Python爬虫b站视频弹幕并生成词云图分析

 1 # -*- coding: utf-8 -*-
 2 import xlrd#读取excel
 3 import xlwt#写入excel
 4 import requests
 5 import linecache
 6 import wordcloud
 7 import jieba
 8 import matplotlib.pyplot as plt
 9 from bs4 import BeautifulSoup
10  
11 if __name__=="__main__":
12     yun=""
13 
14     n=0#ID编号
15     target=‘https://api.bilibili.com/x/v1/dm/list.so?oid=132084205‘#b站oid页
16     user_agent = ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36‘
17     headers = {‘User-Agent‘:user_agent}#伪装浏览器
18 
19     req=requests.get(url=target)
20     html=req.text
21     html=html.encode(‘ISO 8859-1‘)
22     #html=html.replace(‘<br>‘,‘ ‘).replace(‘<br/>‘,‘ ‘).replace(‘/>‘,‘>‘)
23     bf=BeautifulSoup(html,"html.parser")   
24 
25     texts=bf.find(‘i‘)
26     texts_div=texts.find_all(‘d‘)
27     #print(texts_div)
28     for item in texts_div:
29         n=n+1
30         item_name=item.text#标题
31         yun+=str(item_name)
34 
35     yun=yun.replace(" ","")
36     yun=yun.replace("哈","")
37     yun=yun.replace("啊","")
38     yun=yun.replace("一","")#去除无意义弹幕
39     # 结巴分词，生成字符串，wordcloud无法直接生成正确的中文词云
40     cut_text = " ".join(jieba.cut(yun))
41     wc = wordcloud.WordCloud(
42     #设置字体，不然会出现口字乱码，文字的路径是电脑的字体一般路径，可以换成别的
43     font_path="C:/Windows/Fonts/simfang.ttf",
44     #设置了背景，宽高
45     background_color="white",width=1000,height=880).generate(cut_text)
46 
47     plt.imshow(wc, interpolation="bilinear")
48     plt.axis("off")
49     plt.show()
50     print("Done!")