python 展平一系列Excel列，这些列在单元格中包含列表，同时保留行。允许为不可打印的U设置错误级别

Posted 2021-05-10

import csv
import sys
from codecs import encode
from itertools import imap

from pyexcelerate import Workbook
from toolz.curried import *
from xlrd import open_workbook


BOOK = 'cv_fam.xlsx'
SHEET = 'FINAL - Events List'
COLUMN_NAMES = ('CV', 'PR', 'FL', 'CR')
START_ROW = 2
STOP_ROW = None
START_COL = 2
STOP_COL = 6


def xlsreader(workbook, worksheet):
    book = open_workbook('cv_fam.xlsx')
    sheet = book.sheet_by_name('FINAL- Events List')
    for row_num in range(sheet.nrows):
        yield sheet.row(row_num)


def cell2str(cell, errors='replace'):
    try:
        return str(cell.value)
    except UnicodeEncodeError:
        return encode(cell.value, 'utf-8', errors)


def flatten(rows):
    #import pdb; pdb.set_trace()
    for row_num, row in enumerate(rows):
        columns = row[START_COL:STOP_COL]
        for col_num, col in enumerate(columns):
            col_name = COLUMN_NAMES[col_num]
            for item in col.split():
                columns = (row[:START_COL], [col_name, item], row[STOP_COL:])
                yield concat(columns)

def main():
    import pdb; pdb.set_trace()
    rows = list(xlsreader(BOOK, SHEET))[START_ROW:STOP_ROW]
    rows = [list(map(cell2str, i)) for i in rows]
    rows = list(flatten(rows))
    book = Workbook()
    book.new_sheet(SHEET, data=rows)
    book.save(BOOK + '-flat.xlsx')


if __name__ == '__main__':
    main()