def TickerInsideTrader(self):
"""Get insider information table.
Returns:
df(pandas.DataFrame): insider information table
"""
inside_trader = self.soup.find('table', class_='body-table')
rows = inside_trader.findAll('tr')
table_header = [i.text for i in rows[0].findAll('td')]
table_header += ['Insider_id']
df = pd.DataFrame([], columns=table_header)
rows = rows[1:]
num_col = ['Cost', '#Shares', 'Value ($)', '#Shares Total']
num_col_index = [
table_header.index(i) for i in table_header if i in num_col
]
for row in rows:
cols = row.findAll('td')
info_dict = {}
for i, col in enumerate(cols):
if i not in num_col_index:
info_dict[table_header[i]] = col.text
else:
info_dict[table_header[i]] = numberCovert(col.text)
info_dict['Insider_id'] = cols[0].a['href'].split('oc=')[1].split(
'&tc=')[0]
df = df.append(info_dict, ignore_index=True)
self.info['inside trader'] = df
return df
def getInsider(self):
"""Get insider information table.
Returns:
df(pandas.DataFrame): insider information table
"""
insider_trader = self.soup.findAll('table')[5]
rows = insider_trader.findAll('tr')
table_header = [i.text.strip() for i in rows[0].findAll('td')]
df = pd.DataFrame([], columns=table_header)
rows = rows[1:]
num_col = ['Cost', '#Shares', 'Value ($)', '#Shares Total']
num_col_index = [
table_header.index(i) for i in table_header if i in num_col
]
for row in rows:
cols = row.findAll('td')
info_dict = {}
for i, col in enumerate(cols):
if i not in num_col_index:
info_dict[table_header[i]] = col.text
else:
info_dict[table_header[i]] = numberCovert(col.text)
df = df.append(info_dict, ignore_index=True)
self.df = df
return df
def ScreenerView(self, group='Sector', order='Name'):
"""Get screener table.
Args:
group(str): choice of group option.
order(str): sort the table by the choice of order.
Returns:
df(pandas.DataFrame): group information table.
"""
if group not in self.group_dict:
raise ValueError()
if order not in self.order_dict:
raise ValueError()
self.url = self.BASE_URL.format(
group=self.group_dict[group]) + '&' + self.order_dict[order]
soup = webScrap(self.url)
table = soup.findAll('table')[5]
rows = table.findAll('tr')
table_header = [i.text for i in rows[0].findAll('td')][1:]
df = pd.DataFrame([], columns=table_header)
rows = rows[1:]
num_col_index = [i for i in range(2, len(table_header))]
for row in rows:
cols = row.findAll('td')[1:]
info_dict = {}
for i, col in enumerate(cols):
# check if the col is number
if i not in num_col_index:
info_dict[table_header[i]] = col.text
else:
info_dict[table_header[i]] = numberCovert(col.text)
df = df.append(info_dict, ignore_index=True)
return df
def TickerFundament(self, raw=True):
"""Get ticker fundament.
Args:
raw(boolean): if True, the data is raw.
Returns:
fundament(dict): ticker fundament.
"""
fundament_info = {}
table = self.soup.findAll('table')[5]
rows = table.findAll('tr')
fundament_info['Company'] = rows[1].text
fundament_info['Sector'], fundament_info['Industry'], fundament_info[
'Country'] = rows[2].text.split(' | ')
fundament_table = self.soup.find('table', class_='snapshot-table2')
rows = fundament_table.findAll('tr')
for row in rows:
cols = row.findAll('td')
cols = [i.text for i in cols]
header = ''
for i, value in enumerate(cols):
if i % 2 == 0:
header = value
else:
if header == 'Volatility':
fundament_info = self._parse_volatility(
header, fundament_info, value, raw)
elif header == '52W Range':
fundament_info = self._parse_52w_range(
header, fundament_info, value, raw)
elif header == 'Optionable' or header == 'Shortable':
if raw:
fundament_info[header] = value
elif value == 'Yes':
fundament_info[header] = True
else:
fundament_info[header] = False
else:
if raw:
fundament_info[header] = value
else:
try:
fundament_info[header] = numberCovert(value)
except ValueError:
fundament_info[header] = value
self.info['fundament'] = fundament_info
return fundament_info
def _parse_value(self, header, fundament_info, value, raw, info_header,
info_value):
try:
value = value.split()
if raw:
for i, value_index in enumerate(info_value):
fundament_info[info_header[i]] = value[value_index]
else:
for i, value_index in enumerate(info_value):
fundament_info[info_header[i]] = numberCovert(
value[value_index])
except:
fundament_info[header] = value
return fundament_info
def _get_table(self, rows, df, num_col_index, table_header, limit=-1):
"""Get screener table helper function.
Returns:
df(pandas.DataFrame): screener information table
"""
rows = rows[1:]
if limit != -1:
rows = rows[0:limit]
for index, row in enumerate(rows):
cols = row.findAll('td')[1:]
info_dict = {}
for i, col in enumerate(cols):
# check if the col is number
if i not in num_col_index:
info_dict[table_header[i]] = col.text
else:
info_dict[table_header[i]] = numberCovert(col.text)
df = df.append(info_dict, ignore_index=True)
return df
