用Python来分析一波周董新曲《说好不哭》为何如此火爆！

import requests

url = "https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg"

querystring = {"biztype":"1","topid":"237773700","cmd":"8","pagenum":"1","pagesize":"25"}

response = requests.request("GET", url, params=querystring)

print(response.text)

{
    "nick": "丨那壹刻永遠消失\"\"",
    "praisenum": 1,
    "rootcommentcontent": "越听越好听怎么回事！",
    "time": 1568729836,
}

def file_do(list_info, file_name):
    # 获取文件大小
    if not os.path.exists(file_name):
        wb = openpyxl.Workbook()
        page = wb.active
        page.title = 'jay'
        page.append(['昵称','时间','点赞数','评论'])
    else:
        wb = openpyxl.load_workbook(file_name)
        page = wb.active
    for info in list_info:
        try:
            page.append(info)
        except Exception:
            print(info)
    wb.save(filename=file_name)

import requests,json,time,uuid,os,openpyxl
import re
from openpyxl.cell.cell import ILLEGAL_CHARACTERS_RE

info_list = []

def get_comment_info():
    global info_list
    pagenum = 1
    while(True):
        print(pagenum)
        url = "https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg"

        querystring = {"biztype":"1","topid":"237773700","cmd":"8","pagenum":pagenum,"pagesize":"25"}

        response = requests.request("GET", url, params=querystring)

        resp = json.loads(response.text)

        commentlist = resp.get('comment').get('commentlist')

        if not commentlist or len(commentlist) == 0:
            return

        for comment in commentlist:
            info = []
            one_name = comment.get('nick')
            # 将 UNIX 时间戳转化为普通时间格式
            if comment.get('time') < 1568735760:
                return
            time_local = time.localtime(comment.get('time'))
            one_time = time.strftime("%Y-%m-%d %H:%M:%S", time_local)
            one_praisenum = comment.get('praisenum')
            one_comment = comment.get('rootcommentcontent')
            ILLEGAL_CHARACTERS_RE.sub(r'', one_comment)
            ILLEGAL_CHARACTERS_RE.sub(r'', one_name)
            info = [one_name, one_time, one_praisenum, one_comment]
            # print(info)
            info_list.append(info)
        pagenum += 1
            # print(comment.get('nick'))
            # print(comment.get('rootcommentcontent'))
            # print(comment.get('time'))
            # print(comment.get('praisenum'))


def file_do(file_name):
    # 获取文件大小
    if not os.path.exists(file_name):
        wb = openpyxl.Workbook()
        page = wb.active
        page.title = 'jay'
        page.append(['昵称','时间','点赞数','评论'])
    else:
        wb = openpyxl.load_workbook(file_name)
        page = wb.active
    for info in info_list:
        try:
            page.append(info)
        except Exception:
            print(info)
            pass
        continue
    wb.save(filename=file_name)

if __name__ == "__main__":
    file_name = str(uuid.uuid1()) + '.xlsx'
    get_comment_info()
    file_do(file_name)
    print('data has saved in {}'.format(file_name))

# 导入Style类，用于定义样式风格
from pyecharts import Style
import json
# 导入Geo组件，用于生成柱状图
from pyecharts import Bar
# 导入Counter类，用于统计值出现的次数
from collections import Counter

import fileinput,re

# 设置全局主题风格
from pyecharts import configure
configure(global_theme='wonderland')

# 数据可视化
dates = []
comment_text = ""

def render():
    global comment_text
    with open('jay.csv', mode='r', encoding='utf-8') as f:
        rows = f.readlines()
        for row in rows[1:]:
            if row.count(',') != 3:
                continue
            elements = row.split(',')
            user = elements[0]
            date = elements[1]
            if '2019' not in date:
                continue
            like = elements[2]
            comment = elements[3]
            if '2019-09-14' in date:
                dates.append('2019-09-14')
            elif '2019-09-15' in date:
                dates.append('2019-09-15')
            elif '2019-09-16 0' in date or '2019-09-16 1' in date or '2019-09-16 20' in date or '2019-09-16 21' in date:
                dates.append('2019-09-16 0-21')
            elif '2019-09-18' in date:
                continue
            else:
                dates.append(date)
            comment_text += comment

    with open("comment_text.txt","w", encoding='utf-8') as f:
        f.write(comment_text)

    date_data = Counter(dates).most_common()
    # 按日期进行排序
    date_data = sorted(date_data)
    # print(data)

    # 根据评分数据生成柱状图
    bar = Bar('评价人数走势图', '数据来源：QQ音乐网页版',
              title_pos='center', width=800, height=600)
    attr, value = bar.cast(date_data)
    bar.add('', attr, value, is_visualmap=False, visual_range=[0, 3500], visual_text_color='#fff', is_more_utils=True,
            xaxis_interval=0, xaxis_rotate=30,is_label_show=True,xaxis_label_textsize=8, label_text_size=8)

    bar.render(
        'picture\评价人数走势图.html')

render()