def test_get_income_statement_items():
income_statements = fundamental.get_income_statement_items(
'600977', start_date='2016-06-30')
assert len(income_statements) > 0
for item in income_statements:
assert item['operatingRevenue'] > 0
assert item['reportEventDate'] > item['reportPeriod']
def crawl_finance_data(start_code=STOCK_START_CODE, end_code=STOCK_END_CODE):
for _, security_item in get_security_list(start_code=start_code, end_code=end_code).iterrows():
try:
# 先抓事件,有些后续抓取依赖事件
process_crawl(StockFinanceReportEventSpider, {"security_item": security_item})
current_report_period = get_report_period()
# 资产负债表
path = get_balance_sheet_path(security_item)
if not os.path.exists(path):
process_crawl(StockFinanceSpider, {"security_item": security_item,
"report_type": "balance_sheet"})
else:
current_items = get_balance_sheet_items(security_item)
# 当前报告期还没抓取
if current_report_period != current_items[-1]['reportPeriod']:
# 报告出来了
# df = event.get_finance_report_event(security_item, index='reportPeriod')
# if current_report_period in df.index:
process_crawl(StockFinanceSpider, {"security_item": security_item,
"report_type": "balance_sheet"})
# 利润表
path = get_income_statement_path(security_item)
if not os.path.exists(path):
process_crawl(StockFinanceSpider, {"security_item": security_item,
"report_type": "income_statement"})
else:
current_items = get_income_statement_items(security_item)
# 当前报告期还没抓取
if current_report_period != current_items[-1]['reportPeriod']:
# 报告出来了
# df = event.get_finance_report_event(security_item, index='reportPeriod')
# if current_report_period in df.index:
process_crawl(StockFinanceSpider, {"security_item": security_item,
"report_type": "income_statement"})
# 现金流量表
path = get_cash_flow_statement_path(security_item)
if not os.path.exists(path):
process_crawl(StockFinanceSpider, {"security_item": security_item,
"report_type": "cash_flow"})
else:
current_items = get_cash_flow_statement_items(security_item)
# 当前报告期还没抓取
if current_report_period != current_items[-1]['reportPeriod']:
# 报告出来了
# df = event.get_finance_report_event(security_item, index='reportPeriod')
# if current_report_period in df.index:
process_crawl(StockFinanceSpider, {"security_item": security_item,
"report_type": "cash_flow"})
except Exception as e:
logger.exception(e)
def check_net_profit(security_item):
income_statement_list = get_income_statement_items(
security_item=security_item)
for income_statement in income_statement_list:
netProfit = income_statement["totalProfits"] - income_statement[
"incomeTaxExpense"]
diff = netProfit - income_statement["netProfit"]
if abs(diff) >= 1:
print(
"{} net profit calculating not pass,calculating result:{},report result:{}"
.format(income_statement['id'], netProfit,
income_statement["netProfit"]))
else:
print("{} net profit calculating pass".format(
income_statement['id']))
def finance_sheet_to_es(sheet_type=None,
start_code=None,
end_code=None,
force=False):
if sheet_type is None:
sheet_types = [
'balance_sheet', 'income_statement', 'cash_flow_statement'
]
else:
sheet_types = [sheet_type]
for sheet_type in sheet_types:
if sheet_type == 'balance_sheet':
doc_type = BalanceSheet
elif sheet_type == 'income_statement':
doc_type = IncomeStatement
elif sheet_type == 'cash_flow_statement':
doc_type = CashFlowStatement
es_index_mapping(sheet_type, doc_type)
for _, security_item in get_security_list(
start_code=start_code, end_code=end_code).iterrows():
try:
if sheet_type == 'balance_sheet':
items = get_balance_sheet_items(security_item)
elif sheet_type == 'income_statement':
items = get_income_statement_items(security_item)
elif sheet_type == 'cash_flow_statement':
items = get_cash_flow_statement_items(security_item)
df = pd.DataFrame(items)
df = index_df_with_time(df, index='reportPeriod')
df_to_es(df,
doc_type=doc_type,
timestamp_filed='reportPeriod',
security_item=security_item,
force=force)
except Exception as e:
logger.exception(
"index {} {} failed".format(security_item['code'],
sheet_type), e)
def check_eps(security_item):
income_statement_list = get_income_statement_items(
security_item=security_item)
for income_statement in income_statement_list:
balance_sheet = get_balance_sheet_items(
security_item=security_item,
report_period=income_statement['reportDate'])
if not balance_sheet or balance_sheet['totalShareCapital'] == 0:
continue
eps = (income_statement["netProfit"] -
income_statement["minorityInterestIncome"]) / (
balance_sheet['totalShareCapital'])
diff = eps - income_statement["EPS"]
if abs(diff) >= 0.01:
print(
"{} EPS calculating not pass,calculating result:{},report result:{}"
.format(income_statement['id'], eps, income_statement["EPS"]))
else:
print("{} EPS calculating pass".format(income_statement['id']))
def check_operating_profit(security_item):
income_statement_list = get_income_statement_items(
security_item=security_item)
for income_statement in income_statement_list:
operatingProfit = income_statement["operatingRevenue"] \
- income_statement["operatingCosts"] \
- income_statement["businessTaxesAndSurcharges"] \
- income_statement["sellingExpenses"] \
- income_statement["ManagingCosts"] \
- income_statement["financingExpenses"] \
- income_statement["assetsDevaluation"] \
+ income_statement["incomeFromChangesInFairValue"] \
+ income_statement["investmentIncome"]
diff = operatingProfit - income_statement["operatingProfit"]
if abs(diff) >= 1:
print(
"{} operating profit calculating not pass,calculating result:{},report result:{}"
.format(income_statement['id'], operatingProfit,
income_statement["operatingProfit"]))
else:
print("{} operating profit calculating pass".format(
income_statement['id']))
def finance_sheet_to_es(sheet_type='balance_sheet',
start_code=None,
end_code=None,
force=False):
if sheet_type == 'balance_sheet':
doc_type = BalanceSheet
elif sheet_type == 'income_statement':
doc_type = IncomeStatement
elif sheet_type == 'cash_flow_statement':
doc_type = CashFlowStatement
es_index_mapping(sheet_type, doc_type)
for _, security_item in get_security_list(start_code=start_code,
end_code=end_code).iterrows():
query = None
if not force:
query = {"term": {"securityId": ""}}
query["term"]["securityId"] = security_item["id"]
if sheet_type == 'balance_sheet':
items = get_balance_sheet_items(security_item)
elif sheet_type == 'income_statement':
items = get_income_statement_items(security_item)
elif sheet_type == 'cash_flow_statement':
items = get_cash_flow_statement_items(security_item)
df = pd.DataFrame(items)
df = index_df_with_time(df, index='reportPeriod')
df_to_es(df,
doc_type=doc_type,
timestamp_filed='reportPeriod',
query=query,
force=force)