Python 爬取“工商秘密”微博后，我做了这个“可视化大屏”（附gif图）

for i in cards:
    # 在提取json数据时，使用get方法，有就提取，没有就为空
    # mblog可能有可能没有
    if i.get('mblog'):
        result1 = i.get('mblog')['text']
        ids = i.get('mblog')['id']
        # print(result1,ids)
        # print('\n')
        cop = re.compile("[^\u4e00-\u9fa5]") # 匹配不是中文、大小写、数字的其他字符
        string1 = cop.sub('', result1) 
        # print(string1)
        # print('\n')
        # result2 = re.sub('<[^<]+?>', '', result1).replace('\n', '').strip()
        sheet.append([string1,'0','0','0','0','0'])
        # =======微博下面的评论
        # time.sleep(1)
        # md = re.findall('<a href="(.*?)">',result1)[0].split('/')[-1]
        url = 'https://m.weibo.cn/comments/hotflow?id='+ ids +'&mid='+ ids +'&max_id_type=0'
        response1 = requests.get(url,timeout=30,headers=headers)
        dat1 = response1.json()
        
        if dat1['ok'] == 1:
            pinglun_num = dat1['data']['total_number']
            da = dat1['data']['data']
            for i in da:
                pinglun = cop.sub('', i['text'])
                created_at = i['created_at']
                user1 = i['user']['screen_name']
                sheet.append(['0',created_at,pinglun,user1,'0','0'])
                 # =======微博下面的评论的评论
                if i['total_number'] > 0 and i['comments']!=False:
                    comments = i['comments']
                    for g in comments:
                        text = cop.sub('', g['text'])
                        user2 = g['user']['screen_name']
                        sheet.append(['0','0','0','0',text,user2])

from pyecharts.charts import *
from pyecharts import options as opts 
from pyecharts.globals import ThemeType  
import osos.chdir(r'C:\Users\Administrator\Desktop')
ID = ['海啸****','寻找****道长','最好****18881','我可****假猴子ha','工商***精']
values = [53,47,36,34,34]
c = (
        Pie(init_opts=opts.InitOpts(theme=ThemeType.CHALK))
        .add("", zip(ID,values),radius=["40%", "70%"])
        .set_global_opts(
            title_opts=opts.TitleOpts(title="秘密微博评论者TOP5",subtitle="卖山楂啦prss",pos_top="2%",pos_left = 'center'),
            toolbox_opts=opts.ToolboxOpts(
            # 是否显示该工具
            is_show=True,
            ))
        
        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}",font_size=18))
        .render("数据可视化.html")
    )

import pandas as pd
import numpy as np

df = pd.read_excel('C:\\Users\\Administrator\\Desktop\\发布时间.xlsx')

def trans_format(time_string, from_format='%a %b %d %H:%M:%S +0800 %Y', to_format='%Y-%m-%d %H:%M:%S'):
    """
    @note 时间格式转化
    :param time_string:
    :param from_format:
    :param to_format:
    :return:
    """
    time_struct = time.strptime(time_string,from_format)
    times = time.strftime(to_format, time_struct)
    return times

if __name__ == "__main__":
    df["处理后的时间"] = df['时间'].apply(trans_format)

bins = pd.read_csv(r"处理后的数据.csv")
bins
def cut_bins(x):
    if  0.083333<= x <0.250000:
        return '02:00:00--06:00:00'
    elif 0.250000 <=x <0.458333:
        return '06:00:00--11:00:00'
    elif 0.458333 <=x <0.541667:
        return '11:00:00--13:00:00'
    elif 0.541667 <=x <0.708333:
        return '13:00:00--17:00:00'
    elif 0.708333 <=x <0.791667:
        return '17:00:00--19:00:00'
    elif 0.791667 <=x <0.916667:
        return '19:00:00--22:00:00'
    else:
        return '22:00:00--02:00:00'

bins['所在时间段'] = bins['将时分秒改成常规'].map(cut_bins)
bins

bins['所在时间段'].value_counts()