def get_day_boxoffice(day=None):
if day == None:
result = ts.day_boxoffice().to_json()
else:
try:
result = ts.day_boxoffice(day).to_json()
except Exception as e:
result = json.dumps({
"error":
True,
"message":
"can not get the data, format date as YYYY-M-D"
})
return result
def job_9():
try:
print("I'm working......电影票房")
# 实时票房
realtime_boxoffice = ts.realtime_boxoffice()
data = pd.DataFrame(realtime_boxoffice)
data.to_sql('realtime_boxoffice',engine,index=True,if_exists='replace')
print("实时票房......done")
# 每日票房
day_boxoffice = ts.day_boxoffice()
data = pd.DataFrame(day_boxoffice)
data.to_sql('day_boxoffice',engine,index=True,if_exists='replace')
print("每日票房......done")
# 月度票房
month_boxoffice = ts.month_boxoffice()
data = pd.DataFrame(month_boxoffice)
data.to_sql('month_boxoffice',engine,index=True,if_exists='replace')
print("月度票房......done")
# 影院日度票房
day_cinema = ts.day_cinema()
data = pd.DataFrame(day_cinema)
data.to_sql('day_cinema',engine,index=True,if_exists='replace')
print("影院日度票房......done")
except Exception as e:
print(e)
def get_day_boxoffice(day=None):
if day == None:
total = ts.day_boxoffice().to_csv().split()
head = [TRANS.get(i) for i in total[0].split(",")]
body = [line.split(",") for line in total[1:]]
result = {"head": head, "body": body}
else:
try:
total = ts.day_boxoffice(day).to_csv().split()
head = [TRANS.get(i) for i in total[0].split(",")]
body = [line.split(",") for line in total[1:]]
result = {"head": head, "body": body}
except Exception as e:
result = {
"error": True,
"message": "can not get the data, format date as YYYY-M-D"
}
return result
def day_boxoffice(engine, cdate):
tbl = "day_boxoffice"
tsl.log(tbl + " start...")
try:
df = ts.day_boxoffice()
df['date'] = cdate - datetime.timedelta(days=1)
df.to_sql(tbl, engine, if_exists='append')
tsl.log(tbl + " done")
except BaseException, e:
print e
tsl.log(tbl + " error")
def get_day_boxoffice(date=None):
df = ts.day_boxoffice(date)
if df is not None:
if date is None:
date = get_yesterday()
df.insert(0, 'date', date)
res = df.to_sql(fun_day_box_office, engine, if_exists='replace')
msg = 'ok' if res is None else res
print('获取指定单日:{0} 电影票房数据: {1} '.format(date, msg) + '\n')
else:
print('获取指定单日:{0} 电影票房数据: {1} '.format(date, 'None') + '\n')
def today_box_office():
df = ts.day_boxoffice()
f.write('\n### 当日票房\n\n')
table_head = '|影片名|排名|单日票房(万)|累计票房(万)|上映天数|\n|-|-|-|-|-|\n'
f.write(table_head)
for i in range(len(df)):
txt = '|' + df['MovieName'][i] + '|' + df['IRank'][i] + '|' + df['BoxOffice'][i] + '|' + \
df['SumBoxOffice'][i] + '|' + df['MovieDay'][i] + '|\n'
f.write(txt)
pass
f.write('\n\n')
pass
def updateDayBoxoffice(con, date: datetime):
import share.model.dao.boxoffice.DayBoxoffice as Model
dateString = date.strftime("%Y-%m-%d")
logging.debug("Updating day boxoffice of {}".format(dateString))
df = ts.day_boxoffice(date=dateString,retry_count=16)
res = []
for _, row in df.iterrows():
obj = Model.rowToORM(row, date=date)
if obj is not None:
res.append(obj)
Base.metadata.create_all(con.engine)
con.save_all(res)
return
def capture_stock_data():
capture_date = datetime.datetime.now().strftime("%Y%m%d")
save_dir = "/home/dandelion/stock_data/" + capture_date
if not os.path.exists(save_dir):
os.mkdir(save_dir)
print("The save directory is created successfully!\n", save_dir)
print("The save directory is already exist!\n", save_dir)
# ======================Daily Command================================================================
# get the boxoffcie data of the last day and save as csvfile named as the capture command
ts.day_boxoffice().to_csv(
save_dir + "/" + capture_date + "_day_boxoffice.csv",
header=True,
sep=",",
index=False,
)
print("day_boxoffice data capture completed!")
