使用Spire.XLS for Python高效读取Excel数据的代码实现

pip install Spire.XLS

from spire.xls import *
from spire.xls.common import *

# 创建一个Workbook对象
workbook = Workbook()
# 加载Excel文件
# 请将 'sample.xlsx' 替换为你自己的Excel文件路径
workbook.LoadFromFile("sample.xlsx")

# 获取第一个工作表（索引从0开始）
sheet = workbook.Worksheets[0]

print(f"成功加载文件并获取工作表：{sheet.Name}")

# 记得释放资源
workbook.Dispose()

from spire.xls import *
from spire.xls.common import *

workbook = Workbook()
workbook.LoadFromFile("sample.xlsx")
sheet = workbook.Worksheets[0]

# 按A1表示法读取单元格值
cell_a1_value = sheet.Range["A1"].Value
print(f"A1单元格的值: {cell_a1_value}")

# 按行、列索引读取单元格值 (行和列索引都从1开始)
# 读取B2单元格
cell_b2_value = sheet.Range[2, 2].Value
print(f"B2单元格的值: {cell_b2_value}")

# 读取单元格的文本内容（即使是数字或日期，也会返回格式化后的字符串）
cell_c3_text = sheet.Range["C3"].Text
print(f"C3单元格的文本内容: {cell_c3_text}")

# 读取单元格批注
if sheet.Range["A1"].Comment is not None:
    comment_text = sheet.Range["A1"].Comment.Text
    print(f"A1单元格的批注: {comment_text}")

# 读取单元格超链接
if sheet.Range["A1"].HyperLink is not None:
    hyperlink_address = sheet.Range["A1"].HyperLink.Address
    print(f"A1单元格的超链接: {hyperlink_address}")

workbook.Dispose()

from spire.xls import *
from spire.xls.common import *

workbook = Workbook()
workbook.LoadFromFile("sample.xlsx")
sheet = workbook.Worksheets[0]

print("\n读取区域 B2:D4 的数据:")
# 循环遍历指定区域 (例如 B2到D4)
# Range对象的Rows和Columns属性可以帮助我们迭代
data_region = sheet.Range["B2:D4"]
for row_index in range(data_region.Row, data_region.LastRow + 1):
    row_data = []
    for col_index in range(data_region.Column, data_region.LastColumn + 1):
        cell_value = sheet.Range[row_index, col_index].Value
        row_data.append(cell_value)
    print(row_data)

workbook.Dispose()

from spire.xls import *
from spire.xls.common import *

workbook = Workbook()
workbook.LoadFromFile("sample.xlsx")
sheet = workbook.Worksheets[0]

# 假设第一行是标题行
header = [cell.Value for cell in sheet.Rows[0].Cells]
print(f"表头: {header}")

all_data = []
# 从第二行开始读取数据
for row_index in range(1, sheet.LastRow): # sheet.LastRow 返回包含数据的最后一行的索引
    row_values = [sheet.Range[row_index + 1, col_index + 1].Value for col_index in range(sheet.LastColumn)]
    
    # 如果有表头，可以将其转换为字典列表
    if header:
        row_dict = dict(zip(header, row_values))
        all_data.append(row_dict)
    else:
        all_data.append(row_values)

print("\n读取到的所有数据 (字典列表形式):")
for item in all_data:
    print(item)

workbook.Dispose()

from spire.xls import *
from spire.xls.common import *

workbook = None # 初始化为None
try:
    workbook = Workbook()
    workbook.LoadFromFile("non_existent_file.xlsx") # 故意加载不存在的文件
    sheet = workbook.Worksheets[0]
    # ... 进行其他操作 ...
except Exception as e:
    print(f"处理Excel文件时发生错误: {e}")
finally:
    if workbook is not None:
        workbook.Dispose() # 确保资源被释放
        print("Workbook资源已释放。")

from spire.xls import *
from spire.xls.common import *

try:
    with Workbook() as workbook: # 使用with语句自动管理资源
        workbook.LoadFromFile("sample.xlsx")
        sheet = workbook.Worksheets[0]
        print(f"工作表名称: {sheet.Name}")
        # ... 进行其他操作 ...
except Exception as e:
    print(f"处理Excel文件时发生错误: {e}")

print("Workbook资源已自动释放。")