哔哩哔哩视频弹幕词云分析

import requests
import parsel
import csv
import time

for page in range(20,32):
    time.sleep(1)
    print('正在爬取'.format(page))
    url = 'https://api.bilibili.com/x/v2/dm/history?type=1&oid=140610898&date=2020-11-{}'.format(page)
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
        "cookie": "__uuid=1896D3F7-4A98-54EB-F7FA-3301CE9EF5F307776infoc; buvid3=B68B2187-4C3E-4466-A896-FBF9B292099B190963infoc; LIVE_BUVID=AUTO4115757254257055; stardustvideo=1; rpdid=|(umu|ulY)JJ0J'ul~l~klRJ); sid=8cq4r229; im_notify_type_65901796=0; laboratory=1-1; DedeUserID=523606542; DedeUserID__ckMd5=909861ec223d26d8; blackside_state=1; CURRENT_FNVAL=80; SESSDATA=a976c0b4%2C1618637313%2C4d792*a1; bili_jct=7f54729ec20660f750661122b80746d2; PVID=1; bp_video_offset_523606542=458111639975213216; CURRENT_QUALITY=16; bfe_id=1e33d9ad1cb29251013800c68af42315"
    }
    response = requests.get(url=url, headers=headers)
    response.encoding = response.apparent_encoding
    selector = parsel.Selector(response.text)
    data = selector.css('d::text').getall()
    print(data)
    for i in data:
        print(i)
        with open('B站弹幕.csv', mode='a', newline='', encoding='utf-8-sig') as f:
            writer = csv.writer(f)
            links = []
            links.append(i)
            writer.writerow(links)




  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
 

import jieba
import wordcloud
import imageio
from PIL import Image
import numpy as np
# 读取文件内容
f = open('D:\python\爬虫\B站弹幕.csv', encoding='utf-8')#你文件存储的位置
txt = f.read()
# print(txt)
# jiabe 分词 分割词汇
txt_list = jieba.lcut(txt)
string = ' '.join(txt_list)
# 词云图设置
imgobj = Image.open('1.jpg')#你找的图片模型文件
img_mask=np.array(imgobj)
#print(img_mask)
wc = wordcloud.WordCloud(
        mask=img_mask,
        max_words=400,
        width=800,         # 图片的宽
        height=500,         # 图片的高
        background_color='snow',   # 图片背景颜色
        font_path='msyh.ttc',    # 词云字体
        random_state=120,
        max_font_size=60,
      
        scale=15,
)
# 给词云输入文字
wc.generate(string)
# 词云图保存图片地址
wc.to_file('1.png')
print("图片保存成功")

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
  
30
  
31
  
32
  
33
 

文章来源: blog.csdn.net，作者：肥学，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jiahuiandxuehui/article/details/110324992