def get_month_boxoffice(month=None):
if month == None:
result = ts.month_boxoffice().to_json()
else:
try:
result = ts.month_boxoffice(month).to_json()
except Exception as e:
result = json.dumps({"error":True,"message":"can not get the data, format date as YYYY-M"})
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_movie():
movies = []
for m in range(1,11):
df = ts.month_boxoffice('2018-'+str(m))
movies.append(df)
res = pd.concat(movies)
return res
def month_boxoffice(engine, ddate=None):
tbl = "month_boxoffice"
tsl.log(tbl + " start...")
try:
df = ts.month_boxoffice(ddate)
df['date'] = ddate
df.to_sql(tbl, engine, if_exists='append')
tsl.log(tbl + " done")
except BaseException, e:
print e
tsl.log(tbl + " error")
def month_box_office():
df = ts.month_boxoffice()
f.write('\n### 月度票房\n\n')
table_head = '|影片名|排名|上映日期|单月票房(万)|口碑指数|\n|-|-|-|-|-|\n'
f.write(table_head)
for i in range(len(df)):
txt = '|' + df['MovieName'][i] + '|' + df['Irank'][i] + '|' + df['releaseTime'][i] + '|' + \
df['boxoffice'][i] + '|' + df['WomIndex'][i] + '|\n'
f.write(txt)
pass
pass
def get_month_boxoffice(date=None):
df = ts.month_boxoffice(date)
if df is not None:
if date is None:
date = get_last_month()
df.insert(0, 'date', date)
res = df.to_sql(fun_month_box_office, engine, if_exists='replace')
msg = 'ok' if res is None else res
print('获取单月份：{0} 电影票房数据: {1} '.format(date, msg) + '\n')
else:
print('获取单月份：{0} 电影票房数据: {1} '.format(date, 'None') + '\n')
def monthly_box_office(year):
DTS=[]
mbo_path='D:\\ts\\box_office\monthly_boxoffice_%s.csv'%year
for month in range(12):
preDTS=ts.month_boxoffice('%s-%s'%(year,month+1))
preDTS['month']=month+1
DTS.append(preDTS)
DTS=pd.concat(DTS)
if os.path.exists(mbo_path ):
DTS.to_csv(mbo_path, encoding='gbk',mode='a',header=None)
else:
DTS.to_csv(mbo_path, encoding='gbk')
def updateMonthBoxoffice(con, year: int, month: int):
import share.model.dao.boxoffice.MonthBoxoffice as Model
dateString = "{year:04d}-{month:02d}".format(year=year,month=month)
logging.debug("Updating month bboxoffice of {}".format(dateString))
df = ts.month_boxoffice(date=dateString,retry_count=16)
res = []
for _, row in df.iterrows():
obj = Model.rowToORM(row, year=year, month=month)
if obj is not None:
res.append(obj)
Base.metadata.create_all(con.engine)
con.save_all(res)
return
def month_boxoffice(month):
"""
查询当月票房
@param month: 查询月份YYYY-M
@return: 指定月份的票房信息
"""
# 文件路径
file_path = './cache/ts/ts_month_boxoffice_%s.csv' % month
# 如果存在数据文件，则直接读取
if os.path.exists(file_path):
logcm.print_info('读取缓存数据...')
# 读取文件
df_month = pd.read_csv(file_path)
else:
# 取得票房数据
df_month = ts.month_boxoffice(month)
# 保存到文件
df_month.to_csv(file_path, index=False)
return df_month
import tushare as ts
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
df = ts.month_boxoffice('2017-8')
colors = ['red', 'yellow', 'blue']
print df['boxoffice']
pie = plt.pie(df['boxoffice'],
labels=df['MovieName'],
autopct='%1.1f%%',
startangle=0,
colors=colors)
plt.axis('equal')
plt.show()
#data=pd.read_csv('1.txt',sep='\t')
#print data
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)
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!")
for i in range(aaa.shape[0]):
print(aaa.iloc[i,1])
print("aaa result={result}".format(result=aaa[i,1]))
df=pd.DataFrame(columns=['month','cpi'])
for i in range(aaa.shape[0]):
gap=pd.DataFrame({"month":aaa.iloc[i,0],"cpi":(aaa.iloc[i,1].astype(float)-bbb.astype(float))})
df=df.append(gap)
#票房数据
piaofang=ts.day_cinema('2017-10-02')
pd.set_option
pd.set_option('display.max_columns', 200)
pd.set_option('display.width', 1000)
piaofang[piaofang['price'].max()]
rl_piaofang=ts.realtime_boxoffice()
last_m_pf=ts.month_boxoffice('2017-07')
piaofang_df=pd.DataFrame()
def GetMonthBoxOffice():
df = ts.month_boxoffice()
df = df.to_json(force_ascii=False)
print(df)
return df
#b=[3,6,7,4,8,3,7,3,7]
#a = [(1,3,4,5),(2,6,8,5),(4,8,6,9)]
import tushare as ts
import pandas as pd
import matplotlib.pyplot as plt
x = []
y = []
for year in range(2013, 2019):
for m in range(1, 13):
mstr = str(m).zfill(2)
ymstr = str(year) + '-' + str(mstr)
if ymstr == '2018-02':
break
df = ts.month_boxoffice(ymstr)
sum = 0
for i in range(11):
sum += int(df['boxoffice'][i])
x.append(ymstr)
y.append(sum)
x2 = range(len(x))
plt.plot(x2, y) #plot(x轴数据，y轴数据，展现形式)
plt.xticks(x2, x, rotation=45)
#plt.figure(figsize=(40,5))
fig = plt.gcf()
fig.set_size_inches(18.5, 10.5)
plt.show()
# 练习题
# 利用TuShare的电影数据接口，获取电影月票房信息。
# 找到top3的电影，利用接口再次查询它们近7日的票房信息，并绘制成图片。
from matplotlib.font_manager import FontProperties
import matplotlib.pyplot as plt
import numpy as np
import tushare as ts
import datetime
# 默认是取上月月票房，传参传入本月
today = datetime.date.today()
today_display = str(today)
month = today_display[:7]
movie = ts.month_boxoffice(month)
# 如果当月刚开始，没有足够的电影信息，则使用上个月的数据
if len(movie) < 3:
movie = ts.month_boxoffice()
# 取排行榜前3的电影
top_three = movie.head(3)
# 保存top3电影名称
movie_names = list(top_three['MovieName'].values)
print(movie_names)
# 用于保存获取到的电影的票房信息
boxoffice_record = {}
for i in range(3):
boxoffice_record[movie_names[i]] = []
print(boxoffice_record)
import tushare as ts data = ts.month_boxoffice() print(data)
# http://tushare.org/boxoffice.html#id4
import json
import tushare as ts
# df = ts.month_boxoffice() # 取上一月票房数据
df = ts.month_boxoffice('2019-09') # 取2015年10月的数据
df = df[0:5]
# print(df)
d = {}
for idx, row in df.iterrows():
d[idx] = {}
d[idx]['Irank'] = eval(row['Irank'])
d[idx]['MovieName'] = row['MovieName']
d[idx]['avgboxoffice'] = row['avgboxoffice']
d[idx]['avgshowcount'] = row['avgshowcount']
d[idx]['boxoffice'] = row['boxoffice']
# print(d)
with open('hello.txt', 'w') as f:
json.dump(d, f)
with open('hello.txt', 'r') as f:
dd = json.load(f)
print(dd)