python 之 自己记录的几个快捷方式 - Excel 操作

python 之 自己记录的几个快捷方式 - Excel

# -*- coding:utf8 -*-
import codecs
from openpyxl.styles import Alignment
from openpyxl.styles import PatternFill
from openpyxl.styles import Font
from openpyxl import Workbook, load_workbook
from os import remove, path
from openpyxl import *
import xlrd
import csv
import xlwt
import pandas as pd
import xlwings as xw
import win32com.client
import xlwings as xw
import pandas as pd
import numpy as np

# 将DataFrame转换成格式化excel的工具
class XlsxSaver:
    """
    一个将DataFrame转换成格式化excel的工具
    """
    def __init__(self, df_in, filename='a.xlsx', sheet_name='Sheet1'):
        """
        df_in : 从一个DataFrame对象获取表格内容
        filename : 文件名
        sheet_name : 表名
        """
        self.filename = filename  # 保存的xlsx文件的名字
        self.user_def = []  # 储存由用户自定义的列的列名，这些列不再参与自动计算列宽
        if path.exists(filename):
            # 如果文件存在，就直接打开，添加Sheet
            self.wb = load_workbook(filename)
            self.sheet = self.wb.create_sheet(sheet_name)
        else:
            # 如果文件不存在，就创建表格
            self.wb = Workbook()
            self.sheet = self.wb.active
            self.sheet.title = sheet_name
        # 将df的内容复制给sheet
        self.df = df_in.copy()
        self.sheet.append(list(self.df.columns))
        for row in range(0, len(list(self.df.index))):
            for col in range(0, len(list(self.df.columns))):
                self.sheet.cell(row+2, col+1).value = self.df.iloc[row, col]  # 注意：sheet行列从1开始计数
    
    def remove_file(self):
        remove(self.filename)

    def set_sheet_name(self, sheet_name):
        self.sheet.title = sheet_name
    
    def set_filename(self, filename):
        self.filename = filename
        
    def get_maxlength(self, series_in, col):
        """
        获取一个类型为object的Series中的最大占位长度，用于确定导出的xlsx文件的列宽
        col : 表头，也参与比较，解决有时候表头过长的问题
        """
        series = series_in.fillna('-')  # 填充空值，防止出现nan
        str_list = list(series)
        len_list = []
        for elem in str_list + [col]:
            elem_split = list(elem)
            length = 0
            for c in elem_split:
                if ord(c) <= 256:
                    length += 1
                else:
                    length += 2
            len_list.append(length)
        return max(len_list)

    def __auto_width(self):
        cols_list = list(self.df.columns)  # 获取列名
        for i in range(0, len(cols_list)):
            col = cols_list[i]
            if col in self.user_def:
                continue
            self.sheet.cell(1, i+1).font = Font(bold=True)  # 加粗表头
            letter = chr(i+65)  # 由ASCII值获得对应的列字母
            max_len = self.get_maxlength(self.df[col].astype(str), col)
            if max_len <= 12:
                self.sheet.column_dimensions[letter].width = 12
            elif max_len <= 50:
                self.sheet.column_dimensions[letter].width = max_len + 2
            else:
                self.sheet.column_dimensions[letter].width = 50
                for cell in self.sheet[letter]:
                    cell.alignment = Alignment(wrap_text=True)
    
    def set_width(self, col_name, width):
        # 提供调整列宽的接口
        index = list(self.df.columns).index(col_name)
        letter = chr(index+65)
        self.sheet.column_dimensions[letter].width = width
        self.user_def.append(col_name)
        
    def set_color(self, col_name, color, rule):
        # 提供设置颜色的接口，rule:规则函数
        index = list(self.df.columns).index(col_name)
        letter = chr(index+65)
        for cell in self.sheet[letter]:
            if rule(cell.value):
                cell.fill = PatternFill(fill_type="solid", start_color=color, end_color=color)
    
    def set_center_alignment(self, col_name):
        index = list(self.df.columns).index(col_name)
        letter = chr(index+65)
        for cell in self.sheet[letter]:
            cell.alignment = Alignment(wrap_text=True, horizontal='center')

    def save(self):
        # 自动调整列宽，并保存
        self.__auto_width()
        self.wb.save(self.filename)
    
    def set_merge(self, col_name):
        self.user_def.append(col_name)  # 设置为自定义列
        # 设置一列合并单元格
        index = list(self.df.columns).index(col_name)
        letter = chr(index+65)
        i = 1
        while True:
            if i >= self.sheet.max_row:
                # 结束条件：单元格到底
                break
            cell = self.sheet[letter+str(i)]
            j = i+1  # 第一步指向下一个单元格
            while True:
                # 这个过程对j进行试探，最终j指向的单元格是与i连续相同的最后一个
                cell_next = self.sheet[letter+str(j)]
                if cell_next.value != cell.value:
                    j -= 1
                    break
                else:
                    j += 1
                if j > self.sheet.max_row:
                    j -= 1
                    break
            if j-i >= 1 and cell.value != '' and cell.value:
                # 如果有连续两格以上的单元格内容相同，进行融合
                msg = '%s%d:%s%d'%(letter,i,letter,j)
                self.sheet.merge_cells(msg)
            # 控制一下格式
            self.sheet[letter+str(i)].alignment = Alignment(horizontal='center',
                                                            vertical='top',
                                                            wrap_text=True)
            i = j+1  # 继续指向下个单元格


