function drafts

src/mwfin/functions.py

@@ -1,4 +1,5 @@
 from typing import Union
+import re
 
 from aiohttp.client import ClientSession
 from bs4 import BeautifulSoup
@@ -18,7 +19,9 @@ async def soup_from_url(url: str, session: ClientSession = None) -> BeautifulSou
     """
     Requests a web page and turns the response text into BeautifulSoup.
     """
-    pass
+    async with session.get(url) as response:
+        html = await response.text()
+    return BeautifulSoup(html, constants.HTML_PARSER)
 
 
 def extract_end_dates(soup: BeautifulSoup) -> tuple[str]:
@@ -26,21 +29,29 @@ def extract_end_dates(soup: BeautifulSoup) -> tuple[str]:
     Finds and returns the end dates of the reporting periods as strings (either years or quarters) from the page of a
     financial statement.
     """
-    pass
+    ths = soup.find('div', attrs={'class': 'financials'}).thead.find_all('th')
+    return tuple(str(th.string).strip() for th in ths[1:-1])
 
 
 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.
     """
-    pass
+    item_name = str(tr.find_next('td').find_next('div').string).strip()
+    if constants.FINANCIAL_STATEMENT_ITEMS[item_name]:
+        return True
 
 
 def find_relevant_table_rows(soup: BeautifulSoup) -> ResultSet:
     """
     Returns the table rows containing the data of interest.
     """
-    pass
+    table_div = soup.find('div', attrs={'class': 'financials'})
+    rows = table_div.find_all('tr')[1:-1]
+    for r in rows:
+        if not is_relevant_table_row(r):
+            rows.remove(r)
+    return rows
 
 
 def extract_row_data(tr: Tag) -> tuple[str, tuple[int]]: