利用WordCloud和jieba生成词云图（也叫文字云）, （同样的代码，有的图片可以生成mask起作用，有的就不起作用，这个还不不知道原因）

Python生成词云的常用库「wordcloud」。安装： pip install wordcloud

wordcloud默认是为了英文文本来做词云的，如果需要制作中文文本词云，就需要先对中文进行分词。这里就需要用到中文分词库「jieba」。安装：pip install jieba

 

 

# coding: utf-8
# Project：pythonProject8
# File：词云图.py
# Author：李凤娟
# Date ：2023/9/12 14:09
# IDE：PyCharm 
# 功能：生成词云图

from wordcloud import WordCloud
import jieba
from collections import Counter
from matplotlib import pyplot as plt
from imageio.v2 import imread


"""
word.txt里的内容为：
Python
C逆向
C++逆向
C++逆向
C++逆向
C逆向
网络爬虫
数据解析
"""
# 读取文件内容
with open('word.txt', 'r', encoding='utf-8') as f:
    words = f.read()

# 增加jieba库词语（一些完整的词可能被分割）
jieba.add_word("网络爬虫")
jieba.add_word("JS逆向")
jieba.add_word("APP逆向")
jieba.add_word("C逆向")
jieba.add_word("C++逆向")
jieba.add_word("网络数据")

# 使用jieba进行分词
words_list_jieba = jieba.lcut(words)    # ['Python', '\n', 'C逆向', '\n', 'C++逆向', '\n', 'C++逆向', '\n', 'C++逆向', '\n', 'C逆向', '\n', '网络爬虫', '\n', '数据', '解析']

# 定义需要排除的词语集合
excluded_words = ["将", "\n", "地", '小说', '侧', "又", "一雄", "如何", "什么", '可以', '吗', "只是", "他", "本", '们', " ",
                  "…", "把", "人", "很", '那么', '着', '太', '能', '给', '不是', '里', "被", "就是", "一个", "没有", "剧",
                  "让", "/", "而", "与", "一部", "的", "我", "你", "她", "我们", "你们", "他们", "是", "在", "了", "有",
                  "这", "那", "就", "也", "还", "但", "如果", "然后", "因为", "所以", "一", "二", "三", "四", "五", "六",
                  "七", "八", "九", "十", "百", "千", "万", "个", "这些", "那些", "更", "最", "好", "坏", "大", "小", "高",
                  "低", "长", "短", "新", "旧", "常", "少", "多", "全", "每", "些", "去", "来", "到", "从", "为", "以", "对",
                  "和", "或", "及", "上", "下", "中", "前", "后", "左", "右", "内", "外", "间", "部", "种", "年", "月", "日",
                  "时", "分", "秒", "这个", "那个", "这样", "那样", "一些", "很多", "非常", "可能", "一定", "一直", "经常",
                  "不断", "不只", "不要", "不得", "不能", "无法", "没法", "必须", "应该", "需要", "会", "想", "要", "找",
                  "看", "听", "说", "写", "读", "学", "做", "吃", "喝", "睡", "玩", "工作", "生活", "家庭", "朋友", "嫌",
                  "感觉", "思考", "想法", "方法", "原因", "结果", "可能性", "比较", "不同", "相同", "重要", "容易", "困难",
                  "简单", "复杂", "正确", "错误", "，", "。", "！", "？", "；", "：", "“", "”", "‘", "’", "（", "）",
                  "【", "】", "《", "》", "——", "—", "·", "、", "～", "像", "“", "”", ",", "\'", "\"", ","]

# 过滤排除的词语
words_list = [x for x in words_list_jieba if x not in excluded_words]   # ['Python', 'C逆向', 'C++逆向', 'C++逆向', 'C++逆向', 'C逆向', '网络爬虫', '数据', '解析']

# 使用Counter进行词频统计
word_counter = Counter(words_list)  # Counter({'C++逆向': 3, 'C逆向': 2, 'Python': 1, '网络爬虫': 1, '数据': 1, '解析': 1})
sorted_file = word_counter.most_common()    #[('C++逆向', 3), ('C逆向', 2), ('Python', 1), ('网络爬虫', 1), ('数据', 1), ('解析', 1)]
print(sorted_file)
# 加载图像作为遮罩
mask = imread("2.png")
# 生成词云时指定遮罩
# 将字体文件（simhei.ttf）放到本项目目录下，或者指定C:\Windows\Fonts\simhei.ttf目录
wordcloud = WordCloud(
    font_path='simhei.ttf',
    background_color='white',
    mask=mask).generate_from_frequencies(dict(sorted_file))

# 保存词云图
wordcloud_image_path = 'wordcloud.png'
wordcloud.to_file(wordcloud_image_path)

# 到目前为止图片生成完毕!!!!



# 下边只是展示图片，无所谓的
# 生成图片
image = wordcloud.to_image()
# 展示图片
image.show()

# 显示词云图
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.figure()
plt.show()

 

把WordCloud（）里的mask去掉，就会生成指定大小的图片

 

wordcloud = WordCloud(
    font_path='simhei.ttf',
    background_color='white',
    height=1000,
    width=800
    ).generate_from_frequencies(dict(sorted_file))

 

stopwords 的用法

stopwords = {}.fromkeys(["爬虫"])
# 生成词云时指定遮罩
# 将字体文件（simhei.ttf）放到本项目目录下，或者指定C:\Windows\Fonts\simhei.ttf目录
wordcloud = WordCloud(
    font_path='simhei.ttf',
    background_color='white',
    height=600,
    width=800,
    stopwords=stopwords,
   mask=mask).generate_from_frequencies(dict(sorted_file))