From 29b37c756d8f94e6d75f49e01565c3deee13833f Mon Sep 17 00:00:00 2001
From: Daniil Fajnberg <mail@daniil.fajnberg.de>
Date: Mon, 8 Nov 2021 18:40:34 +0100
Subject: [PATCH] first draft (proof of concept) for getting data from single
 row/company

---
 src/stock-symbol-scraper/main.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/src/stock-symbol-scraper/main.py b/src/stock-symbol-scraper/main.py
index e69de29..7a30ab6 100644
--- a/src/stock-symbol-scraper/main.py
+++ b/src/stock-symbol-scraper/main.py
@@ -0,0 +1,30 @@
+import re
+
+from requests import get
+from bs4 import BeautifulSoup
+from bs4.element import Tag
+
+
+row_type = tuple[str, str, str, str, str]
+
+
+def get_row_data(table_row: Tag) -> row_type:
+    tds = table_row.find_all('td')
+    company_name = str(tds[0].a.contents[0]).strip()
+    stock_symbol = str(tds[0].a.contents[1].contents[0]).strip()
+    stock_symbol_pattern = re.compile(r'\((\w+)\)')
+    stock_symbol = re.search(stock_symbol_pattern, stock_symbol).group(1)
+    country = str(tds[1].contents[0])
+    exchange = str(tds[2].contents[0])
+    sector = str(tds[3].contents[0])
+    return company_name, stock_symbol, country, exchange, sector
+
+
+if __name__ == '__main__':
+    response = get('https://www.marketwatch.com/tools/markets/stocks/a-z/0-9')
+    soup = BeautifulSoup(response.text, 'html.parser')
+    trs = soup.find('div', {'id': 'marketsindex'}).table.tbody.find_all('tr')
+    print(get_row_data(trs[0]))
+    print(get_row_data(trs[1]))
+    print(get_row_data(trs[149]))
+    data: list[row_type] = []