def list_stock_news(code, curdate, file): df = ts.get_notices(code, curdate) if df.empty: df = ts.get_notices(code) for index,row in df.iterrows(): if index>1: break print row['date'],row['title'] print ''
def generate_wordcloud_png(session,png_path,default_dict,default_word_font_ttf,stopwords,max_font_size=None,begin_code="000000"):
log_file = (os.getcwd() + os.sep + "logs" + os.sep + "load_word_cloud_%s.log") % (
dt.datetime.now().strftime('%Y-%m-%d'))
logger = get_logger(log_file,'word_cloud')
logger.info('Daily word cloud generation begins')
logger.info("##########################################")
logger.info("Begin get basic")
code_basic = get_all_code_basic(session,begin_code=begin_code)
for code in code_basic.code:
logger.info("##########################################")
logger.info("###Begin to generate for {code}###########".format(code = code))
logger.info("##########################################")
logger.info("Begin to generate for {code}".format(code = code))
cloud_df = ts.get_notices(code)
all = ""
if isinstance(cloud_df,pd.DataFrame):
for url in cloud_df.url:
all += get_url_content(url)
after = ' '.join(jieba.cut(all,cut_all=False))
file = get_word_cloud(after,file_name=code+".png",dict=default_dict,max_words=2000,stopwords=stopwords,folder_path=png_path,max_font_size=max_font_size,font_path=default_word_font_ttf)
logger.info("##########################################")
logger.info("{file} was generated successfully !".format(file = file))
logger.info("##########################################")
logger.info("All word cloud files were generated successfully !")
def store_news():
# 获取新浪股吧的最新新闻
sina_news = ts.guba_sina(show_content=True)
# 防止数据未更新插入重复数据 2018/04/22 0:33
# TODO 集合为空时的容错处理
for i in db.news.sina.find().sort([("_id", -1)]).limit(1):
for j in sina_news[:6][-1:].get("title"):
if i.get("title") != j:
db.news.sina.insert(
json.loads(sina_news[:6].to_json(orient='records')))
# 获取前6条最新的即时新闻
immediate_news = ts.get_latest_news(top=6, show_content=True)
for i in db.news.immediate.find().sort([("_id", -1)]).limit(1):
for j in immediate_news[-1:].get("title"):
if i.get("title") != j:
db.news.immediate.insert(
json.loads(immediate_news.to_json(orient='records')))
# 获取个股信息地雷数据
mines_news = ts.get_notices()
if not mines_news is None:
db.news.mines.insert(json.loads(mines_news.to_json(orient='records')))
def updatespecialnews():
conn = ms.connect(host='localhost',
port=3306,
user='******',
passwd='123456',
db='investment',
charset="utf8")
cur = conn.cursor()
cur.execute('select code from mainlist')
stus = cur.fetchall()
code = ''
for stu in stus:
code = stu[0]
specialnewsdatalist = ts.get_notices(code)
specialnewsdata = pd.DataFrame(specialnewsdatalist)
values = []
print code
for index, row in specialnewsdata.iterrows():
values.append(
(row['title'].encode("utf-8"), row['type'].encode("utf-8"),
row['date'].encode("utf-8"), row['url']))
cur.execute('delete from specialnews_' + code)
insertstr = 'insert into specialnews_' + code + ' (title,type,date,url) values(%s,%s,%s,%s)'
cur.executemany(insertstr, values)
conn.commit()
cur.close()
conn.close()
def get_notices_by_code(code):