# get the cinema data of the last day and save as csvfile named as the capture command
ts.day_cinema().to_csv(
save_dir + "/" + capture_date + "_day_cinema.csv",
header=True,
sep=",",
index=False,
)
print("day_cinema data capture completed!")
ts.month_boxoffice().to_csv(
save_dir + "/" + capture_date + "_month_boxoffice.csv",
header=True,
sep=",",
index=False,
)
print("month_boxoffice data capture completed!")
ts.realtime_boxoffice().to_csv(
save_dir + "/" + capture_date + "_realtime_boxoffice.csv",
header=True,
sep=",",
index=False,
)
print("realtime_boxoffice data capture completed!")
# get the stock data index of the last day and save as csvfile named as the capture command
ts.get_index().to_csv(
save_dir + "/" + capture_date + "_get_index.csv",
header=True,
sep=",",
index=False,
)
print("get_index data capture completed!")
# get the history cpi data and save as csvfile named as the capture command
ts.get_cpi().to_csv(
save_dir + "/" + capture_date + "_get_cpi.csv",
header=True,
sep=",",
index=False,
)
print("get_cpi data capture completed!")
# get the history gdp data by month and save as csvfile named as the capture command
ts.get_gdp_year().to_csv(
save_dir + "/" + capture_date + "_get_gdp_year.csv",
header=True,
sep=",",
index=False,
)
print("get_gdp_year data capture completed!")
# get today all stock data and save as csvfile named as the capture command
# ts.get_today_all().to_csv(save_dir+'/'+capture_date+'_get_today_all.csv',header=True,sep=',',index=False)
# get detail information of the top brokers today and save as csvfile named as the capture command
ts.broker_tops().to_csv(
save_dir + "/" + capture_date + "_broker_tops.csv",
header=True,
sep=",",
index=False,
)
print("broker_tops data capture completed!")
# get detail information of the top brokers today and save as csvfile named as the capture command
ts.cap_tops().to_csv(
save_dir + "/" + capture_date + "_cap_tops.csv",
header=True,
sep=",",
index=False,
)
print("cap_tops data capture completed!")
ts.get_area_classified().to_csv(
save_dir + "/" + capture_date + "_get_area_classified.csv",
header=True,
sep=",",
index=False,
)
print("get_area_classified data capture completed!")
# ts.get_balance_sheet(code='').to_csv(save_dir+'/'+capture_date+'_get_balance_sheet.csv',header=True,sep=',',index=False)
# print('get_balance_sheet data capture completed!')
# ts.get_cash_flow(code='').to_csv(save_dir+'/'+capture_date+'_get_cash_flow.csv',header=True,sep=',',index=False)
# print('get_cash_flow data capture completed!')
ts.get_day_all().to_csv(
save_dir + "/" + capture_date + "_get_day_all.csv",
header=True,
sep=",",
index=False,
)
print("get_day_all data capture completed!")
ts.get_cashflow_data(2018, 3).to_csv(
save_dir + "/" + capture_date + "_get_cashflow_data.csv",
header=True,
sep=",",
index=False,
)
print("get_cashflow_data data capture completed!")
ts.get_concept_classified().to_csv(
save_dir + "/" + capture_date + "_get_concept_classified.csv",
header=True,
sep=",",
index=False,
)
print("get_concept_classified data capture completed!")
