pip install PyPDF2

import PyPDF2
import os

def merge_pdfs_pypdf2(pdf_list, output_path):
    """
    使用PyPDF2合并PDF文件
    
    參數(shù):
        pdf_list: PDF文件路徑列表
        output_path: 輸出文件路徑
    """
    if not pdf_list:
        print("錯(cuò)誤：PDF文件列表為空")
        return
    
    # 創(chuàng)建PDF合并器
    pdf_merger = PyPDF2.PdfFileMerger()
    
    try:
        for pdf_path in pdf_list:
            if not os.path.exists(pdf_path):
                print(f"警告：文件不存在 {pdf_path}")
                continue
                
            print(f"添加: {os.path.basename(pdf_path)}")
            pdf_merger.append(pdf_path)
        
        # 寫入合并后的文件
        with open(output_path, 'wb') as output_file:
            pdf_merger.write(output_file)
        
        print(f"\n? 合并完成！輸出文件: {output_path}")
        print(f"?? 文件大小: {os.path.getsize(output_path):,} 字節(jié)")
        
    except Exception as e:
        print(f"? 合并失敗: {str(e)}")
    finally:
        pdf_merger.close()

# 使用示例
if __name__ == "__main__":
    pdf_files = ["report1.pdf", "report2.pdf", "report3.pdf"]
    merge_pdfs_pypdf2(pdf_files, "merged_reports.pdf")

pip install pypdf

from pypdf import PdfMerger
import os
import glob

def merge_pdfs_pypdf(folder_path=None, pdf_list=None, output_path="merged.pdf"):
    """
    使用pypdf合并PDF文件
    
    參數(shù):
        folder_path: 包含PDF的文件夾路徑
        pdf_list: PDF文件路徑列表
        output_path: 輸出文件路徑
    """
    merger = PdfMerger()
    processed_files = 0
    
    try:
        # 確定輸入源
        if folder_path and os.path.isdir(folder_path):
            # 從文件夾獲取所有PDF文件
            pdf_files = sorted(glob.glob(os.path.join(folder_path, "*.pdf")))
            print(f"?? 從文件夾讀取 {len(pdf_files)} 個(gè)PDF文件")
        elif pdf_list:
            pdf_files = pdf_list
        else:
            raise ValueError("必須提供文件夾路徑或PDF文件列表")
        
        # 逐個(gè)處理PDF文件
        for i, pdf_file in enumerate(pdf_files, 1):
            if not os.path.exists(pdf_file):
                print(f"??  跳過不存在的文件: {pdf_file}")
                continue
            
            try:
                merger.append(pdf_file)
                processed_files += 1
                print(f"? ({i}/{len(pdf_files)}) 已添加: {os.path.basename(pdf_file)}")
            except Exception as e:
                print(f"? 添加失敗 {pdf_file}: {str(e)}")
        
        if processed_files == 0:
            print("??  沒有成功添加任何PDF文件")
            return
        
        # 保存合并后的文件
        merger.write(output_path)
        
        print(f"\n?? 合并完成！")
        print(f"?? 輸出文件: {output_path}")
        print(f"?? 合并了 {processed_files} 個(gè)文件")
        print(f"?? 文件大小: {os.path.getsize(output_path):,} 字節(jié)")
        
    except Exception as e:
        print(f"? 合并過程出錯(cuò): {str(e)}")
    finally:
        merger.close()

# 使用示例
if __name__ == "__main__":
    # 方式1：合并指定文件列表
    files = ["chapter1.pdf", "chapter2.pdf", "appendix.pdf"]
    merge_pdfs_pypdf(pdf_list=files, output_path="complete_book.pdf")
    
    # 方式2：合并文件夾內(nèi)所有PDF
    # merge_pdfs_pypdf(folder_path="./documents", output_path="all_docs.pdf")

from pypdf import PdfMerger
import os

def merge_pdfs_with_bookmarks(pdf_list, output_path):
    """合并PDF并添加書簽"""
    merger = PdfMerger()
    
    for i, pdf_path in enumerate(pdf_list):
        # 添加PDF文件
        merger.append(pdf_path)
        