try:
notices = ts.get_notices(code=str(code), date=today)
return notices
except Exception as e:
print(e)
return None
def nlpHandle(nlp, mic, profile, wxbot=None):
"""
Arguments:
text -- user-input, typically transcribed speech
mic -- used to interact with the user (for both input and output)
profile -- contains information related to the user (e.g., phone
number)
wxbot -- wechat bot instance
"""
def get_news(data):
rs = []
for index, row in data.iterrows():
rs.append(str(index + 1))
for col_name in data.columns:
rs.append(row[col_name])
rs.append('\n')
return ' '.join(rs)
sys.path.append(mic.dingdangpath.LIB_PATH)
from app_utils import wechatUser
text = nlp['text']
if any(word in text for word in [u"财经新闻"]):
news = ts.get_latest_news(top=10, show_content=False)
t = mic.asyncSay("已获取财经新闻," +
('将发送到您的微信' if wxbot != None else "篇幅较长，请登录微信获取"))
if wxbot != None:
wechatUser(profile, wxbot, '财经新闻', get_news(news))
t.join()
elif any(word in text for word in [u"信息地雷"]):
orgName = None
code = None
items = nlp['items']
for item in items:
if item['ne'] == u'ORG':
orgName = item['item']
break
if orgName:
code = db.get_instance().get_stock_code(orgName)
else:
m = pattern.search(text)
if m:
code = m.group(2)
if code:
orgName = db.get_instance().get_stock_name(code)
if not orgName:
mic.say("股票代码可能不存在")
return
notices = ts.get_notices(code)
notices = notices[0:10]
tit = orgName + '的信息地雷'
t = mic.asyncSay("已获取" + tit + "," +
('将发送到您的微信' if wxbot != None else "篇幅较长，请登录微信获取"))
if wxbot != None:
wechatUser(profile, wxbot, tit, get_news(notices))
t.join()
else:
mic.say("没能获取股票代码")
def processData():
for k, v in dic_hangye1.items():
print u"行业：", k
for c in v:
print c
s = c.split(".")
res = ts.get_notices(code=s[0])
print res
def test():
ts.get_sz50s()
ts.get_hs300s()
ts.get_zz500s()
ts.realtime_boxoffice()
ts.get_latest_news()
ts.get_notices(tk)
ts.guba_sina()
ts.get_cpi()
ts.get_ppi()
ts.get_stock_basics()
ts.get_concept_classified()
ts.get_money_supply()
ts.get_gold_and_foreign_reserves()
ts.top_list() #每日龙虎榜列表
ts.cap_tops() #个股上榜统计
ts.broker_tops() #营业部上榜统计
ts.inst_tops() # 获取机构席位追踪统计数据
ts.inst_detail()
def news_notices_worker(engine, codes, ddate):
pid = os.getpid()
tsl.log("pid %i start with %i codes..." % (pid, len(codes)))
df = pd.DataFrame()
for code in codes:
try:
newdf = ts.get_notices(code, ddate, True)
if newdf is not None:
newdf['code'] = code
df = df.append(newdf, ignore_index=True)
except BaseException, e:
print e
tsl.log("pid %i error for %s" % (pid, code))
def getnews1(code):
news = ts.get_notices(code=code)
type = list(news['type'])
title = list(news['title'])
date = list(news['date'])
url = list(news['url'])
print(len(type))
for i in type:
print(i)
for i in title:
print(i)
for i in date:
print(i)
for i in url:
print(i)
def get_news(start_date, end_date):
data = csv.reader(open('./input/tiker_list.csv', 'r'))
news = np.zeros([0, 5])
start_date = datetime.datetime.strptime(start_date, "%Y-%m-%d")
end_date = datetime.datetime.strptime(end_date, "%Y-%m-%d")
codes = []
for num, line in enumerate(data):
if num != 0 and num <= NUM_DATA: #for test
print("开始搜索有关" + line[1] + "(" + line[0] + ')' + "的新闻...")