ts.get_debtpaying_data(2018, 3).to_csv(
save_dir + "/" + capture_date + "_get_debtpaying_data.csv",
header=True,
sep=",",
index=False,
)
print("get_debtpaying_data data capture completed!")
ts.get_deposit_rate().to_csv(
save_dir + "/" + capture_date + "_get_deposit_rate.csv",
header=True,
sep=",",
index=False,
)
print("get_deposit_rate data capture completed!")
ts.get_gdp_contrib().to_csv(
save_dir + "/" + capture_date + "_get_gdp_contrib.csv",
header=True,
sep=",",
index=False,
)
ts.get_gdp_for().to_csv(
save_dir + "/" + capture_date + "_get_gdp_for.csv",
header=True,
sep=",",
index=False,
)
ts.get_gdp_pull().to_csv(
save_dir + "/" + capture_date + "_get_gdp_pull.csv",
header=True,
sep=",",
index=False,
)
ts.get_gdp_quarter().to_csv(
save_dir + "/" + capture_date + "_get_gdp_quarter.csv",
header=True,
sep=",",
index=False,
)
print("get_gdp_ data capture completed!")
# ts.get_gdp_year().to_csv(save_dir+'/'+capture_date+'_get_gdp_year.csv',header=True,sep=',',index=False)
ts.get_gem_classified().to_csv(
save_dir + "/" + capture_date + "_get_gem_classified.csv",
header=True,
sep=",",
index=False,
)
ts.get_gold_and_foreign_reserves().to_csv(
save_dir + "/" + capture_date + "_get_gold_and_foreign_reserves.csv",
header=True,
sep=",",
index=False,
)
ts.get_growth_data(2018, 3).to_csv(
save_dir + "/" + capture_date + "_get_growth_data.csv",
header=True,
sep=",",
index=False,
)
ts.get_industry_classified().to_csv(
save_dir + "/" + capture_date + "_get_industry_classified.csv",
header=True,
sep=",",
index=False,
)
ts.get_hs300s().to_csv(
save_dir + "/" + capture_date + "_get_hs300s.csv",
header=True,
sep=",",
index=False,
)
ts.get_sz50s().to_csv(
save_dir + "/" + capture_date + "_get_sz50s.csv",
header=True,
sep=",",
index=False,
)
ts.get_zz500s().to_csv(
save_dir + "/" + capture_date + "_get_zz500s.csv",
header=True,
sep=",",
index=False,
)
ts.get_operation_data(2018, 3).to_csv(
save_dir + "/" + capture_date + "_get_operation_data.csv",
header=True,
sep=",",
index=False,
)
ts.get_stock_basics().to_csv(
save_dir + "/" + capture_date + "_get_stock_basics.csv",
header=True,
sep=",",
index=False,
)
ts.get_report_data(2018, 3).to_csv(
save_dir + "/" + capture_date + "_get_report_data.csv",
header=True,
sep=",",
index=False,
)
ts.inst_detail().to_csv(
save_dir + "/" + capture_date + "_inst_detail.csv",
header=True,
sep=",",
index=False,
)
ts.inst_tops().to_csv(
save_dir + "/" + capture_date + "_inst_tops.csv",
header=True,
sep=",",
index=False,
)
print("inst_tops data capture completed!")
ts.new_stocks().to_csv(
save_dir + "/" + capture_date + "_new_stocks.csv",
header=True,
sep=",",
index=False,
)
print("new_stocks data capture completed!")
ts.top_list().to_csv(
save_dir + "/" + capture_date + "_top_list.csv",
header=True,
sep=",",
index=False,
)
print("top_list data capture completed!")
