爬取B站马保国弹幕制作词云

有人的地方就有江湖

北京时间5月17日，号称拥有马氏三连鞭、闪电五连鞭的浑元形意太极拳宗师马保国，在山东淄博被一位50岁的民间武术爱好者王庆民30秒KO。如果你还不了解这件震惊中国武林圈的大事，建议你恶补一下这个视频。

我几乎是本能的去b站看了看，播放量已经达到了一个恐怖的境地

1. 先用jsoup把弹幕爬下来

依赖

<!-- 爬虫相关Jar包依赖 -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.10-FINAL</version>
</dependency>
<dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.5.3</version>
</dependency>
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.11.3</version>
</dependency>

代码

package com.example.jm.jmm.util.jsoup;

import com.alibaba.fastjson.JSONObject;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

import java.io.File;
import java.io.FileOutputStream;
import java.io.OutputStream;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * @Description: 
 * @Param: 爬取b站弹幕
 * @Return: 
 * @Author: Jiangsy
 * @Date: 2020/11/20
**/
public class BiliUtil {

    public static void main(String[] args) throws Exception{
        //视频号
        String av = "BV1HJ411L7DP";
        String url = "https://api.bilibili.com/x/player/pagelist?bvid="+av+"&jsonp=jsonp";
        String result = HttpClientUtil.doGet(url);
        //获取cid
        String cid = JSONObject.parseObject(result).getJSONArray("data").getJSONObject(0).getString("cid");
        System.out.println("cid:{}"+cid);
        //获取弹幕打印到文件中
        getContent(cid);
    }

    /**
     * @Description:获取弹幕内容
     * @Param: [cid]
     * @Return: void
     * @Author: Jiangsy
     * @Date: 2020/11/20
    **/
    public static void getContent(String cid) throws Exception{
        CloseableHttpClient closeableHttpClient = HttpClients.createDefault() ;
        HttpGet httpGet1 = new HttpGet("http://comment.bilibili.com/"+cid+".xml");
        CloseableHttpResponse httpResponse1 = closeableHttpClient.execute(httpGet1) ;
        String en = EntityUtils.toString(httpResponse1.getEntity(), "UTF-8");
        String c = "\">(.*?)<" ;
        Pattern a = Pattern.compile(c);
        Matcher m = a.matcher(en);
        File file = new File("/project/11.txt");
        if(file.exists()){
            file.delete();
        }
        OutputStream fos=new FileOutputStream("/project/11.txt");
        while(m.find()){
            String speak = m.group().replace("\">","") ;
            speak = speak.replace("<","") ;
            System.out.println(speak);
            String str=speak;
            str+="";
            fos.write(str.getBytes());
        }
    }
}

python的WordCloud生成词云

import jieba
from matplotlib import pyplot as plt
from wordcloud import WordCloud
from PIL import Image
import numpy as np

path = r'ciyun.png'
font = r'/System/Library/Fonts/Hiragino Sans GB.ttc'

text = open('/project/11.txt', 'r', encoding='utf-8').read()
cut = jieba.cut(text)  #分词
string = ' '.join(cut)
print(len(string))
img = Image.open('ciyun/22.png') #打开图片
img_array = np.array(img) #将图片装换为数组
stopword=['小米']  #设置停止词，也就是你不想显示的词，这里这个词是我前期处理没处理好，你可以删掉他看看他的作用
wc = WordCloud(
    background_color='white',
    width=1000,
    height=800,
    mask=img_array,
    font_path=font,
    stopwords=stopword
)
wc.generate_from_text(string)#绘制图片
plt.imshow(wc)
plt.axis('off')
plt.figure()
plt.show()  #显示图片
wc.to_file('new.png')  #保存图片

效果图

the end