mail_parser2json_extract.py 文件源码

def extract_excel(filename):
    ret_string = ''
    book = xlrd.open_workbook(filename)
    sheets = book.sheet_names()

    for sheet in sheets:
        worksheet = book.sheet_by_name(sheet)
        num_rows = worksheet.nrows - 1
        num_cells = worksheet.ncols - 1
        curr_row = -1
        while curr_row < num_rows:
            curr_row += 1
            row = worksheet.row(curr_row)
            curr_cell = -1
            while curr_cell < num_cells:
                curr_cell += 1
                # Cell Types: 0=Empty, 1=Text, 2=Number, 3=Date, 4=Boolean, 5=Error, 6=Blank
                cell_type = worksheet.cell_type(curr_row, curr_cell)
                cell_value = worksheet.cell_value(curr_row, curr_cell)
                ret_string += cell_value+'\n'
    return ret_string   

# Given a big long string of text, split it by newline and try matching stuff in it.