Hamlet的jieba分词和词云

def getText():
    txt = open("hamlet.txt", "r").read()
    txt = txt.lower()
    for ch in '!"#$%&()*+,-./:;<=>?@[\]^_‘{|}~':
        txt = txt.replace(ch, " ")   #将文本中特殊字符替换为空格
    return txt
 
hamletTxt = getText()
words  = hamletTxt.split()
counts = {}
for word in words:           
    counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba
import numpy as np
from PIL import Image
def create_word_cloud(filename):
    text = open("{}.txt".format(filename),'rb').read()
    wordlist = jieba.cut(text, cut_all=True)
    wl = " ".join(wordlist)
    cloud_mask = np.array(Image.open("taoxin.jpg"))
    wc = WordCloud(
        background_color="black",
        mask=cloud_mask,
        max_words=2000,
        height=1200,
        width=1600,
        max_font_size=100,
        random_state=100,
    )
 
    myword = wc.generate(wl)
    plt.imshow(myword)
    plt.axis("off")
    plt.show()
    wc.to_file('py_book.bmp')
if __name__ == '__main__':
    create_word_cloud('Hamlet')