @@
 import requests
 from bs4 import BeautifulSoup
 
-def scrape_tariff_data(url="https://iesco.com.pk/index.php/customer-services/tariff-guide"):
-    """
-    Scrapes tariff rates from the IESCO tariff guide page.
-    
-    Parameters:
-        url (str): The URL of the tariff guide page.
-    
-    Returns:
-        dict: A dictionary containing tariff rates for different categories.
-        str: Error message if scraping fails.
-    """
+def scrape_tariff_data(url):
     try:
+        # Fetch the webpage
         response = requests.get(url)
-        response.raise_for_status()  # Raise error for bad responses
+        response.raise_for_status()
         soup = BeautifulSoup(response.text, 'html.parser')
 
-        # Locate the main table containing the tariff data
-        table = soup.find("table")
+        # Find the table containing tariff data
+        table = soup.find("table")  # Adjust this if the table has specific attributes like class or id
         if not table:
-            return "No table found on the page. Please verify the URL."
+            return "Error: Could not find the tariff table on the page."
 
-        # 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:
-            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
+        # Extract table rows
+        rows = table.find_all("tr")
+        if not rows:
+            return "Error: No rows found in the tariff table."
 
-        if not tariff_rates:
-            return "No valid tariff rates found in the table."
+        # Parse table rows and extract data
+        tariff_data = []
+        for row in rows:
+            cells = row.find_all(["td", "th"])  # Include both header and data cells
+            tariff_data.append([cell.get_text(strip=True) for cell in cells])
+
+        # Return the tariff data as a list of lists (rows)
+        return tariff_data
 
-        return tariff_rates
     except Exception as e:
         return f"An error occurred while scraping: {e}"