# 判断元素是否为数字
def is_number(s):
    try:
        if np.isnan(s) or s == False or s == True:
            return False
    except Exception:
        pass
    try:
        # 判断是否为浮点数
        float(s)
        return True
    except Exception:
        pass
    try:
        import unicodedata  # 处理ASCii码的包
        # 把一个表示数字的字符串转换为浮点数返回的函数
        unicodedata.numeric(s)
        return True
    except (TypeError, ValueError):
        pass
    return False


# 获取Excel
class GetExcel():
    def __init__(self,file):
        self.file = file
        self.wb = load_workbook(self.file)
        sheets = self.wb.get_sheet_names()
        self.sheet = sheets[0]
        self.ws = self.wb[self.sheet]
        
    #获取表格的总行数和总列数
    def getRowsClosNum(self):
        rows = self.ws.max_row
        columns = self.ws.max_column
        return rows,columns
    
    #获取某个单元格的值
    def getCellValue(self,row,column):       
        cellvalue = self.ws.cell(row=row,column=column).value
        return cellvalue
    
    #获取某列的所有值
    def getColValues(self,column):
        rows = self.ws.max_row
        columndata=[]
        for i in range(1,rows+1):
            cellvalue = self.ws.cell(row=i,column=column).value
            columndata.append(cellvalue)
        return columndata
    
    
    #获取某行所有值
    def getRowValues(self,row):
        columns = self.ws.max_column
        rowdata=[]
        for i in range(1,columns+1):
            cellvalue = self.ws.cell(row=row,column=i).value
            rowdata.append(cellvalue)
        return rowdata
    
    #设置某个单元格的值
    def setCellValue(self,row,colunm,cellvalue):
        try:
            self.ws.cell(row=row,column=colunm).value=cellvalue
            self.wb.save(self.file)
        except:
            self.ws.cell(row=row,column=colunm).value="writefail"
            self.wb.save(self.file)


# xlsx转csv
def xlsx_to_csv(xlsxfile,csvfile):
    workbook = xlrd.open_workbook(xlsxfile)
    table = workbook.sheet_by_index(0)
    with codecs.open(csvfile, 'w', encoding='utf-8') as f:
        write = csv.writer(f)
        for row_num in range(table.nrows):
            row_value = table.row_values(row_num)
            write.writerow(row_value)

# xlsx转csv ，Pd模式
def xlsx_to_csv_pd(xlsxfile,csvfile):
    data_xls = pd.read_excel(xlsxfile, index_col=0,engine='xlrd')
    data_xls.to_csv(csvfile, encoding='utf-8')

# csv转xlsx
def csv_to_xlsx(csvfile, xlsxfile):
    with open(csvfile, 'r', encoding='utf-8') as f:
        read = csv.reader(f)
        workbook = xlwt.Workbook()
        sheet = workbook.add_sheet('data')  # 创建一个sheet表格
        l = 0
        for line in read:
            print(line)
            r = 0
            for i in line:
                print(i)
                sheet.write(l, r, i)  # 一个一个将单元格数据写入
                r = r + 1
            l = l + 1
 
        workbook.save(xlsxfile)  # 保存Excel

# xlsx按行去重
def xlsx_del_weight(filename):
    app = xw.App(visible=False, add_book=False)
    wb = app.books.open(filename)
    sht = wb.sheets[0]

    myList = sht[0,0].current_region.value

    tags = [] #
    m = []
    for ds in myList:
            if ds not in m:
                m.append(ds)
                tags.append(True)
            else:
                tags.append(False)
    clean_data = [ds for i,ds in enumerate(myList) if tags[i]]
    del_data = [ds for i,ds in enumerate(myList) if not tags[i]]
    del m
    sht.clear()
    sht['A1'].value = clean_data
    wb.save()
    wb.close()
    app.kill()

# xls转xlsx
def xls_to_xlsx(filename):
    excel = win32com.client.gencache.EnsureDispatch('Excel.Application')
    wb = excel.Workbooks.Open(filename)

    wb.SaveAs(filename+"x", FileFormat = 51)    #FileFormat = 51 is for .xlsx extension
    wb.Close()                               #FileFormat = 56 is for .xls extension
    excel.Application.Quit()

内容很杂，都是从其他很多大佬那里copy过来修改的。如有看到自己内容，记得私聊博主，加上原文链接。（太杂了，很多找不到了，各位大佬见谅！）