Python爬虫数据可视化分析大作业海量电影数据分析及可视化项目（95分以上）.zip

from datetime import datetime import numpy as np import pandas as pd import requests import json from sklearn.linear_model import LinearRegression # 线性回归 from sklearn.impute import SimpleImputer def recently(): url = "https://ys.endata.cn/enlib-api/api/movie/getMovie_BoxOffice_Day_Chart.do" header = { "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.82 Safari/537.36', "Cookie": 'JSESSIONID=b2685bfa-aa4f-4359-ae96-57befaf8d1ec; route=4e39643a15b7003e568cadd862137cf3; Hm_lvt_82932fc4fc199c08b9a83c4c9d02af11=1649834963,1649852471,1649859039,1649900037; Hm_lpvt_82932fc4fc199c08b9a83c4c9d02af11=1649917933' } post_BoxOffice_Day_data = { 'r': 0.7572955414768414, 'datetype': 'Day', 'date': datetime.now().strftime('%Y-%m-%d'), 'sdate': datetime.now().strftime('%Y-%m-%d'), 'edate': datetime.now().strftime('%Y-%m-%d'), 'bserviceprice': 1 } res = requests.post(url, headers=header, data=post_BoxOffice_Day_data).text json_data = json.loads(res) data0 = json_data['data']['table0'] data1 = json_data['data']['table1'] movie_rank = [] movie_details_MovieName = [] movie_details_BoxOffice = [] movie_details_ShowCount = [] movie_details_AudienceCount = [] movie_details_Attendance = [] movie_percent_BoxOfficePercent = [] movie_percent_ShowCountPercent = [] movie_percent_AudienceCountPercent = [] movie_city1_BoxOffice = [] movie_city1_ShowCount = [] movie_city1_AudienceCount = [] movie_city2_BoxOffice = [] movie_city2_ShowCount = [] movie_city2_AudienceCount = [] movie_city3_BoxOffice = [] movie_city3_ShowCount = [] movie_city3_AudienceCount = [] movie_city4_BoxOffice = [] movie_city4_ShowCount = [] movie_city4_AudienceCount = [] movie_others_BoxOffice = [] movie_others_ShowCount = [] movie_others_AudienceCount = [] for i in range(10): movie_rank.append(data0[i]['Irank']) movie_details_MovieName.append(data0[i]['MovieName']) movie_details_BoxOffice.append(data0[i]['BoxOffice']) movie_details_ShowCount.append(data0[i]['ShowCount']) movie_details_AudienceCount.append(data0[i]['AudienceCount']) movie_details_Attendance.append(data0[i]['Attendance']) movie_percent_BoxOfficePercent.append(data0[i]['BoxOfficePercent']) movie_percent_ShowCountPercent.append(data0[i]['ShowCountPercent']) movie_percent_AudienceCountPercent.append(data0[i]['AudienceCountPercent']) movie_city1_BoxOffice.append(data1[i * 5]['BoxOffice']) movie_city1_ShowCount.append(data1[i * 5]['ShowCount']) movie_city1_AudienceCount.append(data1[i * 5]['AudienceCount']) movie_city2_BoxOffice.append(data1[i * 5 + 1]['BoxOffice']) movie_city2_ShowCount.append(data1[i * 5 + 1]['ShowCount']) movie_city2_AudienceCount.append(data1[i * 5 + 1]['AudienceCount']) movie_city3_BoxOffice.append(data1[i * 5 + 2]['BoxOffice']) movie_city3_ShowCount.append(data1[i * 5 + 2]['ShowCount']) movie_city3_AudienceCount.append(data1[i * 5 + 2]['AudienceCount']) movie_city4_BoxOffice.append(data1[i * 5 + 3]['BoxOffice']) movie_city4_ShowCount.append(data1[i * 5 + 3]['ShowCount']) movie_city4_AudienceCount.append(data1[i * 5 + 3]['AudienceCount']) movie_others_BoxOffice.append(data1[i * 5 + 4]['BoxOffice']) movie_others_ShowCount.append(data1[i * 5 + 4]['ShowCount']) movie_others_AudienceCount.append(data1[i * 5 + 4]['AudienceCount']) top10_data = pd.DataFrame({ "影片排名": movie_rank, "影片名称": movie_details_MovieName, "影片票房": movie_details_BoxOffice, "影片场次": movie_details_ShowCount, "影片人次": movie_details_AudienceCount, "上座率": movie_details_Attendance, "影片票房占比": movie_percent_BoxOfficePercent, "影片场次占比": movie_percent_ShowCountPercent, "影片人次占比": movie_percent_AudienceCountPercent, "一线城市票房": movie_city1_BoxOffice, "一线城市场次": movie_city1_ShowCount, "一线城市人次": movie_city1_AudienceCount, "二线城市票房": movie_city2_BoxOffice, "二线城市场次": movie_city2_ShowCount, "二线城市人次": movie_city2_AudienceCount, "三线城市票房": movie_city3_BoxOffice, "三线城市场次": movie_city3_ShowCount, "三线城市人次": movie_city3_AudienceCount, "四线城市票房": movie_city4_BoxOffice, "四线城市场次": movie_city4_ShowCount, "四线城市人次": movie_city4_AudienceCount, "其它票房": movie_others_BoxOffice, "其它场次": movie_others_ShowCount, "其它人次": movie_others_AudienceCount }) print(top10_data) top10_data.to_csv("data/top10_data.csv", encoding='gbk', index=False) def showing(): header = { "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.82 Safari/537.36', "Cookie": 'JSESSIONID=edf01a0d-deae-4143-9071-2e7eda2c5055; route=4e39643a15b7003e568cadd862137cf3; Hm_lvt_82932fc4fc199c08b9a83c4c9d02af11=1649859039,1649900037,1649983572,1649988152; Hm_lpvt_82932fc4fc199c08b9a83c4c9d02af11=1650016413' } url_total = "https://ys.endata.cn/enlib-api/api/movie/getMovie_BoxOffice_Day_List.do" total_post_data = { 'r': 0.08330054546930543, 'datetype': 'Day', 'date': datetime.now().strftime('%Y-%m-%d'), 'sdate': datetime.now().strftime('%Y-%m-%d'), 'edate': datetime.now().strftime('%Y-%m-%d'), 'bserviceprice': 1, 'columnslist': '100,102,103,119,105,107,109,106,112,129,142,143,163,164,165', 'pageindex': 1, 'pagesize': 20, 'order': 103, 'ordertype': 'desc', } total_res = requests.post(url_total, headers=header, data=total_post_data).text total_json_data = json.loads(total_res) pagesize = total_json_data['data']['table2'][0]['TotalCounts'] total_post_data = { 'r': 0.08330054546930543, 'datetype': 'Day', 'date': datetime.now().strftime('%Y-%m-%d'), 'sdate': datetime.now().strftime('%Y-%m-%d'), 'edate': datetime.now().strftime('%Y-%m-%d'), 'bserviceprice': 1, 'columnslist': '100,102,103,119,105,107,109,106,112,129,142,143,163,164,165', 'pageindex': 1, 'pagesize': pagesize, 'order': 103, 'ordertype': 'desc', } total_res = requests.post(url_total, headers=header, data=total_post_data).text total_json_data = json.loads(total_res)['data']['table1'] print(total_json_data) movies_rank = [] movies_MovieName = [] movies_BoxOffice = [] movies_ReleaseDate = [] movies_TotalBoxOffice = [] movies_ShowCount = [] movies_AudienceCount = [] movies_BoxOfficePercent = [] movies_ReleaseDay = [] movies_ShowDay = [] movies_HjBoxOffice = [] movies_HjShowCount = [] movies_HjBoxOfficePercent = [] movies_HjShowCountPercent = [] movies_HjAudienceCountPercent = [] movies_MaoYanWantToSee = [] movies_TaoPiaoPiaoWantToSee = [] movies_DouBanWantToSee = [] for i in range(pagesize): if total_json_data[i]['EntMovieID'] != 0: movies_rank.append(total_json_data[i]['Irank']) movies_MovieName.append(total_json_data[i]['MovieName']) movies_BoxOffice.append(total_json_data[i]['BoxOffice']) movies_ReleaseDate.append(total_json_data[i]['ReleaseDate']) movies_TotalBoxOffice.append(total_json_data[i]['TotalBoxOffice']) movies_ShowCount.append(total_json_data[i]['ShowCount']) movies_AudienceCount.append(total_json_data