python词云制作

总结：
1.jieba模块分割的前必须是字符串类型
2.获取不到信息请修改请求头和cookie信息

# -*- coding: utf-8 -*-
import requests  #请求
import re  ##提取
from os import path
import jieba  #分割
from wordcloud import WordCloud   ##制作词云


class Bilibili(object):
    #这个是储存抓取的弹屏的信息，列表形式
    res_text = [] #是这个形式['出现了]，['第二张才是黑白']
    def run(self):
        headers = {
            'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36',
            "cookie":"_uuid=CC7F8292-4760-241E-C7BA-02399DF75B5C62046infoc; buvid3=25AD665B-F23E-4969-A84A-09EFD72F28E8138369infoc; CURRENT_FNVAL=80; blackside_state=1; rpdid=|(Jll|YR|mYl0J'uY|RkJJJYR; DedeUserID=318123043; DedeUserID__ckMd5=469977c6d3c3e8b4; SESSDATA=ad86913a%2C1619785580%2C1a312*b1; bili_jct=e75b93f471f9575d2b90ce6ba5122037; CURRENT_QUALITY=80; PVID=1; bsource=search_baidu; sid=daz5ksmp; bfe_id=603589b7ce5e180726bfa88808aa8947; fingerprint3=f84297d89bfe209608369114312776d4; fingerprint=c83191bdad10a54ee8be9890d81a2586; fingerprint_s=e8ed533e293e6893803dd992288ef650; buvid_fp=25AD665B-F23E-4969-A84A-09EFD72F28E8138369infoc; buvid_fp_plain=25AD665B-F23E-4969-A844-09EFD72F28E8138369infoc"
        }
        for a in range(8,10):
            url = 'https://api.bilibili.com/x/v2/dm/history?type=1&oid=217636750&date=2021-01-0{}'.format(a)
            respose = requests.get(url,headers=headers,)
            #转成文字
            respose = respose.content.decode()

            content = re.compile('<d.*?>(.*?)</d>')
            text_all = re.findall(content,respose)
            self.res_text.append(text_all)
        # print(len(text_all))
        # print(text_all)
            # with open('bilibili.csv','a',newline='',encoding='utf-8-sig') as tp:
            #     writer = csv.writer(tp)
            #     writer.writerow(text_all)

        result = ' '.join(text_all)  #字符串
        txt_list = jieba.lcut(result)   #txt_list是数据类型,result是字符串类型
        txt_str = ' '.join(txt_list)
        wordcloud = WordCloud(
            width=1000,
            height=1000,
            # background_color='white',  ##背景颜色
            background_color=None,
            mode="RGBA",
            font_path="C:/Windows/Fonts/simfang.ttf").generate(txt_str)
        image = wordcloud.to_image()
        image.show()
        # 获得模块所在的路径的
        d = path.dirname(__file__)
        # os.path.join()：  将多个路径组合后返回
        # wordcloud.to_file(path.join(d, "h11.png"))
        wordcloud.to_file('ciyun.png')


def main():
    bili = Bilibili()
    bili.run()

if __name__ == '__main__':
    main()

效果如下