codes.append(line[0])
day = start_date
while day <= end_date:
try:
hight = np.array(
ts.get_notices(line[0],
day.strftime('%Y-%m-%d'))).shape[0]
news = np.vstack(
(news,
np.hstack(
(np.array([[line[0]] * hight]).T,
ts.get_notices(line[0],
day.strftime('%Y-%m-%d'))))))
print("获取在" + day.strftime('%Y-%m-%d') + '的新闻成功')
except IndexError:
pass
except:
print("获取在" + day.strftime('%Y-%m-%d') + '的新闻失败，正在重试')
continue
day += datetime.timedelta(days=1)
writer = csv.writer(open('./input/news.csv', 'w'))
writer.writerows(news)
codes = np.array([list(codes)])
codes = codes.T
out = open('./input/finished.reuters', 'w', newline='')
csv_write = csv.writer(out)
csv_write.writerows(codes)
def generate_wordcloud_png(session,
png_path,
default_dict,
default_word_font_ttf,
stopwords,
max_font_size=None,
begin_code="000000"):
log_file = (os.getcwd() + os.sep + "logs" + os.sep +
"load_word_cloud_%s.log") % (
dt.datetime.now().strftime('%Y-%m-%d'))
logger = get_logger(log_file, 'word_cloud')
logger.info('Daily word cloud generation begins')
logger.info("##########################################")
logger.info("Begin get basic")
code_basic = get_all_code_basic(session, begin_code=begin_code)
for code in code_basic.code:
logger.info("##########################################")
logger.info(
"###Begin to generate for {code}###########".format(code=code))
logger.info("##########################################")
logger.info("Begin to generate for {code}".format(code=code))
cloud_df = ts.get_notices(code)
all = ""
if isinstance(cloud_df, pd.DataFrame):
for url in cloud_df.url:
all += get_url_content(url)
after = ' '.join(jieba.cut(all, cut_all=False))
file = get_word_cloud(after,
file_name=code + ".png",
dict=default_dict,
max_words=2000,
stopwords=stopwords,
folder_path=png_path,
max_font_size=max_font_size,
font_path=default_word_font_ttf)
logger.info("##########################################")
logger.info("{file} was generated successfully !".format(file=file))
logger.info("##########################################")
logger.info("All word cloud files were generated successfully !")
def run(self):
while not self.stop:
for i, stock in enumerate(self.stocklist):
print('processing: {0}. By thread:{1}'.format(stock, self.ix))
t = datetime(2015, 6, 20)
t_delta = datetime.now() - t
dframe = pd.DataFrame()
while t_delta.days > 0:
t = t + timedelta(1)
t_delta = datetime.now() - t
subdf = ts.get_notices(stock, t)
if not (subdf is None or subdf is [None]):
subdf = subdf.ix[subdf.ix[:, 0].str.contains(key_word)]
subdf = subdf.ix[subdf.ix[:, 1].str.contains(key_word2)]
dframe = dframe.append(subdf, ignore_index=True)
if len(dframe) == 0:
continue
dframe.to_csv(to_file + stock + '.csv', index=False)
def __call__(self, conns):
self.base = Base()
self.financial_data = conns['financial_data']
'''即时财经新闻'''
latest_news = ts.get_latest_news()
self.base.batchwri(latest_news, 'latest_news', self.financial_data)
'''
名称：个股信息地雷
功能：获得个股信息地雷数据
参数
code：股票代码
date：信息公布日期
'''
notices = ts.get_notices()
self.base.batchwri(notices, 'notices', self.financial_data)
'''新浪股吧新闻'''
guba_sina = ts.guba_sina()
self.base.batchwri(guba_sina, 'guba_sina', self.financial_data)
