问我可以在Python中从html文件中抓取表格吗？

EN

url = r'https://www.sec.gov/Archives/edgar/data/1181232/000104746903038553/a2123752z424b4.htm'

filing_url = requests.get(url)
content = filing_url.text
soup = BeautifulSoup(content, 'lxml') 

tables = soup.find_all(text=re.compile('SUMMARY CONSOLIDATED FINANCIAL AND OTHER DATA'))

n_columns = 0
n_rows = 0
column_names = []
for table in tables:
    for row in table.find_next('table').find_all('tr'):

        # Determine the number of rows in the table
        td_tags = row.find_all('td')
        if len(td_tags) > 0:
            n_rows += 1
            if n_columns == 0:
                # Set the number of columns for the table
                n_columns = len(td_tags)

        # Handle column names if find them
        th_tags = row.find_all('th')
        if len(th_tags) > 0 and len(column_names) == 0:
            for th in th_tags:
                column_names.append(th.get_text())

        # Safeguard on Column Titles
    if len(column_names) > 0 and len(column_names) != n_columns:
        raise Exception("Column titles do not match the number of columns")

    columns = column_names if len(column_names) > 0 else range(0, n_columns)
    df = pd.DataFrame(columns=columns,
                      index=range(0, n_rows))
    row_marker = 0
    for row in table.find_all('tr'):
        column_marker = 0
        columns = row.find_all('td')
        for column in columns:
            df.iat[row_marker, column_marker] = column.get_text()
            column_marker += 1
        if len(columns) > 0:
            row_marker += 1

    print(df)