|
|
|
@ -97,6 +97,10 @@ def get_wordcloud(ai_danmu):
|
|
|
|
|
ai = ' '.join(ai_danmu)
|
|
|
|
|
# 使用jieba分词对连接后的字符串进行分词,并将分词结果再次连接成一个长字符串,分词之间用空格分隔
|
|
|
|
|
cut_t = ' '.join(jieba.cut(ai))
|
|
|
|
|
# 设置停用词,减少无效信息
|
|
|
|
|
stop_words = set()
|
|
|
|
|
content = [line.strip() for line in open('停用词.txt', 'r', encoding='utf-8').readlines()]
|
|
|
|
|
stop_words.update(content)
|
|
|
|
|
# 创建一个WordCloud对象,设置词云图的参数
|
|
|
|
|
wordcloud = WordCloud(background_color="white", # 设置背景颜色为白色
|
|
|
|
|
width=800, # 设置词云图的宽度
|
|
|
|
@ -106,12 +110,12 @@ def get_wordcloud(ai_danmu):
|
|
|
|
|
font_path='msyh.ttc', # 设置字体路径,确保能够显示中文
|
|
|
|
|
contour_width=2, # 设置词云图的轮廓宽度
|
|
|
|
|
contour_color='steelblue', # 设置词云图轮廓的颜色
|
|
|
|
|
repeat='true' # 设置单词课重复出现
|
|
|
|
|
repeat='true', # 设置单词课重复出现
|
|
|
|
|
stopwords = stop_words, # 设置停用词
|
|
|
|
|
).generate(cut_t)
|
|
|
|
|
# 将生成的词云图保存为PNG文件
|
|
|
|
|
wordcloud.to_file('词云图.png')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
bvlist = get_bvlist()
|
|
|
|
|
cidlist = get_cidlist(bvlist)
|
|
|
|
|