def get_stock_news(code, start, end):
start_date = datetime.strptime(start, '%Y-%m-%d')
end_date = datetime.strptime(end, '%Y-%m-%d')
res = None
while start_date <= end_date:
try:
temp = ts.get_notices(code, start_date.strftime("%Y-%m-%d"))
except:
start_date += timedelta(days=1)
continue
print(temp)
if res is None:
res = temp
else:
res = res.append(temp, ignore_index=True)
start_date += timedelta(days=1)
return res
def updatespecialnews():
conn= ms.connect(host='localhost',port = 3306,user='******', passwd='123456',db ='investment',charset="utf8")
cur = conn.cursor()
cur.execute('select code from mainlist')
stus = cur.fetchall()
code=''
for stu in stus:
code=stu[0]
specialnewsdatalist=ts.get_notices(code)
specialnewsdata=pd.DataFrame(specialnewsdatalist)
values=[]
print code
for index,row in specialnewsdata.iterrows():
values.append((row['title'].encode("utf-8"),row['type'].encode("utf-8"),row['date'].encode("utf-8"),row['url']))
cur.execute('delete from specialnews_'+code)
insertstr='insert into specialnews_'+code+' (title,type,date,url) values(%s,%s,%s,%s)'
cur.executemany(insertstr,values)
conn.commit()
cur.close()
conn.close()
def fetchNewsByCode(self, code, drop=False):
tableName = 'stockNews'
param = []
try:
db, dbname = connectConfigDB('database')
cursor = db.cursor()
cursor.execute("SET NAMES utf8mb4;")
if drop:
cursor.execute("DROP TABLE IF EXISTS %s" % tableName)
sql = """
CREATE TABLE
`%s`.`%s` (
`code` VARCHAR(10) NOT NULL COMMENT '股票代码',
`title` VARCHAR(45) NULL COMMENT '标题',
`type` VARCHAR(45) NULL COMMENT '类型',
`date` VARCHAR(45) NULL COMMENT '日期',
`url` TEXT NULL COMMENT '链接',
PRIMARY KEY (`code`, `title`, `date`)
) DEFAULT CHARSET=utf8mb4;
""" % (dbname, tableName
) # !IMPORTANT: DEFAULT CHARSET=utf8mb4;
cursor.execute(sql)
print('table %s created' % tableName)
# fetch and insert data
res = ts.get_notices(code)
sql = 'INSERT IGNORE INTO `' + tableName + \
"""` values(%s, %s, %s, %s, %s)
"""
for row in res.values:
param.append([code] + row.tolist())
cursor.executemany(sql, param)
db.commit()
print('\ntable %s inserted %s records.' %
(tableName, len(res.values)))
except:
print_exc()
db.rollback()
return False
finally:
db.close()
return True
def list_latest_news(codeArray, curdate): cur_dt = datetime.datetime.strptime(curdate, '%Y-%m-%d').date() for code in codeArray: bFlag = 0 news_ct = 0 df = ts.get_notices(code) for index,row in df.iterrows(): news_dt = datetime.datetime.strptime(row['date'], '%Y-%m-%d').date() delta = cur_dt-news_dt if delta.days<=0: print "===================================" bFlag=1 else: if bFlag==0: news_ct += 1 else: break if news_ct>1: break print row['date'],row['title'] print ''
def job_6():
try:
print("I'm working......新闻事件数据")
# 即时新闻
latest_news = ts.get_latest_news()
data = pd.DataFrame(latest_news)
data.to_sql('latest_news',engine,index=True,if_exists='replace')
print("即时新闻......done")
# 信息地雷
notices = ts.get_notices()
data = pd.DataFrame(notices)
data.to_sql('notices',engine,index=True,if_exists='replace')
print("信息地雷......done")
# 新浪股吧
guba_sina = ts.guba_sina()
data = pd.DataFrame(guba_sina)
