爬取猫眼票房数并数据可视化

时间：03-29来源：作者：点击数：35

我发现猫眼有个移动端某页接口，获取的json的，获取数据也是更新的，链接：http://piaofang.maoyan.com/getBoxList?date=1&isSplit=true，去掉接口后你会发现就是字体加密反爬的猫眼专业版，数据就是json格式

我们就利用json模块进行抓取这个网页数据存入csv做数据可视化

我们先发送请求获取数据

class Maoyan(object):
    # 初始化数据
    def __init__(self):
        self.url = 'http://piaofang.maoyan.com/getBoxList?date=1&isSplit=true'
        self.header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                          'Chrome/87.0.4280.88 Safari/537.36 '
        }

    # 获取数据
    def get_data(self):
        response = requests.get(url=self.url, headers=self.header)
        return response.content

我们直接返回content，接下来就是解析数据，我们就把这个content，用json模块解析，loads一个字典方便取值：

# 解析数据
    def parse_data(self, response):
        data = json.loads(response)
        data_list = data['boxOffice']["data"]["list"]
        datas = list()
        for main_data in data_list:
            temp = {}
            temp["电影ID"] = main_data['movieInfo']["movieId"]
            temp["电影名称"] = main_data['movieInfo']["movieName"]
            temp["综合票房"] = main_data['sumBoxDesc']
            temp["综合票房占比"] = main_data['boxRate']
            temp["排片占比"] = main_data['showCountRate']
            temp["排坐占比"] = main_data['seatCountRate']
            datas.append(temp)
        return datas

最后我们保存csv，后续我们进行数据可视化，先保存，代码如下：

 def save_data(self, datas):
        for data in datas:
            csv_writer.writerow([data["电影ID"], data["电影名称"], data["综合票房"], data["综合票房占比"], data["排片占比"], data["排坐占比"]])

整体代码如下：

import requests
import json
import csv


class Maoyan(object):
    # 初始化数据
    def __init__(self):
        self.url = 'http://piaofang.maoyan.com/getBoxList?date=1&isSplit=true'
        self.header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                          'Chrome/87.0.4280.88 Safari/537.36 '
        }

    # 获取数据
    def get_data(self):
        response = requests.get(url=self.url, headers=self.header)
        return response.content

    # 解析数据
    def parse_data(self, response):
        data = json.loads(response)
        data_list = data['boxOffice']["data"]["list"]
        datas = list()
        for main_data in data_list:
            temp = {}
            temp["电影ID"] = main_data['movieInfo']["movieId"]
            temp["电影名称"] = main_data['movieInfo']["movieName"]
            temp["综合票房"] = main_data['sumBoxDesc']
            temp["综合票房占比"] = main_data['boxRate']
            temp["排片占比"] = main_data['showCountRate']
            temp["排坐占比"] = main_data['seatCountRate']
            datas.append(temp)
        return datas

    # 保存数据
    def save_data(self, datas):
        for data in datas:
            csv_writer.writerow([data["电影ID"], data["电影名称"], data["综合票房"], data["综合票房占比"], data["排片占比"], data["排坐占比"]])

    def run(self):
        response = self.get_data()
        datas = self.parse_data(response)
        self.save_data(datas)


if __name__ == '__main__':
    head = ["电影ID", "电影名称", "综合票房", "综合票房占比", "排片占比", "排坐占比"]
    with open('猫眼.csv', 'a', newline='', encoding="gb18030") as f:
        csv_writer = csv.writer(f)
        csv_writer.writerow(head)
    maoyan = Maoyan()
    maoyan.run()

由于票房单位不统一，我们存下来的csv，我就手动修改了下，单位不用，有的亿，有的万，这里我就直接用excel进行修改了，把亿全修改成了万单位

我们用matplotlib，pandas， numpy 模块进行数据可视化，先读取数据

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

movie = pd.read_csv("./movie.csv",encoding = "gbk",index_col=0)

获取电影名称

movie_name = movie["电影名称"].values

这里我们获取下电影的个数，因为使用matplotlib绘图的时候，x_ticks,y_ticks不能以文字开头

num = int(len(movie_name))

获取票房那一列

movie_num = movie["综合票房"].values

绘制柱状图

movie_name = movie_name
x = range(len(movie_name))
y = movie_num
plt.figure(figsize=(20,15),dpi=100)
plt.bar(x, y, width=0.8, color=['b','r','g','y','c','m','y','k','c','g','b'],align="center")
plt.xticks(x,movie_name,fontsize=12,rotation=-90)

plt.grid(linestyle="--", alpha=0.5)
plt.title("2020年12月电影票房收入对比",fontsize=25)
plt.xlabel("票房名称",fontsize=28)
plt.ylabel("电影数量",fontsize=25)
plt.savefig('./2.png')
plt.show()

横向柱状图

movie_name = movie_name
x = range(len(movie_name))
y = movie_num
plt.figure(figsize=(20,8),dpi=100)
plt.barh(x, y, color=['b','r','g','y','c','m','y','k','c','g','b'],align="center",height=0.8)
plt.yticks(x,movie_name,fontsize=15)

plt.grid(linestyle="-.", alpha=0.5)
plt.title("2020年12月电影院票房统计",fontsize=24)
plt.xlabel("票房数量",fontsize=28)
plt.ylabel("电影名称",fontsize=25)
plt.savefig("./1.png")
plt.show()

饼状图


movie_name = movie_name
labels = range(len(movie_name))
x = movie_num
color=['#336633','#CCCC00','#0066CC','#CC0033','#003399','#CC99CC','#333366','#FFFF66','#6699CC','#FF6600','#CC6600']
plt.figure(figsize=(15,14),dpi=100)
patches,l_text,p_text = plt.pie(x,labels=movie_name,autopct="%1.2f%%",startangle=100,pctdistance=0.7,radius=1,colors=color,explode=(0.1,0,0,0,0,0,0,0,0,0.2,0,0,0,0.2,0,0,0,0.3,0.3,0.2,0,0.2,0.1,0,0.05))
for l in l_text:
    l.set_size(10)
for p in p_text:
    p.set_size(5)
plt.grid()
plt.legend(loc=1,ncol=2)
plt.title("2020年12月各电影占比",fontsize=28)
plt.savefig("./3.png")
plt.show()

我把电影名称单独拿出来了，保存到了txt，对电影名称生成词云

import jieba
import matplotlib.pyplot as plt
from wordcloud import WordCloud

with open('./词云.txt','r',encoding="utf-8") as f:
    data = f.read()
    data_list = jieba.cut(data,cut_all=True)
    data_text = ','.join(data_list)
    wordcloud = WordCloud(
        font_path=r'./msyh.ttc',
        background_color="white",width=1000,height=1000
    ).generate(data_text)
plt.imshow(wordcloud,interpolation="bilinear")
plt.axis("off")
plt.savefig('./2.jpg')
plt.show()