Python实现读取HTML表格 pd.read_html()

data_lines = read_excel_file(self.file_path)

def read_excel_file(file_path):
    """
    读取excel文件
    """
    import xlrd
    print('[Info] excel file: {}'.format(file_path))
    book = xlrd.open_workbook(file_path)
    sheet = book.sheet_by_index(0)
    data_lines = []
    for row in range(0, sheet.nrows):
        line_data = []
        for column in range(0, sheet.ncols):
            val = sheet.cell(row, column).value
            line_data.append(val)
        data_lines.append(line_data)
    return data_lines  # 二维数组

def read_html_table(file_path):
    """
    读取html表格
    """
    import pandas as pd
    pd_table = pd.read_html(file_path)
    df = pd_table[0]
    # num_col = df.shape[1]
    # num_row = df.shape[0]
    df_data = df.values.tolist()
    df_data = df_data[1:]
    for r_idx, row in enumerate(df_data):
        for c_idx, value in enumerate(row):
            # 判断nan，参考https://stackoverflow.com/questions/944700/how-can-i-check-for-nan-values
            if value != value:
                df_data[r_idx][c_idx] = ""
    return df_data