data.to_sql('guba_sina',engine,index=True,if_exists='replace')
print("新浪股吧......done")
except Exception as e:
print(e)
def gonggao_dict(gongsi,year1,month1,day1,year2,month2,day2):
gg = pd.DataFrame()
ggl =[]
dated = datelist(year1,month1,day1,year2,month2,day2)
for date in dated:
print gongsi,date
try:
hhd = ts.get_notices(gongsi,date)
gg = gg.append(hhd,ignore_index=True)
except:
pass
try:
for num in range(gg.iloc[:,0].size):
ggd = {}
ggd['stock_id'] = gongsi
ggd['title'] = gg.loc[num]['title']
ggd['publish_time'] = datetimestr2ts(gg.loc[num]['date'])
ggd['url'] = gg.loc[num]['url']
ggd['type'] = getkind(gg.loc[num]['title'])
#ggd['content'] = '待取'
ggl.append(ggd)
except:
pass
return ggl
def gonggao_dict(gongsi, year1, month1, day1, year2, month2, day2):
gg = pd.DataFrame()
ggl = []
dated = datelist(year1, month1, day1, year2, month2, day2)
for date in dated:
print gongsi, date
try:
hhd = ts.get_notices(gongsi, date)
gg = gg.append(hhd, ignore_index=True)
except:
pass
try:
for num in range(gg.iloc[:, 0].size):
ggd = {}
ggd['stock_id'] = gongsi
ggd['title'] = gg.loc[num]['title']
ggd['publish_time'] = datetimestr2ts(gg.loc[num]['date'])
ggd['url'] = gg.loc[num]['url']
ggd['type'] = getkind(gg.loc[num]['title'])
#ggd['content'] = '待取'
ggl.append(ggd)
except:
pass
return ggl
import tushare as ts import sys df = ts.get_notices(code=sys.argv[1]) path = sys.argv[2] df.to_csv(path, encoding="utf8")
import tushare as ts
from sqlalchemy import create_engine
import MySQLdb
import sys
reload(sys)
sys.setdefaultencoding("utf-8")
db = MySQLdb.connect("localhost", "root", "2578", "CSEIII-Data")
cursor = db.cursor()
DB_CONNECT_STRING = 'mysql+mysqldb://root:2578@localhost/CSEIII-Data?charset=utf8'
engine = create_engine(DB_CONNECT_STRING)
name = 'investnews'
sql = "CREATE TABLE " + name + """ (index VARCHAR(20) NOT NULL,
title VARCHAR(20) NOT NULL,
type VARCHAR(20) NOT NULL,
date VARCHAR(20) NOT NULL,
url VARCHAR(20) NOT NULL)"""
cursor.execute(sql)
sql = "SELECT code FROM codelist "
cursor.execute(sql)
for index in cursor.fetchall():
df = ts.get_notices(str(index).split('(\'')[1].split('\'')[0])
if df is None:
pass
else:
df.to_sql(name, engine, if_exists='append')
def get_notices(self,code):
notices = ts.get_notices(code,self.dateS)
return notices
df_forecast = ts.forecast_data(2017,4)
'''业绩预告'''
df_restrict = ts.xsg_data()
'''限售股解禁'''
df_fund = ts.fund_holdings(2017, 2)
'''基金持股'''
df_sh = ts.sh_margin_details(start='2015-01-01', end='2015-04-19', symbol='601989')
'''上交所融资融券明细'''
df_sz = ts.sz_margins(start='2015-01-01', end='2015-04-19')
df_sz_detail = ts.sz_margin_details('2015-04-20')
'''深交所融资融券总额'''
#==============================================================================新闻==============================================================================
ts.get_latest_news() #默认获取最近80条新闻数据，只提供新闻类型、链接和标题
ts.get_latest_news(top=5,show_content=True) #显示最新5条新闻，并打印出新闻内容
'''即时新闻'''
ts.get_notices('600028')
'''个股新闻'''
ts.guba_sina(True)
'''新浪股吧'''
#==============================================================================海外数据源==============================================================================
import pandas.io.data as web
