2018-11-26 python文件读取(yaml，excel，csv)模块

# -*- coding: utf-8 -*-
"""
文件读取。YamlReader读取yaml文件，ExcelReader读取excel，CsvReader读取csv。
"""
import yaml
import os
from xlrd import open_workbook
from csv import reader, DictReader
import xlutils.copy


class YamlReader(object):
    """
    读取yaml文件中的内容，返回list
    """

    def __init__(self, yamlf):
        if os.path.exists(yamlf):
            self.yamlf = yamlf
        else:
            raise FileNotFoundError('文件不存在！')
        self.__data = None

    @property
    def data(self):
        # 如果是第一次调用data，读取yaml文档，否则直接返回之前保存的数据
        if not self.__data:
            with open(self.yamlf, 'rb') as f:
                self.__data = list(yaml.safe_load_all(f))  # load后是个generator，用list组织成列表
        return self.__data


class SheetTypeError(Exception):
    pass


class ExcelReader(object):
    """
    读取excel文件中的内容。返回list。

    如：
    excel中内容为：
    | A  | B  | C  |
    | A1 | B1 | C1 |
    | A2 | B2 | C2 |

    如果 print(ExcelReader(excel, title_line=True).data)，输出结果：
    [{A: A1, B: B1, C:C1}, {A:A2, B:B2, C:C2}]

    如果 print(ExcelReader(excel, title_line=False).data)，输出结果：
    [[A,B,C], [A1,B1,C1], [A2,B2,C2]]

    可以指定sheet，通过index或者name：
    ExcelReader(excel, sheet=2)
    ExcelReader(excel, sheet='BaiDuTest')
    """

    def __init__(self, excel, sheet=0, title_line=True):
        if os.path.exists(excel):
            self.excel = excel
        else:
            raise FileNotFoundError('文件不存在！')
        self.sheet = sheet
        self.title_line = title_line
        self._data = list()

    # 装饰器添加了一个返回参数功能
    @property
    def data(self):
        if not self._data:
            workbook = open_workbook(self.excel)
            if type(self.sheet) not in [int, str]:
                raise SheetTypeError('Please pass in <type int> or <type str>, not {0}'.format(type(self.sheet)))
            elif type(self.sheet) == int:
                s = workbook.sheet_by_index(self.sheet)
            else:
                s = workbook.sheet_by_name(self.sheet)

            if self.title_line:
                title = s.row_values(0)  # 首行为title
                for col in range(1, s.nrows):
                    # 依次遍历其余行，与首行组成dict，拼到self._data中
                    self._data.append(dict(zip(title, s.row_values(col))))
            else:
                for col in range(0, s.nrows):
                    # 遍历所有行，拼到self._data中
                    self._data.append(s.row_values(col))
        return self._data

    def deleteData(self):
        if not self._data:
            rb = open_workbook(self.excel)
            if type(self.sheet) not in [int, str]:
                raise SheetTypeError('Please pass in <type int> or <type str>, not {0}'.format(type(self.sheet)))
            elif type(self.sheet) == int:
                s = rb.sheet_by_index(self.sheet)
            else:
                s = rb.sheet_by_name(self.sheet)

            if self.title_line:
                # 首行为title
                title = s.row_values(0)
                # 跳过第二行
                for col in range(2, s.nrows):
                    # 依次遍历其余行，与首行组成dict，拼到self._data中
                    self._data.append(dict(zip(title, s.row_values(col))))
            else:
                # 跳过第二行
                for col in range(1, s.nrows):
                    # 遍历所有行，拼到self._data中
                    self._data.append(s.row_values(col))

            # 重新写入数据，然后覆盖保存，达到删除第二行的目的
            title = s.row_values(0)
            wb = xlutils.copy.copy(rb)
            # 获取sheet对象，通过sheet_by_index()获取的sheet对象没有write()方法
            ws = wb.get_sheet(0)
            n = 0
            datas = list(self._data)
            # wb = xlwt.Workbook()  # 注意Workbook的开头W要大写
            ws.write(0, n, title[0])
            for i in datas:
                n = n + 1
                ws.write(n, 0, int(i[title[0]]))
            # sheet1 = wb.add_sheet("sheet1", cell_overwrite_ok=True)
            # wb.add_sheet('sheetnnn2', cell_overwrite_ok=True)
            wb.save(self.excel)

    # 装饰器添加了一个返回参数功能
    @property
    def testdata(self):
        if not self._data:
            workbook = open_workbook(self.excel)
            if type(self.sheet) not in [int, str]:
                raise SheetTypeError('Please pass in <type int> or <type str>, not {0}'.format(type(self.sheet)))
            elif type(self.sheet) == int:
                s = workbook.sheet_by_index(self.sheet)
            else:
                s = workbook.sheet_by_name(self.sheet)

            if self.title_line:
                title = s.row_values(0)  # 首行为title
                for col in range(1, s.nrows):
                    # 依次遍历其余行,拼到self._data中
                    self._data.append(s.row_values(col))
            else:
                for col in range(0, s.nrows):
                    # 遍历所有行，拼到self._data中
                    self._data.append(s.row_values(col))
        return self._data


class CsvReader(object):
    """
    读取csv文件中的内容，返回list
    """

    def __init__(self, csvf, title_line=True):
        if os.path.exists(csvf):
            self.csvf = csvf
        else:
            raise FileNotFoundError('文件不存在！')
        self.title_line = title_line
        self.__data = None

    @property
    def data(self):
        # 如果是第一次调用data，读取csv文档，否则直接返回之前保存的数据
        if not self.__data:
            with open(self.csvf, 'r') as f:
                if self.title_line:
                    self.__data = list(DictReader(f))  # load后是个generator，用list组织成列表
                else:
                    self.__data = list(reader(f))
        return self.__data


if __name__ == '__main__':