数据筛选与处理

handle.py

@@ -0,0 +1,44 @@
+import requests
+from bs4 import BeautifulSoup
+import re
+import time
+import jieba  
+import wordcloud  
+import matplotlib.pyplot as plt
+import pandas as pd  
+from pandas import ExcelWriter
+from collections import Counter
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Edg/127.0.0.0',
+   
+}
+keywords = [
+    'AI', '人工智能', '机器学习', '深度学习', '神经网络', '自动化', 
+    '算法', '数据科学' '自然语言处理', '计算机视觉',  '人工智能技术', 'AI技术', 'AI应用', 'AI模型', 
+    '大数据', '预测分析', '机器视觉', '自动驾驶',
+     '智能推荐', '计算机科学', '人工智能应用',
+    '数据分析','智能化', '情感计算','ai'
+]
+
+def chuli(etxt):
+    #danmustr=''.join(i for i in etxt) #将所有弹幕拼接在一起
+    #words=list(jieba.cut(danmustr))  ###利用jieba库将弹幕按词进行切分
+    words=[i for i in etxt if len(i)>1] ###挑出长度大于1的词语（为去除诸如？，哈，啊等字符）
+    wc=wordcloud.WordCloud(background_color='white',height=1000,width=1000,font_path='simsun.ttc')#利用wordcloud库定义词云图片的信息
+    wc.generate(' '.join(words))   ##生成图片
+    print(wc)
+    plt.imshow(wc)
+    plt.show()
+
+def sort(txt, keywords):
+    
+    comment_counter = Counter()
+    for line in txt:
+        line.strip()
+        if any(word in keywords for word in jieba.cut(line)):
+            comment_counter[line] += 1
+    
+    return comment_counter
+
+AIdanmu = sort(altxt, keywords)
+chuli(AIdanmu)