DAX = web.DataReader(name='^GDAXI',data_source='yahoo',start='2000-1-1')#读取德国DAX指数
#data_source='yahoo'/'google'/'fred'圣路易斯储蓄银行/'famafrench'/'pandas.io.web'世界银行
#write_code
#total_basic_data.to_excel(location_save_all_data+"/Basic_report_for_all_stocks.xlsx")
#total_financial_report.to_excel(location_save_all_data+"/all_general_financial_report.xlsx")
#total_profit_data.to_excel(location_save_all_data+"/all_profit_data.xlsx")
#total_operation_data.to_excel(location_save_all_data+"/all_operation_data.xlsx")
#total_growth_data.to_excel(location_save_all_data+"/all_growth_data.xlsx")
#total_leverage_data.to_excel(location_save_all_data+"/all_leverage_data.xlsx")
# -*- coding: utf-8 -*- import tushare as ts ''' 获取个股信息地雷数据。 参数说明： code:股票代码 date:信息公布日期 返回值说明： title:信息标题 type:信息类型 date:公告日期 url:信息内容URL 如果获取信息内容，请调用notice_content(url)接口，把url地址作为参数传入即可。 ''' data = ts.get_notices() print(data)
def stock_news(code):
return tushare.get_notices('%06d' % code)
import tushare as ts
from pandas import DataFrame
# print(tushare.__version__)
# 获取股票新闻
data = ts.get_notices(
code="002131") # 返回的对象是一个<class 'pandas.core.frame.DataFrame'>
# 使用pandas处理返回的对象
frame1 = DataFrame(data, columns=["title"],
index=[0, 1, 2]) # 只获取标题和url,并且只获取最近的3条记录
# print(frame1)
# 获取股票的历史行情
# 上证指数 深圳成指 沪深300指数 上证50 中小板 创业板
# 'sh','sz','hs300','sz50','zxb','cyb'
hist = ts.get_hist_data('sh', start='2019-03-25', end='2019-04-02')
# 只获取股票的开盘价和收盘价
# frame2 = DataFrame(hist, columns=["open", "close", "low", "high", "volume", "p_change", "price_change", "ma5", "ma10", "ma20", "v_ma5", "v_ma10", "v_ma20"])
# print(frame2)
# frame2.to_csv('F:/01/sh.csv')
# df = ts.get_index()
# print(df)
df = ts.get_index()
df.to_csv('F:/01/get_index.csv')
print(df)
def query_stock_info(ls_code, ls_all_stock_data, df_model_basics):
[ df_stock_basics, df_quarter_report_data, df_profit_data, df_operation_data, df_growth_data, df_debtpaying_data, \
df_cashflow_data, df_divi_data, df_forcast_quarter_report_data, df_restrict_stock_data, df_concept_classified ] = ls_all_stock_data
space = lambda x: ' ' * x # 方便区分不同季度数据
pd.options.mode.chained_assignment = None # 不显示warn信息 default='warn'
dict_stock_info = {}
for code in ls_code:
try:
basics = df_stock_basics.loc[int(code)]
content = '\n{0} {1}\n'.format(code, basics['name'])
try:
cur_price = float(
Data().get_k_line_data(code).iloc[-1]['close'])
except:
cur_price = float(
Data().get_realtime_quotes(code)['price'])
content += '\nbasics:\n上市日期：{0}\n所属行业：{1}\t行业市盈率排名：{6}\n地区：{2}\n市盈率(动态)：{3}\n市盈率(静态)：{4:.2f}\n市净率：{5}\n'\
.format( basics[ 'timeToMarket' ], basics[ 'industry' ], basics[ 'area' ], basics[ 'pe' ], \
cur_price / float( basics[ 'esp' ] ), float( basics[ 'pb' ] ), df_model_basics[ 'rank_pe' ][ int( code ) ] )
content += '每股公积金：{0}\n每股未分配利润：{1}\n'\
.format( basics[ 'reservedPerShare' ], basics[ 'perundp' ] )
content += '总市值：{0:.2f} 亿元\n流动市值：{1:.2f} 亿元\n'\
.format( cur_price * float( basics[ 'totals' ] ), cur_price * float( basics[ 'outstanding' ] ) )
content += '总资产：{0:.2f} 亿元\n固定资产：{1:.2f} 亿元\n流动资产：{2:.2f} 亿元\n'\
.format( float( basics[ 'totalAssets' ] ) / 10000, float( basics[ 'fixedAssets' ] ) / 10000, \