'''
import datetime
import tushare as ts
from matplotlib import pyplot as plt
boxOffice = []
movieDay = []
# ['2018-05-22', '2018-05-23', '2018-05-24', '2018-05-25', '2018-05-26', '2018-05-27', '2018-05-28', '2018-05-29', '2018-05-30']
begin = datetime.date(2018,5,22)
end = datetime.date(2018,5,30)
d = begin
delta = datetime.timedelta(days=1)
while d <= end:
movieDay.append(d.strftime("%Y-%m-%d"))
d += delta
print(movieDay)
for day in movieDay:
data = ts.day_boxoffice(day)
print(data[:1])
boxOffice.append(data[:1].SumBoxOffice)
print(boxOffice)
plt.plot(movieDay,boxOffice,'o',movieDay,boxOffice,'-')
plt.show()
def data2str(n):
today = datetime.today()
delta = datetime.timedelta(days=n)
start = today - delta
return start.strftime("%Y-%m-%d")
def test_boxoffice_1(self):
bf: pd.DataFrame = ts.realtime_boxoffice()
print(bf)
bf: pd.DataFrame = ts.day_boxoffice()
print(bf)
import tushare as ts
# 实时票房
ts.realtime_boxoffice()
# 每日票房
ts.day_boxoffice() #取上一日的数据
ts.day_boxoffice('2010-01-01') #取指定日期的数据
# 月度票房
ts.month_boxoffice() #取上一月票房数据
ts.month_boxoffice('2019-02') #此月数据
# 影院日度票房
ts.day_cinema() #取上一日全国影院票房排行数据
df = ts.day_cinema('2019-02-05') # 指定日期的数据 2019年春节
df.to_excel('movie.xlsx') # pip install openpyxl
import tushare as ts
from sqlalchemy import create_engine
token = ts.set_token(
'c723069dd4a25402d05ea6afad36da2937111adf012f8258abb5f7e05936e575')
#engine = create_engine('mysql+pymysql://root:[email protected]/packageing?charset=utf8')
engine = create_engine(
'mysql+pymysql://root:[email protected]/gupiao?charset=utf8')
realtime = ts.realtime_boxoffice()
#realtime.to_sql('realtime_boxoffice',engine)
realtime.to_sql('realtime_boxoffice', engine, if_exists='append')
day = ts.day_boxoffice()
#day.to_sql('day_boxoffice',engine)
day.to_sql('day_boxoffice', engine, if_exists='append')
month = ts.month_boxoffice()
#month.to_sql('month_boxoffice',engine)
month.to_sql('month_boxoffice', engine, if_exists='append')
cinema = ts.day_cinema()
#cinema.to_sql('day_cinema',engine)
cinema.to_sql('day_cinema', engine, if_exists='append')
import tushare as ts
# 实时票房
# 获取实时电影票房数据，30分钟更新一次票房数据，可随时调用。
df = ts.realtime_boxoffice()
print(df)
# 每日票房
# 获取单日电影票房数据，默认为上一日的电影票房，可输入参数获取指定日期的票房。
# 似乎只能显示前一日的
df = ts.day_boxoffice("2015-01-01")
print(df)
# 月度票房
# 获取单月电影票房数据，默认为上一月，可输入月份参数获取指定月度的数据。
df = ts.month_boxoffice('2016-12')
print(df)
# 影院日度票房
# 获取全国影院单日票房排行数据，默认为上一日，可输入日期参数获取指定日期的数据。
df = ts.day_cinema('2015-12-24')
print(df)
g_p.index=g_p.month;g_p g_p.plot(); #工业品价格指数 g_p1=g_p[['ppiip','ppi','qm','rmi','pi']].dropna() g_p1.plot(); #生活价格指数 g_p2=g_p[['cg','food','clothing','roeu','dcg']].dropna();g_p2 g_p2.plot(grid=True) ###10.4 电影票房数据的实时分析 #实时票房 #获取实时电影票房数据，30分钟更新一次票房数据，可随时调用。 r_b = ts.realtime_boxoffice() r_b.info() r_b plt.barh(r_b.MovieName,r_b.BoxOffice.astype(float)); plt.pie(r_b.boxPer,labels=r_b.MovieName); #每日票房 d_b = ts.day_boxoffice() #取上一日的数据 d_b #影院日度票房 #获取全国影院单日票房排行数据，默认为上一日，可输入日期参数获取指定日期的数据。 d_c=ts.day_cinema() #取上一日全国影院票房排行数据 d_c.info() d_c[:10] plt.barh(d_c.CinemaName[:10],d_c.Attendance.astype(float)[:10]);
