def download_day_k_data(self, response):
path = response.meta['path']
item = response.meta['item']
try:
# 已经保存的csv数据
if os.path.exists(path):
saved_df = pd.read_csv(path, dtype=str)
else:
saved_df = pd.DataFrame()
df = utils.read_csv(io.BytesIO(response.body),
encoding='GB2312',
na_values='None')
df['code'] = item['code']
df['securityId'] = item['id']
df['name'] = item['name']
# 指数数据
if item['type'] == 'index':
df = df.loc[:, [
'日期', 'code', 'name', '最低价', '开盘价', '收盘价', '最高价', '成交量',
'成交金额', 'securityId', '前收盘', '涨跌额', '涨跌幅'
]]
df['turnoverRate'] = None
df['tCap'] = None
df['mCap'] = None
df['pe'] = None
df.columns = KDATA_INDEX_COL
# 股票数据
else:
df = df.loc[:, [
'日期', 'code', 'name', '最低价', '开盘价', '收盘价', '最高价', '成交量',
'成交金额', 'securityId', '前收盘', '涨跌额', '涨跌幅', '换手率', '总市值',
'流通市值'
]]
df['factor'] = None
df.columns = KDATA_STOCK_COL
# 合并到当前csv中
saved_df = saved_df.append(df, ignore_index=True)
if item['type'] == 'index':
saved_df = saved_df.dropna(subset=KDATA_INDEX_COLUMN_163)
# 保证col顺序
saved_df = saved_df.loc[:, KDATA_INDEX_COL]
else:
saved_df = saved_df.dropna(subset=KDATA_COLUMN_163)
# 保证col顺序
saved_df = saved_df.loc[:, KDATA_STOCK_COL]
saved_df = saved_df.drop_duplicates(subset='timestamp',
keep='last')
saved_df = saved_df.set_index(saved_df['timestamp'], drop=False)
saved_df.index = pd.to_datetime(saved_df.index)
saved_df = saved_df.sort_index()
saved_df.to_csv(path, index=False)
except Exception as e:
self.logger.exception(
'error when getting k data url={} error={}'.format(
response.url, e))
def download_day_k_data(self, response):
path = response.meta['path']
item = response.meta['item']
try:
# 已经保存的csv数据
if os.path.exists(path):
df_current = pd.read_csv(path, dtype=str)
else:
df_current = pd.DataFrame()
df = utils.read_csv(io.BytesIO(response.body), encoding='GB2312', na_values='None')
df['code'] = item['code']
df['securityId'] = item['id']
df = df.loc[:,
['日期', 'code', '最低价', '开盘价', '收盘价', '最高价', '成交量', '成交金额', 'securityId', '前收盘', '涨跌额', '涨跌幅', '换手率',
'总市值', '流通市值']]
df['factor'] = None
df.columns = KDATA_COLUMN_STOCK
# 合并到当前csv中
df_current = df_current.append(df, ignore_index=True)
df_current = df_current.dropna(subset=KDATA_COLUMN_163)
df_current = df_current.drop_duplicates(subset='timestamp', keep='last')
df_current = df_current.set_index(df_current['timestamp'])
df_current.index = pd.to_datetime(df_current.index)
df_current = df_current.sort_index()
df_current.to_csv(path, index=False)
except Exception as e:
self.logger.error('error when getting k data url={} error={}'.format(response.url, e))
def download_day_k_data(self, response):
path = response.meta['path']
item = response.meta['item']
try:
# 已经保存的csv数据
if os.path.exists(path):
df_current = pd.read_csv(path, dtype=str)
else:
df_current = pd.DataFrame()
df = utils.read_csv(io.BytesIO(response.body),
encoding='GB2312',
na_values='None')
df['code'] = item['code']
df['securityId'] = item['id']
df = df.loc[:, [
'日期', 'code', '最低价', '开盘价', '收盘价', '最高价', '成交量', '成交金额',
'securityId', '前收盘', '涨跌额', '涨跌幅', '换手率', '总市值', '流通市值'
]]
df['factor'] = None
df.columns = KDATA_COLUMN_STOCK
# 合并到当前csv中
df_current = df_current.append(df, ignore_index=True)
df_current = df_current.dropna(subset=KDATA_COLUMN_163)
df_current = df_current.drop_duplicates(subset='timestamp',
keep='last')
df_current = df_current.set_index(df_current['timestamp'])
df_current.index = pd.to_datetime(df_current.index)
df_current = df_current.sort_index()
df_current.to_csv(path, index=False)
except Exception as e:
self.logger.error(
'error when getting k data url={} error={}'.format(
response.url, e))
