Python爬蟲b站視頻彈幕並生成詞雲圖分析

爬蟲：requests，beautifulsoup

詞雲：wordcloud，jieba

代碼加注釋：

# -*- coding: utf-8 -*-
import xlrd#讀取excel
import xlwt#寫入excel
import requests
import linecache
import wordcloud
import jieba
import matplotlib.pyplot as plt
from bs4 import BeautifulSoup
 
if __name__=="__main__":
    yun=""

    n=0#ID編號
    target='https://api.bilibili.com/x/v1/dm/list.so?oid=132084205'#b站oid頁
    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'
    headers = {'User-Agent':user_agent}#偽裝瀏覽器

    req=requests.get(url=target)
    html=req.text
    html=html.encode('ISO 8859-1')
    #html=html.replace('<br>',' ').replace('<br/>',' ').replace('/>','>')
    bf=BeautifulSoup(html,"html.parser")   

    texts=bf.find('i')
    texts_div=texts.find_all('d')
    #print(texts_div)
    for item in texts_div:
        n=n+1
        item_name=item.text#標題
        yun+=str(item_name)

    yun=yun.replace(" ","")
    yun=yun.replace("哈","")
    yun=yun.replace("啊","")
    yun=yun.replace("一","")#去除無意義彈幕
    # 結巴分詞，生成字符串，wordcloud無法直接生成正確的中文詞雲
    cut_text = " ".join(jieba.cut(yun))
    wc = wordcloud.WordCloud(
    #設置字體，不然會出現口字亂碼，文字的路徑是電腦的字體一般路徑，可以換成別的
    font_path="C:/Windows/Fonts/simfang.ttf",
    #設置了背景，寬高
    background_color="white",width=1000,height=880).generate(cut_text)

    plt.imshow(wc, interpolation="bilinear")
    plt.axis("off")
    plt.show()
    print("Done!")

運行結果圖：