def get_today_all():
"""获取单日电影票房数据"""
df = ts.day_boxoffice()
print df
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import tushare as ts
df_film = ts.realtime_boxoffice()
print(df_film)
df_film_date = ts.day_boxoffice('2017-05-17')
print(df_film_date)
def GetDayBoxOffice():
df = ts.day_boxoffice()
df = df.to_json(force_ascii=False)
print(df)
return df
def reset_tables():
origin_html = ts.day_boxoffice()
origin_html = pd_to_bootstraptabels(origin_html)
return origin_html
boxoffice_record = {}
for i in range(3):
boxoffice_record[movie_names[i]] = []
print(boxoffice_record)
# 取每部电影最近7天的票房信息
date_record = []
for i in range(7):
# 计算7天的日期
current = str(today + datetime.timedelta(days=i) -
datetime.timedelta(days=7))
# 写入记录日期用的数据结构
print(current)
date_record.append(current)
# 获取单日的电影票房信息
single_day_boxoffice = ts.day_boxoffice(current)
# 对当日结果的检查，如果top3中有电影在当日没有被查询到，则认为当日没有票房，记为0
# 反之，则将票房数据记录到预设的dict中
for j in range(len(movie_names)):
movie_boxoffice = boxoffice_record[movie_names[j]]
top3_movie = single_day_boxoffice[single_day_boxoffice['MovieName'] ==
movie_names[j]]
if top3_movie.empty:
movie_boxoffice.append(0)
else:
movie_boxoffice.append(float(top3_movie['BoxOffice']))
# 绘图
# 汇总日期与票房，方便后续绘图方便
days = np.arange(7)
boxoffices = np.array(
import datetime
import tushare as ts
import numpy as np
from scipy import signal
from matplotlib import pyplot as plt
from matplotlib.font_manager import FontProperties
'''
3、请使用tushare模块提供的api并结合numpy、scipy等模块，
获取前一天电影排行数据中上映天数大于7中日平均票价最高的电影，
分析该电影近一个星期的票房及电影票价的走势，
要求分别绘制出票房走势和平均票价走势
'''
today = datetime.date.today()
delta = datetime.timedelta(days=1)
yesterday = (today - delta).strftime("%Y-%m-%d")
data = ts.day_boxoffice(yesterday)
movieDay, movieName, moviePrice = data.MovieDay, data.MovieName, data.AvgPrice
#获取需要分析的电影的名称
targetMovieName = None
tmpMoviePrice = 0
#通过循环，找到上映天数大于7天并且平均票价最高的电影
for name, day, price in zip(movieName, movieDay, moviePrice):
if int(day) > 7:
if tmpMoviePrice < int(price):
tmpMoviePrice = int(price)
targetMovieName = name
def date2num(n):
today = datetime.date.today()
delta = datetime.timedelta(days=n)
# -*- coding: utf-8 -*-
import tushare as ts
'''
获取单日电影票房数据，默认为上一日的电影票房，可输入参数获取指定日期的票房。
参数说明：
date: 日期（YYYY-MM-DD）,默认为上一日
返回值说明：
AvgPrice 平均票价
AvpPeoPle 场均人次
BoxOffice 单日票房（万）
BoxOffice_Up 环比变化 （%）
IRank 排名
MovieDay 上映天数
MovieName 影片名
SumBoxOffice 累计票房（万）
WomIndex 口碑指数
'''
## #取上一日的数据
data = ts.day_boxoffice('2018-01-01')
print(data)
#df = ts.day_boxoffice('2015-12-24') #取指定日期的数据