pip install pandas openpyxl matplotlib win32com xlwings

import win32com.client as win32

def excel_to_pdf_win32com(excel_path, pdf_path, sheet_name=None):
    """
    使用win32com將Excel轉換為PDF
    :param excel_path: Excel文件路徑
    :param pdf_path: 輸出PDF路徑
    :param sheet_name: 指定工作表名，None則轉換所有
    """
    excel = win32.gencache.EnsureDispatch('Excel.Application')
    excel.Visible = False  # 不顯示Excel界面
    
    try:
        workbook = excel.Workbooks.Open(excel_path)
        
        if sheet_name:
            # 轉換單個工作表
            sheets = workbook.Worksheets(sheet_name)
            sheets.ExportAsFixedFormat(0, pdf_path)  # 0=PDF格式
        else:
            # 轉換所有工作表
            for sheet in workbook.Worksheets:
                # 為每個工作表創(chuàng)建單獨PDF或合并（此處演示單獨）
                sheet_pdf_path = f"{pdf_path.rsplit('.', 1)[0]}_{sheet.Name}.pdf"
                sheet.ExportAsFixedFormat(0, sheet_pdf_path)
                
    except Exception as e:
        print(f"轉換失敗: {e}")
    finally:
        workbook.Close(False)
        excel.Quit()

# 使用示例
excel_to_pdf_win32com('data.xlsx', 'output.pdf', 'Sheet1')

import pandas as pd
from matplotlib.backends.backend_pdf import PdfPages
import matplotlib.pyplot as plt

def excel_to_pdf_pandas(excel_path, pdf_path, sheet_name=0):
    """
    使用pandas+matplotlib將Excel轉換為PDF
    :param sheet_name: 工作表名或索引，默認第一個
    """
    df = pd.read_excel(excel_path, sheet_name=sheet_name)
    
    with PdfPages(pdf_path) as pdf:
        fig, ax = plt.subplots(figsize=(12, 6))
        ax.axis('tight')
        ax.axis('off')
        
        # 創(chuàng)建表格
        table = ax.table(
            cellText=df.values,
            colLabels=df.columns,
            loc='center',
            cellLoc='center'
        )
        
        # 調整樣式
        table.auto_set_font_size(False)
        table.set_fontsize(10)
        table.scale(1.2, 1.2)
        
        pdf.savefig(fig, bbox_inches='tight')
        plt.close()

# 使用示例（適合簡單表格）
excel_to_pdf_pandas('data.xlsx', 'simple_output.pdf')

from openpyxl import load_workbook
from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Table, TableStyle

def excel_to_pdf_openpyxl(excel_path, pdf_path, sheet_name=0):
    """
    使用openpyxl+reportlab轉換
    """
    wb = load_workbook(excel_path)
    sheet = wb.worksheets[sheet_name]
    
    # 提取數(shù)據(jù)
    data = []
    for row in sheet.iter_rows(values_only=True):
        data.append(list(row))
    
    # 創(chuàng)建PDF
    doc = SimpleDocTemplate(pdf_path, pagesize=letter)
    table = Table(data)
    
    # 添加樣式
    style = TableStyle([
        ('BACKGROUND', (0, 0), (-1, 0), '#4472C4'),  # 表頭背景
        ('TEXTCOLOR', (0, 0), (-1, 0), 'white'),      # 表頭文字
        ('ALIGN', (0, 0), (-1, -1), 'CENTER'),        # 居中
        ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
        ('FONTSIZE', (0, 0), (-1, 0), 12),
        ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
    ])
    table.setStyle(style)
    
    doc.build([table])

# 使用示例
excel_to_pdf_openpyxl('data.xlsx', 'openpyxl_output.pdf')

import os
from pathlib import Path

def batch_convert(input_folder, output_folder):
    """
    批量轉換文件夾內所有Excel文件
    """
    Path(output_folder).mkdir(parents=True, exist_ok=True)
    
    for file in os.listdir(input_folder):
        if file.endswith(('.xlsx', '.xls')):
            excel_path = os.path.join(input_folder, file)
            pdf_path = os.path.join(output_folder, f"{Path(file).stem}.pdf")
            
            try:
                excel_to_pdf_win32com(excel_path, pdf_path)
                print(f"轉換成功: {file}")
            except Exception as e:
                print(f"{file} 轉換失敗: {e}")

# 使用示例
batch_convert('input_excels', 'output_pdfs')

def convert_with_charts(excel_path, pdf_path):
    """
    保留圖表和條件格式的轉換（需win32com）
    """
    excel = win32.gencache.EnsureDispatch('Excel.Application')
    excel.Visible = False
    
    try:
        workbook = excel.Workbooks.Open(excel_path)
        
        # 復制整個工作表到新工作簿（避免修改原文件）
        new_workbook = excel.Workbooks.Add()
        workbook.Worksheets(1).Copy(Before=new_workbook.Worksheets(1))
        
        # 導出為PDF（自動包含所有圖表）
        new_workbook.Worksheets(1).ExportAsFixedFormat(0, pdf_path)
        
    finally:
        new_workbook.Close(False)
        workbook.Close(False)
        excel.Quit()

