Update tariff_scraper.py

tariff_scraper.py

@@ -1,25 +1,39 @@
 import requests
 from bs4 import BeautifulSoup
 
-def scrape_tariff_data(url):
+def scrape_tariff_data(url="https://iesco.com.pk/index.php/customer-services/tariff-guide"):
+    """
+    Scrapes tariff data from the IESCO tariff guide page.
+    
+    Parameters:
+        url (str): The URL of the tariff data page.
+                  Defaults to the IESCO Tariff Guide page.
+    
+    Returns:
+        list: A list of rows containing tariff-related data as strings.
+        str: Error message if scraping fails.
+    """
     try:
-        response = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
-        response.raise_for_status()
+        response = requests.get(url)
+        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
+        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 = []
         
-        # Find all tables in the webpage
-        tariff_sections = soup.find_all('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))
+
+        if not scraped_data:
+            return "No tariff data found in the table. Please check the page structure."
 
-        # Extract data row by row
-        data = []
-        for section in tariff_sections:
-            table_rows = section.find_all('tr')
-            for row in table_rows:
-                row_text = ' | '.join(
-                    col.get_text(strip=True) for col in row.find_all(['th', 'td'])
-                )
-                if row_text:
-                    data.append(row_text)
-        return data
+        return scraped_data
     except Exception as e:
-        return f"An error occurred: {e}"
+        return f"An error occurred while scraping: {e}"