# Remove the break tags (<br />)
df['review_cleaned'] = df['review'].apply(lambda x: x.replace('<br />', ''))

# Remove unnecessary whitespace
df['review_cleaned'] = df['review_cleaned'].replace('s+', ' ', regex=True)

# Compare 72 characters of the second review before and after cleaning
print('Before cleaning:')
print(df.iloc[1]['review'][0:72])

print('nAfter cleaning:')
print(df.iloc[1]['review_cleaned'][0:72])