明星热度动态排行

参考： B站_葩葩数据_2021年4月流量明星百度搜索指数动态排名.
小姐姐讲的非常好，希望多多关注、点赞。

明星排行数据来源： 微博-超话排行-明星.
明星热度数据来源： 百度指数.
动态排行生成工具： flourish Bar chart race.

1.微博爬取排名前120的明星

import requests
import pandas as pd
import numpy as np
import time
import re
import json
import demjson
import datetime as dt
from lxml import etree
from selenium import webdriver

# 获取namelist
headers = {
    "Accept": "application/json, text/plain, */*",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Cache-Control": "no-cache",
    "Connection": "keep-alive",
    "Cookie": "你的cookie",   # 换成你的cookie
    "Host": "huati.weibo.cn",
    "Pragma": "no-cache",
    "Referer": "https://huati.weibo.cn/discovery/super",
    "sec-ch-ua-mobile": "?0",
    "Sec-Fetch-Dest": "empty",
    "Sec-Fetch-Mode": "cors",
    "user-agent":"你的user-agent",  # 换成你的user-agent
    "X-Requested-With": "XMLHttpRequest"
}

name_list = []
base_url = "https://huati.weibo.cn/aj/discovery/rank?cate_id=2&page={page}&topic_to_page=&block_time=0&star_type=star&from=&wm=&isvivo=false"
for i in range(1,7):
    url = base_url.format(page=i)
    page_text = requests.get(url=url,headers=headers).text
    ex = '"display_name":"(.*?)","toprank"'
    page_name_list = re.findall(ex, page_text, re.S)
    for name in page_name_list:  
        name_list.append(name)
name_list       
#         with open("name.txt","a+",encoding="utf-8") as fp:
#             fp.write()

运行结果：

2.百度指数获取明星热度值

headers = {
    "user-agent":"自己的user-agent",
    "cookie":'自己的cookie'
}
# 爬取百度指数每日值（需要解码，可一次爬取大量数据）
def decrypt(ptbk, data):
    d = {}
    res = []
    for i in range(len(ptbk)//2):
        d[ptbk[i]] = ptbk[len(ptbk)//2 + i]
    for x in data:
        res.append(d[x])
    return "".join(res)

def get_ptbk(uniqid):
    url = 'https://index.baidu.com/Interface/ptbk?uniqid={}'.format(uniqid)
    response = requests.get(url=url, headers=headers).text
    whh = demjson.encode(response, encoding='utf-8')
    h1 = json.loads(whh)
    h2 = json.loads(h1).get("data")
    return h2



def get_dailydata(keyword, start, end):
    url = f'https://index.baidu.com/api/SearchApi/index?area=0&word=[[%7B%22name%22:%22{keyword}%22,%22wordType%22:1%7D]]&startDate={start}&endDate={end}'
    res = requests.get(url, headers=headers)
    j = res.json()
    
    uniqid = j.get('data').get('uniqid')
    ptbk = get_ptbk(uniqid)
    data = j.get('data').get('userIndexes')[0].get('all').get('data')
    res = decrypt(ptbk, data)
    return res

# 爬取多人的百度指数并制作成字典
def make_dict(name_list, sy, sm, sd, ey, em, ed):
    start = str(dt.date(sy, sm, sd))
    end = str(dt.date(ey, em, ed))
    data_dict = {}
    for name in name_list:
        print(name+"  loading...")
        try:
            data_dict[name] = get_dailydata(name, start, end).split(',')
        except:
            break
        time.sleep(2)
    return data_dict

data_d = make_dict(name_list, 2021,1,1,2021,5,4)

start = dt.date(2021,1,1)
end = dt.date(2021,5,5)   # 注意：end要比抓取的end日期多一天
day_list = []
for i in range(start.toordinal(), end.toordinal()):
    day_list.append(str(dt.date.fromordinal(i)))

df = pd.DataFrame(data_d, index=day_list)
# 对空白数据进行填充
df.replace('','0',inplace=True)

# 取当前日期和前两天的日期的平均值作为当天的热度值
df_rolling = df.rolling(window=3).mean().round(0)
# 生成表格 根据flourish的需求需要将表格进行处理
df_rolling.transpose().to_excel("百度热度.xls")

3.flourish生成动态排行

将生成的表格导入flourish中，效果图如下图所示：