from wordcloud import WordCloud
from collections import Counter
import matplotlib.pyplot as plt
import pandas as pd

final_danmu=[]#所有弹幕合集
final_danmu_ai=[]#所有ai有关弹幕合计
for num in range(1,301):#遍历爬好的弹幕
    text_name=f"第{num}个视频弹幕.txt"
    danmu=[]
    key=[
        '人工智能','AI'
    ]
    try:
        with open(f"{text_name}",mode='r',encoding='utf-8') as f:
            for i in f:
                danmu.append(i.strip())
        danmu_ai=[i for i in danmu if any(j in i for j in key)]
        final_danmu_ai+=danmu_ai
        final_danmu+=danmu
    except:
        continue
aicount=Counter(final_danmu_ai)
danmucount=Counter(final_danmu)
#分别计数
for i in aicount.most_common(8):#AI有关弹幕排名前8
    print(f"弹幕：{i[0]}\n次数：{i[1]}\n")
wordcloud = WordCloud(width=800, height=400, background_color='white',
                      font_path='msyh.ttc',  # 设置字体路径，可以根据系统字体路径调整
                      max_words=100, colormap='viridis').generate_from_frequencies(danmucount)

# 显示词云图
plt.figure(figsize=(10, 5))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')  # 不显示坐标轴
plt.show()

#写入excel
df = pd.DataFrame(danmucount.items(), columns=['弹幕内容', '出现次数'])
df.to_excel("弹幕大全.xlsx", index=False)