2018年全国电影票房分析图

2018年全国电影票房分析图

2018年即将过去，在这一年中，我们遇到了很多牛逼的电影，他们的数据怎么样呢？就看看一下数据吧。

影院数据为每日票房排名前10的影院，院线数据为每日票房排名前10的院线，城市数据为每日票房排名前10的城市，影片数据为每日票房排名前10的影片。故数据有很多缺失（爬取的目标网站就这么多数据，哈哈）

1，数据的抓取

使用Python+requests抓取数据，保存数据为csv，简单方便，代码如下

# encoding=utf-8

import requests
import time
import json
from datetime import datetime, timedelta


def download(date):
    '''
    download data
    :param date:
    :return:
    '''
    url = "https://zgdypw.cn/pors/w/webStatisticsDatas/api/{}/searchDayBoxOffice".format(date)
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
        "Cache-Control": "no-cache",
        "Connection": "keep-alive",
        "Host": "zgdypw.cn",
        "Pragma": "no-cache",
        "Referer": "https://zgdypw.cn/",
        "User-Agent": "Mozilla/5.0(Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
    }
    proxies = {
        "http": "****",
        "https": "****",
    }
    response = requests.get(url, headers=headers, proxies=proxies)
    response.encoding = "utf-8"
    if response.status_code == 200:
        data = json.loads(response.text)["data"]
        # total
        dayBoxOffice = data["dayBoxOffice"]
        with open("dayBoxOffice.csv", "a+", encoding="utf-8") as file:
            file.write("{0},{1},{2},{3},{4}\n".format(
                dayBoxOffice["businessDay"],
                dayBoxOffice["cinemaCount"],
                dayBoxOffice["totalAudience"],
                dayBoxOffice["totalBoxoffice"],
                dayBoxOffice["totalSession"],
            ))
        # CinemaChains
        top10CinemaChains = data["top10CinemaChains"]
        with open("top10CinemaChains.csv", "a+", encoding="utf-8") as file:
            for item in top10CinemaChains:
                file.write("{0},{1},{2},{3},{4},{5}\n".format(
                    date,
                    item["cinemaChainName"],
                    item["dayAudience"],
                    item["daySession"],
                    item["rank"],
                    item["totalSales"],
                ))
        # Cinemas
        top10Cinemas = data["top10Cinemas"]
        with open("top10Cinemas.csv", "a+", encoding="utf-8") as file:
            for item in top10Cinemas:
                file.write("{0},{1},{2},{3},{4},{5}\n".format(
                    date,
                    item["cinemaName"],
                    item["dayAudience"],
                    item["daySession"],
                    item["rank"],
                    item["totalSales"],
                ))
        # Citys
        top10Citys = data["top10Citys"]
        with open("top10Citys.csv", "a+", encoding="utf-8") as file:
            for item in top10Citys:
                file.write("{0},{1},{2},{3},{4},{5}\n".format(
                    date,
                    item["cityName"],
                    item["dayAudience"],
                    item["daySession"],
                    item["rank"],
                    item["totalSales"],
                ))
        # Films
        top10Films = data["top10Films"]
        with open("top10Films.csv", "a+", encoding="utf-8") as file:
            for item in top10Films:
                file.write("{0},{1},{2},{3},{4},{5}\n".format(
                    date,
                    item["filmName"],
                    item["dayAudience"],
                    item["daySession"],
                    item["rank"],
                    item["daySales"],
                    item["filmTotalSales"],
                ))
        pass
    pass


if __name__ == "__main__":
    start = datetime(year=2018, month=1, day=31)
    end = datetime.now()

    days = 0
    tem = start + timedelta(days=days)
    while tem <= end:
        print(tem.strftime("%Y-%m-%d"))
        download(tem.strftime("%Y-%m-%d"))
        days += 1
        tem = start + timedelta(days=days)

2，数据展示

1)全国票房数据

每日的票房曲线

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from datetime import datetime,timedelta
import time


df = pd.read_csv("dayBoxOffice.csv")
df["date"] = pd.to_datetime(df["date"])
df.set_index("date",inplace=True)

# 每日的票房曲线图
plt.figure(figsize=(20,8),dpi=80)

data = df["totalBoxoffice"]
_x = data.index
_x = [row.strftime("%Y-%m-%d") for row in _x]
_y = data.values
plt.plot(range(len(_x)),_y)

interval = 7
last = time.strftime("%Y-%m-%d",time.localtime(time.mktime(time.strptime(_x[-1], "%Y-%m-%d")) + interval * 24 * 60 * 60))
plt.xticks(range(0,len(_x)+interval,interval),(_x+[last])[::interval],rotation=45)

plt.xlabel("日期")
plt.ylabel("票房(单位:万)")
plt.title("2018年电影每日票房图")

plt.grid()
plt.show()

显示的图片

2，每日的观影人次曲线图

# 每日的人次曲线图
plt.figure(figsize=(20,8),dpi=80)

data = df["totalAudience"]
_x = data.index
_x = [row.strftime("%Y-%m-%d") for row in _x]
_y = data.values.astype(int)/10000
plt.plot(range(len(_x)),_y)

interval = 7
last = time.strftime("%Y-%m-%d",time.localtime(time.mktime(time.strptime(_x[-1], "%Y-%m-%d")) + interval * 24 * 60 * 60))
plt.xticks(range(0,len(_x)+interval,interval),(_x+[last])[::interval],rotation=45)

plt.xlabel("日期")
plt.ylabel("人次(单位:万)")
plt.title("2018年电影每日观影人次图")

plt.grid()
plt.show()

从上图可以看出，节假日周六周日的观影人次确实比工作日高出很多。

3，城市票房占全国票房的百分比

等等，图标数据很多，详细数据可以看源码运行。

2018电影票房分析（numpy,pandas,matplotlib）

欢迎吐槽