读写文件
把待读取的文本存在info.txt中，content类型为str
with open('info.txt', 'r', encoding="UTF-8") as file1: # with as操作读取文件很ok
content = "".join(file1.readlines())
待写入文件为 output.txt，content_after为待写入字符串
with open('output.txt', 'w', encoding='utf-8') as file2:
file2.write(content_after+"\n")
分词
# 调用jieba.cut
sentence_seged = jieba.cut(content)
去除停用词
- 建立停用词表
将停用词表放在stop.txt中，一行一个词# stopwords为停用词list stopwords = [line.strip() for line in open('stop.txt', 'r', encoding='utf-8').readlines()] - 遍历去除停用词
outstr = '' # 待返回字符串 for word in sentence_seged: if word not in stopwords: outstr += word + " "
生成词云图
images = Image.open("something.png") # 打开保存的图片
maskImages = np.array(images) # 并用numpy转换
wc = WordCloud(font_path="msyh.ttc", background_color="white", max_words=100, max_font_size=100).generate(content_after) # 生成词云图
wc.to_file('wordCloudPic.png') # 保存到本地图片文件
