爬取B站视频弹幕并制作词云

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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
import requests
from lxml import etree
import datetime
import random as r
from datetime import timedelta
import jieba
from wordcloud import WordCloud
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

useragent = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.75 Safari/537.36',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:65.0) Gecko/20100101 Firefox/65.0',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.0.3 Safari/605.1.15',
    'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'

]

headers={
    'user-agent': r.choice(useragent),
    "cookie":"_uuid=72919017-AD53-374F-B5D7-9B83AB97EED158304infoc; buvid3=36B30709-3B4E-4FF4-AAC0-4882356AF274143084infoc; sid=aifpqhjy; DedeUserID=626120309; DedeUserID__ckMd5=cbd6baccd20c90d4; SESSDATA=d8ed0e66%2C1615632718%2Cd3403*91; bili_jct=fdb9c69e8b41f6ee814b34d385be5e20; CURRENT_FNVAL=80; blackside_state=1; rpdid=|(u|JRRkuJu)0J'uY|||)|~R~; LIVE_BUVID=AUTO6816006815353517; PVID=3; CURRENT_QUALITY=80; bfe_id=1bad38f44e358ca77469025e0405c4a6; bp_video_offset_626120309=438479623642879626; bp_t_offset_626120309=438479623642879626"
}
def getdanmu(date):
    date = datetime.datetime.strptime(date, "%Y-%m-%d") + timedelta(days=-1)
    print(date.strftime("%Y-%m-%d"))
    res=requests.get(f'https://api.bilibili.com/x/v2/dm/history?type=1&oid=238498824&date={date.strftime("%Y-%m-%d")}',headers=headers)
    # print(res.encoding)
    xml=etree.HTML(res.text.encode(res.encoding))
    text=xml.xpath('//d//text()')
    for i in text:
        with open("bilibili.txt","a+") as f:
            f.write(i)
            f.write("\n")
    if text:
        getdanmu(date.strftime("%Y-%m-%d"))

def cutTest():
    with open("bilibili.txt","r") as f:
        for i in f.readlines():
            for j in jieba.lcut(i):
                with open("cut.txt","a+") as w:
                    with open('stop.txt',"r") as s:
                        if w.readline()!=j:
                            w.write(j)
                            w.write('\n')

def word():
    text = open('cut.txt').read()

    mask = np.array(Image.open("beijing.jpeg"))
    wc = WordCloud(mask=mask, font_path='FZQiuDYRHJW.TTF', mode='RGBA', background_color=None,collocations=False).generate(text)

    # 显示词云
    plt.imshow(wc, interpolation='bilinear')
    plt.axis("off")
    plt.show()

    # 保存到文件
    wc.to_file('wordcloud4.png')

getdanmu("2020-09-25")
cutTest()
word()

0SDt1g.png