daniil-berg/mwfin
2
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

bugfix, minor change, full coverage

Browse Source
This commit is contained in:
Daniil Fajnberg 2021-11-27 18:11:16 +01:00
parent 2380540659
commit 63008be829
3 changed files with 10 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/mwfin/constants.py
View File

@ -1,6 +1,6 @@
HTML_PARSER = 'html.parser' HTML_PARSER = 'html.parser'
DOMAIN = 'www.marketwatch.com' DOMAIN = 'www.marketwatch.com'
BASE_URL = f'https://{DOMAIN}/investing/stock/' BASE_URL = f'https://{DOMAIN}/investing/stock'
BS, IS, CF = 'bs', 'is', 'cf' BS, IS, CF = 'bs', 'is', 'cf'
FIN_STMT_URL_SUFFIX = { FIN_STMT_URL_SUFFIX = {

16
src/mwfin/functions.py
View File

@ -1,9 +1,9 @@
import logging import logging
from typing import Union from typing import Union, List
from aiohttp.client import ClientSession from aiohttp.client import ClientSession
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from bs4.element import ResultSet, Tag from bs4.element import Tag
from . import constants from . import constants
@ -39,8 +39,6 @@ def is_relevant_table_row(tr: Tag) -> bool:
""" """
Returns True if the item in the table row is marked as relevant. Additionally warns when an item is unknown. Returns True if the item in the table row is marked as relevant. Additionally warns when an item is unknown.
""" """
if tr.name != 'tr':
return False
item_name = str(tr.td.div.string).strip() item_name = str(tr.td.div.string).strip()
try: try:
return constants.FINANCIAL_STATEMENT_ITEMS[item_name] return constants.FINANCIAL_STATEMENT_ITEMS[item_name]
@ -49,11 +47,12 @@ def is_relevant_table_row(tr: Tag) -> bool:
return False return False
def find_relevant_table_rows(soup: BeautifulSoup) -> ResultSet: def find_relevant_table_rows(soup: BeautifulSoup) -> List[Tag]:
""" """
Returns the table rows containing the data of interest. Returns the table rows containing the data of interest.
""" """
return soup.find('div', attrs={'class': 'financials'}).tbody.find_all(is_relevant_table_row) trs = soup.find('div', attrs={'class': 'financials'}).tbody.find_all('tr')
return [tr for tr in trs if is_relevant_table_row(tr)]
def extract_row_data(tr: Tag) -> tuple[str, tuple[int]]: def extract_row_data(tr: Tag) -> tuple[str, tuple[int]]:
@ -84,8 +83,9 @@ async def _get_financial_statement(statement: str, ticker_symbol: str, quarterly
""" """
Returns data from the specified financial statement of the specified company. Returns data from the specified financial statement of the specified company.
""" """
q = '/quarter' if quarterly else '' url = f'{constants.BASE_URL}/{ticker_symbol}/financials{constants.FIN_STMT_URL_SUFFIX[statement]}'
url = constants.BASE_URL + ticker_symbol + '/financials' + constants.FIN_STMT_URL_SUFFIX[statement] + q if quarterly:
url += '/quarter'
soup = await soup_from_url(url, session) soup = await soup_from_url(url, session)
return extract_all_data(soup) return extract_all_data(soup)

3
tests/test_functions.py
View File

@ -62,7 +62,6 @@ class FunctionsTestCase(IsolatedAsyncioTestCase):
self.assertFalse(functions.is_relevant_table_row(test_soup.tr)) self.assertFalse(functions.is_relevant_table_row(test_soup.tr))
test_soup = BeautifulSoup('<tr><td><div> baz </div></td></tr>', HTML_PARSER) test_soup = BeautifulSoup('<tr><td><div> baz </div></td></tr>', HTML_PARSER)
self.assertFalse(functions.is_relevant_table_row(test_soup.tr)) self.assertFalse(functions.is_relevant_table_row(test_soup.tr))
self.assertFalse(functions.is_relevant_table_row(test_soup.div))
@patch.object(functions, 'is_relevant_table_row') @patch.object(functions, 'is_relevant_table_row')
def test_find_relevant_table_rows(self, mock_is_relevant_table_row): def test_find_relevant_table_rows(self, mock_is_relevant_table_row):
@ -104,7 +103,7 @@ class FunctionsTestCase(IsolatedAsyncioTestCase):
async def test__get_financial_statement(self, mock_soup_from_url, mock_extract_all_data): async def test__get_financial_statement(self, mock_soup_from_url, mock_extract_all_data):
mock_session = MagicMock() mock_session = MagicMock()
test_ticker, statement = 'bar', BS test_ticker, statement = 'bar', BS
test_url = f'{BASE_URL}{test_ticker}/financials{FIN_STMT_URL_SUFFIX[statement]}' test_url = f'{BASE_URL}/{test_ticker}/financials{FIN_STMT_URL_SUFFIX[statement]}'
mock_soup_from_url.return_value = mock_soup = MagicMock() mock_soup_from_url.return_value = mock_soup = MagicMock()
mock_extract_all_data.return_value = expected_output = {'foo': 'bar'} mock_extract_all_data.return_value = expected_output = {'foo': 'bar'}