WebScraping Code

📋 Copy Code

# URL of the webpage
url = <url>

# Send a request to the webpage
response = requests.get(url)

# Check if the request was successful
if response.status_code == 200:
    # Parse the HTML content
    soup = BeautifulSoup(response.text, 'html.parser')

    # Find all the divs with the class 'The Class'
    data_divs = soup.find_all('div', class_='The Class')

    # Initialize lists to store the scraped data
    countries = []
    total_life_expectancy = []
    males = []
    females = []

    # Iterate through each div
    for div in data_divs:
        # Get the country name from the <a> tag
        country_tag = div.find('a')
        if country_tag:
            countries.append(country_tag.text.strip())
        else:
            countries.append(None)  # Append None if country not found
        
        # Get the total life expectancy from the first <strong> tag and the next text node
        total_life_expectancy_tag = div.find('strong')
        if total_life_expectancy_tag and total_life_expectancy_tag.next_sibling:
            total_life_expectancy.append(total_life_expectancy_tag.next_sibling.strip())
        else:
            total_life_expectancy.append(None)  # Append None if not found

        # Find all <strong> tags and extract male data from the second one
        strong_tags = div.find_all('strong')
        if len(strong_tags) > 1:  # Ensure there is a second <strong> tag
            male_text = strong_tags[1].next_sibling  # Text after the second <strong>
            males.append(male_text.strip() if male_text else None)
        else:
            males.append(None)  # Append None if not enough <strong> tags

        # Extract female data from the third <strong> tag
        if len(strong_tags) > 2:  # Ensure there is a third <strong> tag
            female_text = strong_tags[2].next_sibling  # Text after the third <strong>
            females.append(female_text.strip() if female_text else None)
        else:
            females.append(None)  # Append None if not enough <strong> tags

    # Create a DataFrame
    df = pd.DataFrame({
        'Country': countries,
        'Total life expectancy': total_life_expectancy,
        'Males': males,
        'Females': females
    })

else:
    print(f"Failed to retrieve data: {response.status_code}")
            

📋 Copy Code

df_cleaned = df.dropna(subset=['Country', 'Total life_expectancy'])
df_cleaned.head()
            

📋 Copy Code

# Function to clean total life_expectancy data
def clean_total_life_expectancy(value):
    if isinstance(value, str):
        return value.split()[0]  # Keep everything before the first whitespace
    return value

# Applying the function
df_cleaned['Total life_expectancy'] = df_cleaned['Total life_expectancy'].apply(clean_total_life_expectancy)

df_cleaned.head()
            

📋 Copy Code

# Function to clean male and female data
def clean_life_expectancy(value):
    if isinstance(value, str):
        return re.sub(r'[^0-9]*$', '', value)  # Remove everything after the last digit
    return value
        
# Applying the function
df_cleaned['Males'] = df_cleaned['Males'].apply(clean_life_expectancy)
df_cleaned['Females'] = df_cleaned['Females'].apply(clean_life_expectancy)
        
df_cleaned.head()
            

📋 Copy Code

# Save the cleaned DataFrame to a CSV file
df_cleaned.to_csv('cleaned_life_expectancy_data.csv', index=False)
            

📋 Copy Code

url = url
response = requests.get(url)
soup = BeautifulSoup(response.text, "lxml")
            

📋 Copy Code

country_dishes = soup.find_all('h3')
country_dishes[:5]
            

            [<h3>Note</h3>,
            <h3>Afghanistan (Kabuli Pulao)</h3>,
            <h3>Algeria (Couscous)</h3>,
            <h3>Australia (Meat Pie)</h3>,
            <h3>Austria (Wiener Schnitzel)</h3>]
        

📋 Copy Code

country_n_dish = [country_dish.text for country_dish in country_dishes]
country_n_dish[:5]
            

            ['Note',
            'Afghanistan (Kabuli Pulao)',
            'Algeria (Couscous)',
            'Australia (Meat Pie)',
            'Austria (Wiener Schnitzel)']
        

📋 Copy Code

df = pd.DataFrame({'country + dish': country_n_dish})
df.head()
            

📋 Copy Code

df.tail()
            

📋 Copy Code

df = df[df["country + dish"].str.contains(" ()]
df.head()
            

📋 Copy Code

df.tail()
            

📋 Copy Code

values = df["country + dish"].str.split(" (, n=1, expand=True)
df["country"] = values[0]
df["dish"] = values[1]
        
df["country"].head()
            

            1    Afghanistan
            2        Algeria
            3      Australia
            4        Austria
            5     Azerbaijan
            Name: country, dtype: object
        

📋 Copy Code

df["dish"].head()
            

            1        Kabuli Pulao)
            2            Couscous)
            3            Meat Pie)
            4    Wiener Schnitzel)
            5                Plov)
            Name: dish, dtype: object
        

📋 Copy Code

df['dish'] = df['dish'].apply(lambda x: re.sub(r'[\\)]', '', x))
df["dish"].head()
            

            1        Kabuli Pulao
            2            Couscous
            3            Meat Pie
            4    Wiener Schnitzel
            5                Plov
            Name: dish, dtype: object
        

📋 Copy Code

df.head()
            

📋 Copy Code

df.drop(['country + dish'], axis=1, inplace=True)
df.head()
            

📋 Copy Code

df.to_csv("national_dishes.csv", index=False)