Python代码实现将HTML转换为Excel

pip install Spire.XLS

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

def ConvertHtmlToExcel():
    """将 HTML 文件转换为 Excel"""
    inputFile = "/input/表格.html"
    outputFile = "/output/Html转Excel.xlsx"
    
    # 创建工作簿对象
    workbook = Workbook()
    
    # 从 HTML 文件加载内容
    workbook.LoadFromHtml(inputFile)
    
    # 保存为 Excel 格式（Excel 2013）
    workbook.SaveToFile(outputFile, ExcelVersion.Version2013)

if __name__ == "__main__":
    ConvertHtmlToExcel()

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

def InsertHtmlIntoCell():
    """将 HTML 字符串插入 Excel 单元格"""
    outputFile = "InsertHtmlStringIntoCell.xlsx"
    
    # 创建工作簿
    workbook = Workbook()
    
    # 获取第一个工作表
    sheet = workbook.Worksheets[0]
    
    # 定义 HTML 字符串
    htmlCode = "<div>第一行<strong>第二行（加粗）</strong>第三行</div>"
    
    # 将 HTML 字符串插入到 A1 单元格
    cell_range = sheet["A1"]
    cell_range.HtmlString = htmlCode
    
    # 保存文件
    workbook.SaveToFile(outputFile, ExcelVersion.Version2013)
    workbook.Dispose()
    
    print(f"HTML 字符串已插入，Excel 文件已保存至: {outputFile}")

if __name__ == "__main__":
    InsertHtmlIntoCell()

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

def ConvertMultiTableHtml():
    """转换包含多个表格的 HTML 文件"""
    inputFile = "./Demos/Data/MultiTable.html"
    outputFile = "MultiTableExcel.xlsx"
    
    # 创建工作簿并加载 HTML
    workbook = Workbook()
    workbook.LoadFromHtml(inputFile)
    
    # 遍历所有工作表并重命名
    for i in range(workbook.Worksheets.Count):
        sheet = workbook.Worksheets[i]
        sheet.Name = f"表格_{i + 1}"
        
        # 自动调整列宽以适应内容
        sheet.AllocatedRange.AutoFitColumns()
    
    # 保存文件
    workbook.SaveToFile(outputFile, ExcelVersion.Version2013)
    workbook.Dispose()
    
    print(f"多表格 HTML 转换完成，文件已保存至: {outputFile}")

if __name__ == "__main__":
    ConvertMultiTableHtml()

import urllib.request
from spire.xls import *
from spire.xls.common import *
import tempfile
import os

def ConvertUrlToExcel(url, output_file):
    """从 URL 加载 HTML 并转换为 Excel"""
    
    # 下载 HTML 内容
    print(f"正在下载: {url}")
    response = urllib.request.urlopen(url)
    html_content = response.read().decode('utf-8')
    
    # 创建临时 HTML 文件
    with tempfile.NamedTemporaryFile(mode='w', suffix='.html', delete=False, encoding='utf-8') as temp_file:
        temp_file.write(html_content)
        temp_html_path = temp_file.name
    
    try:
        # 创建工作簿并加载 HTML
        workbook = Workbook()
        workbook.LoadFromHtml(temp_html_path)
        
        # 自动调整所有工作表的列宽
        for sheet in workbook.Worksheets:
            sheet.AllocatedRange.AutoFitColumns()
        
        # 保存为 Excel
        workbook.SaveToFile(output_file, ExcelVersion.Version2013)
        workbook.Dispose()
        
        print(f"转换完成，Excel 文件已保存至: {output_file}")
        
    finally:
        # 清理临时文件
        if os.path.exists(temp_html_path):
            os.remove(temp_html_path)

def main():
    # 示例：从网页转换（请替换为实际 URL）
    # ConvertUrlToExcel(
    #     "https://example.com/data-table.html",
    #     "WebData.xlsx"
    # )
    print("URL 转换函数已定义，取消注释 main() 中的代码即可使用")

if __name__ == "__main__":
    main()

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

class HtmlToExcelConverter:
    """HTML 转 Excel 批量转换器"""
    
    def __init__(self, output_folder=None):
        self.output_folder = output_folder or "./Excel_Output"
        
        # 创建输出文件夹
        if not os.path.exists(self.output_folder):
            os.makedirs(self.output_folder)
    
    def convert_single_file(self, input_file, output_file=None):
        """转换单个 HTML 文件为 Excel"""
        try:
            workbook = Workbook()
            workbook.LoadFromHtml(input_file)
            
            # 自动调整所有工作表的列宽
            for sheet in workbook.Worksheets:
                sheet.AllocatedRange.AutoFitColumns()
            
            if output_file is None:
                base_name = os.path.splitext(os.path.basename(input_file))[0]
                output_file = os.path.join(self.output_folder, f"{base_name}.xlsx")
            
            workbook.SaveToFile(output_file, ExcelVersion.Version2013)
            workbook.Dispose()
            
            print(f"✓ 转换成功: {os.path.basename(input_file)}")
            return True
            
        except Exception as e:
            print(f"✗ 转换失败 {os.path.basename(input_file)}: {str(e)}")
            return False
    
    def batch_convert(self, input_folder):
        """批量转换文件夹中的所有 HTML 文件"""
        html_files = []
        
        # 查找所有 HTML 文件
        for filename in os.listdir(input_folder):
            if filename.lower().endswith(('.html', '.htm')):
                html_files.append(os.path.join(input_folder, filename))
        
        if not html_files:
            print(f"在 {input_folder} 中未找到 HTML 文件")
            return
        
        print(f"找到 {len(html_files)} 个 HTML 文件，开始转换...")
        
        success_count = 0
        fail_count = 0
        
        for html_file in html_files:
            if self.convert_single_file(html_file):
                success_count += 1
            else:
                fail_count += 1
        
        print(f"\n转换完成!")
        print(f"成功: {success_count} 个文件")
        print(f"失败: {fail_count} 个文件")
        print(f"输出目录: {self.output_folder}")

def main():
    # 创建转换器实例
    converter = HtmlToExcelConverter("./Excel_Output")
    
    # 批量转换
    converter.batch_convert("./HTML_Files")
    
    # 或者转换单个文件
    # converter.convert_single_file("./Data/Table.html")

if __name__ == "__main__":
    main()