Python将QQ聊天记录生成词云的示例代码

pip install jieba -i https://pypi.douban.com/simple/

pip install wordcloud-1.8.1-cp38-cp38-win_amd64.whl

import matplotlib.pyplot as plt
from wordcloud import WordCloud
import jieba
from wordcloud import WordCloud, ImageColorGenerator, STOPWORDS
import os
import numpy as np
import PIL.Image as Image
 
newtext = []
#打开聊天记录文件
for word in open('F:\\csdn\\chat.txt', 'r',encoding='utf-8'):
  tmp = word[0:4]
  #过滤掉聊天记录的时间和qq名称
  if (tmp == "2021"):
    continue
  tmp = word[0:2]
  #print(tmp)
  newtext.append(word)
 
#将过滤后的文本重新写入文件并保存
with open('F:\\csdn\\chat_final.txt', 'w', encoding='utf-8') as f:
  for i in newtext:
    f.write(i)
#打开新生成的聊天记录文件
text = open('F:\\csdn\\chat_final.txt', 'r',encoding = 'utf-8').read()
word_jieba = jieba.cut(text, cut_all=True)
word_split = " ".join(word_jieba)
#去掉一些意义不大的字
stop_words = set(STOPWORDS)
stop_words.add("的")
stop_words.add("我")
stop_words.add("你")
stop_words.add("是")
stop_words.add("就")
#根据心形图片生成配色方案，这里的路径要配置正确
alice_coloring = np.array(Image.open(os.path.join('F:\\','heart.jpg')))
my_wordcloud = WordCloud(scale=16,background_color="white", max_words=800, stopwords=stop_words, mask=alice_coloring,max_font_size=80, random_state=42,font_path='C:/Windows/Fonts/simhei.ttf')\
  .generate(word_split)
image_colors = ImageColorGenerator(alice_coloring)
plt.imshow(my_wordcloud.recolor(color_func=image_colors))
plt.imshow(my_wordcloud)
plt.axis("off")
plt.show()

python qqChat.py