def analyze_csv(file_path):
# Load CSV
df = pd.read_csv(file_path)

# Count total rows
num_rows = len(df)

# Extract unique domains from 'Source url'
df['Source Domain'] = df['Source url'].apply(lambda x: urlparse(x).netloc)
unique_domains = df['Source Domain'].nunique()

return num_rows, unique_domains

Example usage

file_path = "your_file.csv" # Replace with actual file path
num_rows, unique_domains = analyze_csv(file_path)
print(f"Total rows: {num_rows}")
print(f"Unique source domains: {unique_domains}")