# 使用示例
convert_with_charts('complex_report.xlsx', 'formatted_output.pdf')

def convert_with_auto_size(excel_path, pdf_path, scale_factor=1.0):
    """
    根據(jù)內容自動調整PDF尺寸
    """
    excel = win32.gencache.EnsureDispatch('Excel.Application')
    excel.Visible = False
    
    try:
        workbook = excel.Workbooks.Open(excel_path)
        sheet = workbook.Worksheets(1)
        
        # 獲取打印區(qū)域設置
        if sheet.PageSetup.PrintArea:
            # 如果有打印區(qū)域，使用該范圍
            pass  # 實際實現(xiàn)需解析PrintArea范圍
        
        # 設置縮放
        sheet.PageSetup.Zoom = False
        sheet.PageSetup.FitToPagesTall = False
        sheet.PageSetup.FitToPagesWide = 1  # 強制一頁寬度
        
        # 導出PDF
        sheet.ExportAsFixedFormat(0, pdf_path)
        
    finally:
        workbook.Close(False)
        excel.Quit()

# 使用示例
convert_with_auto_size('wide_table.xlsx', 'auto_sized.pdf')

# 對于reportlab方案
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

# 注冊中文字體（需提前下載字體文件）
pdfmetrics.registerFont(TTFont('SimSun', 'SimSun.ttf'))

# 然后在TableStyle中使用
style = TableStyle([
    ('FONTNAME', (0, 0), (-1, -1), 'SimSun'),
])

# 處理大文件時分段讀取
def convert_large_file(excel_path, pdf_path, chunk_size=1000):
    """
    分段處理大型Excel文件
    """
    excel = win32.gencache.EnsureDispatch('Excel.Application')
    excel.Visible = False
    
    try:
        workbook = excel.Workbooks.Open(excel_path)
        sheet = workbook.Worksheets(1)
        
        # 獲取總行數(shù)
        used_range = sheet.UsedRange
        total_rows = used_range.Rows.Count
        
        # 分段處理邏輯（此處簡化，實際需實現(xiàn)分段導出）
        for i in range(0, total_rows, chunk_size):
            # 每次處理chunk_size行
            pass
            
    finally:
        workbook.Close(False)
        excel.Quit()

gs -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 -dPDFSETTINGS=/ebook -dNOPAUSE -dQUIET -dBATCH -sOutputFile=compressed.pdf input.pdf

import subprocess

def compress_pdf(input_path, output_path):
    cmd = [
        'gs',
        '-sDEVICE=pdfwrite',
        '-dCompatibilityLevel=1.4',
        '-dPDFSETTINGS=/ebook',
        '-dNOPAUSE',
        '-dQUIET',
        '-dBATCH',
        f'-sOutputFile={output_path}',
        input_path
    ]
    subprocess.run(cmd, check=True)

# converter.py
import os
from enum import Enum
from typing import Union, Optional

class ConvertMethod(Enum):
    WIN32COM = 1
    PANDAS = 2
    OPENPYXL = 3

class ExcelConverter:
    def __init__(self, method: ConvertMethod = ConvertMethod.WIN32COM):
        self.method = method
        
    def convert(self, 
                input_path: str, 
                output_path: str, 
                sheet_name: Optional[Union[str, int]] = None,
                **kwargs) -> bool:
        """
        統(tǒng)一轉換接口
        """
        if self.method == ConvertMethod.WIN32COM:
            from .utils import win32com_convert
            return win32com_convert(input_path, output_path, sheet_name, **kwargs)
        elif self.method == ConvertMethod.PANDAS:
            from .utils import pandas_convert
            return pandas_convert(input_path, output_path, sheet_name, **kwargs)
        else:
            from .utils import openpyxl_convert
            return openpyxl_convert(input_path, output_path, sheet_name, **kwargs)

# 使用示例
if __name__ == "__main__":
    converter = ExcelConverter(ConvertMethod.WIN32COM)
    success = converter.convert(
        input_path='data.xlsx',
        output_path='output.pdf',
        sheet_name='Sheet1',
        scale_factor=1.2
    )
    
    print("轉換成功" if success else "轉換失敗")

style = TableStyle([
    ('GRID', (0, 0), (-1, -1), 1, 'black'),  # 添加網(wǎng)格線
])

from PyPDF2 import PdfMerger

def merge_pdfs(pdf_list, output_path):
    merger = PdfMerger()
    for pdf in pdf_list:
        merger.append(pdf)
    merger.write(output_path)
    merger.close()

# 先轉換每個工作表為單獨PDF，再合并

try:
    # 操作代碼
finally:
    if 'workbook' in locals():
        workbook.Close(False)
    if 'excel' in locals():
        excel.Quit()

sheet.PageSetup.CenterHeader = "&""Arial,Bold""&12報表標題"
sheet.PageSetup.RightFooter = "第&P頁，共&N頁"

# win32com方案
sheet.ExportAsFixedFormat(
    0, 
    pdf_path,
    Quality=0,  # 0=最高質量
    IncludeDocProperties=True,
    IgnorePrintAreas=False
)