用python给爬取到的新闻生成词云提取关键词

最新推荐文章于 2024-04-04 08:29:13 发布

Jellyfish0029

最新推荐文章于 2024-04-04 08:29:13 发布

阅读量270

点赞数

文章标签： python 爬虫数据分析中文分词

本文链接：https://blog.csdn.net/m0_60451449/article/details/132194105

版权

import jieba
import wordcloud
import pandas as pd


# 读取 Excel 文件
df = pd.read_excel('chinanews2.xlsx', sheet_name='news2')

# 读取某一列的数据，
s = df['content']


ls = df['content'].apply(lambda x: jieba.lcut(str(x)))  # 对每个元素进行分词操作
text = ' '.join(ls.sum())  # 连接分词结果并转换为字符串



stopwords = ["的","是","了","记者","和","在","社","月","日","日电","说","不","而","这",
             "到","被","就","认为","以及","已经","上","后","其","都","他","来","也","将"
             ,"为","没有","从","已","向","等","年","但","有","对","又","但","应该","要"
             ,"我们","与","并"] # 去掉不需要显示的词

wc = wordcloud.WordCloud(font_path="msyh.ttc",
                         width = 1000,
                         height = 700,
                         background_color='white',
                         max_words=100,stopwords=stopwords)
# msyh.ttc电脑本地字体，写可以写成绝对路径
wc.generate(text) # 加载词云文本
wc.to_file("chinanews.png") # 保存词云文件