wordclouds

# importing the necessery modules 
from wordcloud import WordCloud
import matplotlib.pyplot as plt 
import csv
import codecs


def read_csv(line):
    '''
    Returns: a list of all the urls of articles from huntington news,
    read from a preexisting csv file
    '''
    text = ''
    with open('scraped_articles_DATE.csv', encoding="ISO-8859-1") as file:
        csv_reader = csv.reader(file)
        
        # skip the headers
        next(csv_reader, None)

        counter = 2
        for row in csv_reader:
            url = row[0]
            headline = row[1]
            byline = row[2]
            date = row[3]
            content = row[4]

            if counter == line:
                return content
            
            counter += 1
    return ''
            


lineYo = int(input('What line?'))
article = read_csv(lineYo)

wordcloud = WordCloud(width=480, height=480, 
            stopwords=["the", "and","but", "if", "to", "of", "at", "with",
                       "we", "it", "on", "in", "from", "for", "her", "him",
                       "up", "just", "had", "they", "that", "said", "got", "did",
                       "really", "their", "or", "who", "is", "its", "be", "am", "are"
                       "was", "about", "so", "also", "this", "you", "would", "she", 
                       "could", "can"
                       ]).generate(article) 
  
plt.figure() 
plt.imshow(wordcloud, interpolation="bilinear") 
plt.axis("off") 
plt.margins(x=0, y=0) 
plt.show()