float( basics[ 'liquidAssets' ] ) / 10000 )
except:
content = '\n{0}\n'.format(code)
try:
content += '\nconcept:\n'
id_concept = 1
id_rank = 1
name_concept = '_'.join(['concept', str(id_concept)])
name_rank = '_'.join(['rank_pe', str(id_rank)])
while df_model_basics[name_concept][int(code)] is not np.nan:
content += '{0} 市盈率排名:{1}\n'.format( df_model_basics[ name_concept ][ int( code ) ], \
df_model_basics[ name_rank ][ int( code ) ] )
id_concept += 1
id_rank += 1
if id_concept > 20:
break
name_concept = '_'.join(['concept',
str(id_concept)])
name_rank = '_'.join(['rank_pe', str(id_rank)])
content += '\n'
except:
pass
try:
profit = df_profit_data.loc[int(code)].sort_values(
by=['year',
'quarter'], axis=0, ascending=True).drop_duplicates()
content += '\nprofit:\n排名：{0}\n年份 季度 净资产收益率 净利润（百万） 每股收益（元）每股主营业务收入(元)\n'\
.format( df_model_basics[ 'rank_profit_grow' ][ int( code ) ] )
for id in range(profit.index.size):
content += '{5}{0} {1} {2:-10.2f} {3:-12.2f} {4:-15.2f} {6:-20.2f}\n'.format( profit.iloc[ id ][ 'year' ], profit.iloc[ id ][ 'quarter' ], \
profit.iloc[ id ][ 'roe' ], profit.iloc[ id ][ 'net_profits' ], profit.iloc[ id ][ 'eps' ], \
space( int( profit.iloc[ id ][ 'quarter' ] ) - 1 ), profit.iloc[ id ][ 'bips' ] )
except:
pass
try:
operation = df_operation_data.loc[int(code)].sort_values(
by=['year',
'quarter'], axis=0, ascending=True).drop_duplicates()
content += '\noperation:\n年份 季度 应收账款周转天数 存货周转天数 流动资产周转天数\n'
for id in range(operation.index.size):
content += '{5}{0} {1} {2:-16.2f} {3:-8.2f} {4:-15.2f}\n'.format( operation.iloc[ id ][ 'year' ], \
operation.iloc[ id ][ 'quarter' ],operation.iloc[ id ][ 'arturndays' ], operation.iloc[ id ][ 'inventory_days' ], \
operation.iloc[ id ][ 'currentasset_days' ], space( int( operation.iloc[ id ][ 'quarter' ] ) - 1 ) )
except:
pass
try:
debtpaying = df_debtpaying_data.loc[int(code)].sort_values(
by=['year',
'quarter'], axis=0, ascending=True).drop_duplicates()
content += '\ndebtpaying:\n年份 季度 流动比率 利息支付倍数 股东权益比率 股东权益增长率\n'
for col in ['currentratio', 'icratio', 'sheqratio', 'adratio']:
for id in range(debtpaying.index.size):
try:
float(debtpaying[col].iloc[id])
except:
debtpaying[col].iloc[id] = np.nan
for id in range(debtpaying.index.size):
content += '{5}{0} {1} {2:-8.2f} {3:-12.2f} {4:-10.2f} {6:-14.2f}\n'.format( debtpaying.iloc[ id ][ 'year' ], \
debtpaying.iloc[ id ][ 'quarter' ], float( debtpaying.iloc[ id ][ 'currentratio' ] ), float( debtpaying.iloc[ id ][ 'icratio' ] ), \
float( debtpaying.iloc[ id ][ 'sheqratio' ] ), space( int( debtpaying.iloc[ id ][ 'quarter' ] ) - 1 ), \
float( debtpaying.iloc[ id ][ 'adratio' ] ) )
except:
pass
try:
divi = df_divi_data.loc[int(code)]
content += '\ndivision:\n年份 公布日期 分红金额(每10股) 转增股数(每10股)\n'
if type(divi) == pd.Series:
divi = divi.to_frame().T
if type(divi) == pd.DataFrame:
divi = divi.sort_values(by=['year', 'report_date'],
axis=0,
ascending=True)
for id in range(divi.index.size):
content += '{0} {1} {2:-12d} {3:-16d}\n'.format( divi.iloc[ id ][ 'year' ], divi.iloc[ id ][ 'report_date' ], int( divi.iloc[ id ][ 'divi' ] ), \
int( divi.iloc[ id ][ 'shares' ] ) )
else:
ERROR('divi type error.')
