jieba文本分词，去除停用词，添加用户词

import jieba
from collections import Counter
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
import jieba.analyse
from pyquery import PyQuery

cc = ‘‘‘文本‘‘‘

jieba.load_userdict(‘./userdict.txt‘)#加载外部 用户词典

# 创建停用词list
def stopwordslist(filepath):
    stopwords = [line.strip() for line in open(filepath, ‘r‘, encoding=‘utf-8‘).readlines()]
    return stopwords

# 对句子去除停用词
def movestopwords(sentence):
    list = []
    stopwords = stopwordslist(‘./stop_words.txt‘)  # 这里加载停用词的路径
    for word in sentence:
        if word not in stopwords:
            if word != ‘\t‘ and len(word) >1:
                list.append(word)
    return list


words = jieba.cut(PyQuery(cc).text()) #去除HTML标签
word_list = movestopwords(words) # 去除停用词
words_split = " ".join(word_list) #列表解析为字符串
#keywords = jieba.analyse.extract_tags(words_split, topK=100, withWeight=True) # tf-tdf算法
keywords = jieba.analyse.textrank(words_split, topK=100, withWeight=True,allowPOS=(‘ns‘, ‘n‘, ‘vn‘, ‘v‘)) #textrank算法

for item in keywords:
     print(item[0],item[1])

#mycount = Counter(word_list) # 统计词频
#for key, val in mycount.most_common(100):  # 有序（返回前10个）
#    print(key, val)


#alice_mask = np.array(Image.open("./zhihu.png")) #遮罩
wc = WordCloud(
    # width=800,
    # height=600,
    background_color="#000000",  # 设置背景颜色
    max_words=50,  # 词的最大数（默认为200）
    max_font_size=400,  # 最大字体尺寸
    min_font_size=10,  # 最小字体尺寸（默认为4）
    #colormap=‘bone‘,  # string or matplotlib colormap, default="viridis"
    random_state=42,  # 设置有多少种随机生成状态，即有多少种配色方案
    #mask=plt.imread("./zhihu.png"),  # 读取遮罩图片！！
    #mask=alice_mask, #设置遮罩
    font_path=‘./SimHei.ttf‘
)


my_wordcloud = wc.generate(words_split) #按词频生成词云
plt.imshow(my_wordcloud) #展示词云
plt.axis("off") #去除横纵轴
plt.show()
wc.to_file(‘zzz.png‘) # 保存图片文件