ahnazary / stockdex Goto Github PK

class Ticker(TickerAPI, JustETF):
    """
    Class for the Ticker
    """
    ...

    @property
    def income_stmt(self) -> pd.DataFrame:
        """
        Get income statement for the ticker

        Returns:
        pd.DataFrame: A pandas DataFrame including the income statement
        visible in the Yahoo Finance statistics page for the ticker
        """

        # URL of the website to scrape
        url = f"https://finance.yahoo.com/quote/{self.ticker}/financials"
        response = self.get_response(url)

        # Parse the HTML content of the website
        soup = BeautifulSoup(response.content, "html.parser")

        # <div class="" data-test="fin-row">
        raw_data = soup.find_all("div", {"data-test": "fin-row"})

        data_df = pd.DataFrame()
        dates = []
        for item in raw_data:

            if not dates:
                # collect date headers for data_df
                # e.g., ['12/31/2023', '12/31/2022', '12/31/2021', '12/31/2020']
                dates = re.findall(
                    pattern=r"\d+/\d+/\d{4}", string=item.parent.parent.text
                )
                assert (
                    len(dates) == 4
                ), f"len(dates)={len(dates)}, should be 4 (dates={', '.join(dates)})"

                # column for the most recent period gets collected twice below
                # i.e., ['12/31/2023', '12/31/2023',  '12/31/2022', '12/31/2021', '12/31/2020']
                dates = [dates[0]] + dates

            # get criteria. e.g. "Total Revenue"
            major_div = item.find_all("div", {"class": True})[0]
            criteria = major_div.find_all("div", {"class": True})[0].find("span").text

            # get data. e.g. "274515000000"
            minor_div = major_div.find_all("div", {"class": "Ta(c)"})
            data_list = []
            for div in minor_div:
                data_list.append(div.text)

            data_df[criteria] = data_list

        data_df = data_df.T
        
        # update columns to reflect the date headers
        data_df.columns = dates

        return data_df