except:
pass
try:
forcast_quarter_data = df_forcast_quarter_report_data.loc[int(
code)]
content += '\nforcast quarter report:\n发布日期 业绩变动类型 上年同期每股收益 业绩变动范围\n'
if type(forcast_quarter_data) == pd.Series:
forcast_quarter_data = forcast_quarter_data.to_frame().T
if type(forcast_quarter_data) == pd.DataFrame:
forcast_quarter_data = forcast_quarter_data.sort_values(
by='report_date', axis=0, ascending=True)
for id in range(forcast_quarter_data.index.size):
content += '{0} {1:>8s} {2:-14.2f} {3:>12s}\n'.format( forcast_quarter_data.iloc[ id ][ 'report_date' ], \
forcast_quarter_data.iloc[ id ][ 'type' ], float( forcast_quarter_data.iloc[ id ][ 'pre_eps' ] ), \
forcast_quarter_data.iloc[ id ][ 'range' ] )
else:
ERROR('forcast_quarter_data type error.')
except:
pass
try:
restrict = df_restrict_stock_data.loc[int(code)]
content += '\nrestrict:\n解禁日期 解禁数量（万股） 占总盘比率\n'
if type(restrict) == pd.Series:
restrict = restrict.to_frame().T
if type(restrict) == pd.DataFrame:
restrict = restrict.sort_values(by='date',
axis=0,
ascending=True)
for id in range(restrict.index.size):
content += '{0} {1:-12.2f} {2:-10.2f}\n'.format( restrict.iloc[ id ][ 'date' ], \
float( restrict.iloc[ id ][ 'count' ] ), float( restrict.iloc[ id ][ 'ratio' ] ) )
else:
ERROR('restrict type error.')
except:
pass
try:
df_news = ts.get_notices(code)
content += '\nnotice:\n'
for index in range(0, 10): # df_news.index:
content += '{3}、{0}\t{1}\tdate:{2}\n'.format( df_news[ 'title' ][ index ], \
df_news[ 'type' ][ index ], df_news[ 'date' ][ index ], index + 1 )
if index < 3:
content += ts.notice_content(df_news['url'][index])
content += '\n\n'
content += '\n'
except:
pass
LOG(content)
dict_stock_info[code] = content
return dict_stock_info
def Getxinxidilei():
df = ts.get_notices(date=getNowTime())
print(df)
return df
def getNotice(self):
file_name = self.code + '_' + self.startDate + '.csv'
path = self.index + self.index_notice + file_name
data = ts.get_notices(code=self.code, date=self.startDate)
data.to_csv(path, encoding='utf-8')
print(file_name)
import matplotlib import matplotlib.pyplot as plt import numpy as np import pandas as pd import tushare as ts # 显示matplotlib路径 print(matplotlib.matplotlib_fname()) # 全局路径设置 os.getcwd() source_path = os.getcwd() + r'/idea/work/' # 一次性获取最近一个日交易日所有股票的交易数据 # ts_df = ts.get_today_all() # 新闻数据 new_df = ts.get_notices() # 保存数据到csv # ts_df.to_csv(source_path + r'ts_df.csv', encoding='utf_8_sig') # new_df.to_csv(source_path + r'new_df.csv', encoding='utf_8_sig') # 从csv读取数据 ts_df = pd.read_csv(source_path + r'ts_df.csv') ts_df.info() ts_df.head() ts_df.shape # 使用 utf_8_sig 可以解决中文乱码问题 (ts_df['trade'] - ts_df['open']) / ts_df['open'] * 100 ts_df['settlement'] * (1 + ts_df['changepercent'] / 100)
import tushare as ts
# 即时新闻
# 获取即时财经新闻，类型包括国内财经、证券、外汇、期货、港股和美股等新闻信息。
news = ts.get_latest_news()
print(news)
# 信息地雷
# 获取个股信息地雷数据
n = ts.get_notices('600000')
print(n)
# 新浪股吧
# 获取sina财经股吧首页的重点消息。股吧数据目前获取大概17条重点数据，可根据参数设置是否显示消息内容，默认情况是不显示。
gb = ts.guba_sina()
print(gb)
# -*- coding: utf-8 -*- import tushare as ts # ts.get_latest_news(show_content=True) #默认获取最近80条新闻数据，只提供新闻类型、链接和标题 # ts.get_latest_news(top=5,show_content=True) #显示最新5条新闻，并打印出新闻内容 news = ts.get_notices() print(news) news = ts.guba_sina() print(news) print(news['title'][4]['content'])
