Function _parse_table

soccerdata/fbref.py:1037–1064

Parse HTML table into a dataframe. Parameters ---------- html_table : lxml.html.HtmlElement HTML table to clean up. Returns ------- pd.DataFrame

(html_table: html.HtmlElement)

def _parse_table(html_table: html.HtmlElement) -> pd.DataFrame:
    """Parse HTML table into a dataframe.

    Parameters
    ----------
    html_table : lxml.html.HtmlElement
        HTML table to clean up.

    Returns
    -------
    pd.DataFrame
    """
    # remove icons
    for elem in html_table.xpath(".//span[contains(@class, 'f-i')]"):
        parent = elem.getparent()
        if parent is not None:
            etree.strip_elements(parent, "span", with_tail=False)
    # remove sep rows
    for elem in html_table.xpath("//tbody/tr[contains(@class, 'spacer')]"):
        elem.getparent().remove(elem)
    # remove thead rows in the table body
    for elem in html_table.xpath("//tbody/tr[contains(@class, 'thead')]"):
        elem.getparent().remove(elem)
    # parse HTML to dataframe
    (df_table,) = pd.read_html(
        io.StringIO(html.tostring(html_table, encoding="unicode")), flavor="lxml"
    )
    return df_table.convert_dtypes()


def _concat(dfs: list[pd.DataFrame], key: list[str]) -> pd.DataFrame: