# Note that the pandas dataframe created from the dataset was named article_df and article text was stored in the
# 'content' column.

# Remove non-ASCII characters:
for index, row in article_df.iterrows():
    article_df.loc[index, 'content'] = ''.join([i if ord(i) < 128 else ' '
                                                for i in article_df.loc[index, 'content']])

# Remove punctuation:
for index, row in article_df.iterrows():
    article_df.loc[index, 'content'] = (article_df.loc[index, 'content']
                                        .translate(str.maketrans('', '', string.punctuation)))