寫入:
# 以下代碼默認已經導入 np,pd
import numpy as np
import pandas as pd
# 執行下面示例之前,最好先刪除 ./test.xlsx 文件覆蓋所有原有數據,只保留最后一份數據:
# pandas:1.4.1 openpyxl:3.0.9
# 刪除文件原有數據,只保留 s2 一份數據(最后一份)
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
s1.to_excel('test.xlsx', sheet_name="111", index=False)
s2.to_excel('test.xlsx', sheet_name="222", index=False) # 只保留此份數據覆蓋所有原有數據,保留當前寫入的多份數據:
# pandas:1.4.1 openpyxl:3.0.9
# 刪除文件原有數據,同時保留s1 和s2 兩份數據
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
with pd.ExcelWriter("test.xlsx") as writer:
# 保留兩份數據
s1.to_excel(writer, sheet_name="111", index=False)
s2.to_excel(writer, sheet_name="222", index=False)保留原有數據,新開一個sheet 寫入數據
# pandas:1.4.1 openpyxl:3.0.9
# 保留原有數據 s1,新開一個sheet 寫入數據 s2
from openpyxl import load_workbook
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
# 先寫入 s1 的數據(會新建excel文件)
s1.to_excel('test.xlsx', sheet_name='111', index=False)
book = load_workbook("test.xlsx") # 該文件必須存在,並且該語句必須在 with pd.ExcelWriter() 之前
with pd.ExcelWriter("test.xlsx") as writer:
writer.book = book
s2.to_excel(writer, sheet_name="222", index=False)
# 新增一個sheet 並寫入,如果這里這里指定的sheet已經存在,那么會在該名稱后追加1,2,3,... 創建一個新的sheet寫入,不會在原有sheet上修改重寫指定sheet數據,保留原有的其余sheet數據
# pandas:1.4.1 openpyxl:3.0.9
# 重寫指定sheet數據,保留原有的其余sheet數據
from openpyxl import load_workbook
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
s3 = pd.DataFrame(np.array([['s3', 's3', 's3', 's3']]), columns=['a', 'b', 'c', 'd'])
with pd.ExcelWriter("test.xlsx") as writer:
# 先寫入兩個sheet
s1.to_excel(writer, sheet_name="111", index=False)
s2.to_excel(writer, sheet_name="222", index=False)
book = load_workbook("test.xlsx")
with pd.ExcelWriter("test.xlsx") as writer:
writer.book = book
writer.sheets = {i.title: i for i in book.worksheets} # 指定sheet
s3.to_excel(writer, sheet_name="111", index=False)修改指定sheet內的部分數據,其余保持不變
# pandas:1.4.1 openpyxl:3.0.9
# 修改指定sheet內的部分數據,其余保持不變
from openpyxl import load_workbook
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
with pd.ExcelWriter("test.xlsx") as writer:
# 先寫入兩個sheet
s1.to_excel(writer, sheet_name="111", index=False)
s2.to_excel(writer, sheet_name="222", index=False)
book = load_workbook("test.xlsx")
with pd.ExcelWriter("test.xlsx") as writer:
writer.book = book
sheet = book['222'] # 通過sheet名稱 獲取 sheet
sheet.cell(2, 1, 'hello') # 修改第二行第一列的值
sheet['b2'] = '你好' # 修改 b2 單元格的值向 sheet 中追加數據
1.在Excel 中追加
# pandas:1.4.1 openpyxl:3.0.9
# 向sheet中追加數據(一),在Excel 中追加
from openpyxl import load_workbook
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
# s4 只有3列,並且列順序被打亂,以模擬新數據與元數據的差異
s4 = pd.DataFrame(np.array([['s4b', 's4d', 's4c']]), columns=['b', 'd', 'c'])
with pd.ExcelWriter("test.xlsx") as writer:
# 先寫入兩個sheet
s1.to_excel(writer, sheet_name="111", index=False)
s2.to_excel(writer, sheet_name="222", index=False)
df = pd.read_excel('test.xlsx', sheet_name='111')
row = df.shape[0] # 獲取原數據的行數
# 將 新數據 格式化成原數據的模樣,以解決數據列之間的差異
s4 = pd.concat([pd.DataFrame(columns=df.columns), s4], ignore_index=True)
book = load_workbook("test.xlsx")
with pd.ExcelWriter("test.xlsx") as writer:
writer.book = book
writer.sheets = {sheet.title: sheet for sheet in book.worksheets}
# 追加新數據,追加前必須先格式化新數據,否則新數據缺少列,或是列順序不對會導致數據紊亂
s4.to_excel(writer, sheet_name='111', startrow=row + 1, index=False, header=False)向sheet中追加數據
2.在pandas中追加數據后,重寫指定sheet
# pandas:1.4.1 openpyxl:3.0.9
# 向sheet中追加數據(二),在pandas中追加數據后,重寫指定sheet
from openpyxl import load_workbook
s1 = pd.DataFrame(np.array([['s1', 's1', 's1', 's1']]), columns=['a', 'b', 'c', 'd'])
s2 = pd.DataFrame(np.array([['s2', 's2', 's2', 's2']]), columns=['a', 'b', 'c', 'd'])
# s4 只有3列,並且列順序被打亂,以模擬新數據與元數據的差異
s4 = pd.DataFrame(np.array([['s4b', 's4d', 's4c']]), columns=['b', 'd', 'c'])
with pd.ExcelWriter("test.xlsx") as writer:
s1.to_excel(writer, sheet_name="111", index=False)
s2.to_excel(writer, sheet_name="222", index=False)
df = pd.read_excel('test.xlsx', sheet_name='111')
df = pd.concat([df, s4], ignore_index=True) # 合並數據
book = load_workbook("test.xlsx")
with pd.ExcelWriter("test.xlsx") as writer:
writer.book = book
writer.sheets = {sheet.title: sheet for sheet in book.worksheets}
df.to_excel(writer, sheet_name='111', index=False) # 重寫sheet 