        # 添加書簽（使用文件名作為書簽名）
        bookmark_name = os.path.splitext(os.path.basename(pdf_path))[0]
        merger.add_outline_item(bookmark_name, i)
    
    merger.write(output_path)
    merger.close()
    print(f"已創(chuàng)建帶書簽的PDF: {output_path}")

pip install PyPDF4

import PyPDF4
import os

def merge_pdfs_pypdf4(pdf_list, output_path):
    """使用PyPDF4合并PDF"""
    pdf_merger = PyPDF4.PdfFileMerger()
    
    for pdf_path in pdf_list:
        if os.path.exists(pdf_path):
            pdf_merger.append(pdf_path)
    
    with open(output_path, 'wb') as output_file:
        pdf_merger.write(output_file)
    
    pdf_merger.close()
    return True

#!/usr/bin/env python3
"""
PDF合并工具 - 功能完整的實(shí)現(xiàn)
支持：批量合并、文件夾掃描、進(jìn)度顯示、錯(cuò)誤處理
"""

import os
import sys
import argparse
import glob
from datetime import datetime
from pypdf import PdfMerger, PdfReader

class PDFMergerTool:
    """PDF合并工具類"""
    
    def __init__(self):
        self.total_pages = 0
        self.start_time = None
    
    def get_pdf_list(self, input_source):
        """獲取PDF文件列表"""
        pdf_files = []
        
        # 判斷輸入源類型
        if os.path.isdir(input_source):
            # 輸入是文件夾
            pdf_files = sorted(glob.glob(os.path.join(input_source, "*.pdf")))
            if not pdf_files:
                # 嘗試其他擴(kuò)展名
                pdf_files = sorted(glob.glob(os.path.join(input_source, "*.PDF")))
        else:
            # 輸入可能是通配符或文件列表
            if '*' in input_source:
                pdf_files = sorted(glob.glob(input_source))
            else:
                # 檢查是否是包含文件列表的文本文件
                if os.path.isfile(input_source) and input_source.endswith('.txt'):
                    with open(input_source, 'r', encoding='utf-8') as f:
                        pdf_files = [line.strip() for line in f if line.strip()]
                else:
                    pdf_files = [input_source]
        
        # 過濾存在的文件
        valid_files = []
        for pdf in pdf_files:
            if os.path.exists(pdf):
                valid_files.append(pdf)
            else:
                print(f"警告：文件不存在 {pdf}")
        
        return valid_files
    
    def calculate_total_pages(self, pdf_files):
        """計(jì)算總頁數(shù)"""
        total = 0
        for pdf in pdf_files:
            try:
                with open(pdf, 'rb') as f:
                    reader = PdfReader(f)
                    total += len(reader.pages)
            except:
                pass
        return total
    
    def merge_pdfs(self, pdf_files, output_path, add_bookmarks=True):
        """合并PDF文件的主要功能"""
        if not pdf_files:
            print("錯(cuò)誤：沒有找到有效的PDF文件")
            return False
        
        self.start_time = datetime.now()
        merger = PdfMerger()
        processed = 0
        
        print(f"?? 找到 {len(pdf_files)} 個(gè)PDF文件")
        self.total_pages = self.calculate_total_pages(pdf_files)
        print(f"?? 總頁數(shù): {self.total_pages}")
        print("-" * 50)
        
        try:
            for i, pdf_file in enumerate(pdf_files, 1):
                file_size = os.path.getsize(pdf_file)
                file_name = os.path.basename(pdf_file)
                
                print(f"[{i}/{len(pdf_files)}] 處理: {file_name}")
                print(f"   大小: {file_size:,} 字節(jié)")
                
                try:
                    # 添加PDF文件
                    merger.append(pdf_file)
                    
                    # 添加書簽
                    if add_bookmarks:
                        bookmark_name = os.path.splitext(file_name)[0]
                        merger.add_outline_item(bookmark_name, i-1)
                    
                    processed += 1
                    print(f"   ? 已添加")
                    
                except Exception as e:
                    print(f"   ? 添加失敗: {str(e)}")
                
                print()
            
            # 寫入輸出文件
            print(f"?? 正在寫入文件: {output_path}")
            merger.write(output_path)
            
            # 統(tǒng)計(jì)信息
            elapsed = datetime.now() - self.start_time
            output_size = os.path.getsize(output_path)
            
            print("\n" + "=" * 50)
            print("?? PDF合并完成！")
            print("=" * 50)
            print(f"?? 統(tǒng)計(jì)信息:")
            print(f"   處理文件數(shù): {processed}/{len(pdf_files)}")
            print(f"   輸出文件: {output_path}")
            print(f"   輸出大小: {output_size:,} 字節(jié)")
            print(f"   耗時(shí): {elapsed.total_seconds():.2f} 秒")
            
            if self.total_pages > 0:
                print(f"   平均速度: {self.total_pages/elapsed.total_seconds():.1f} 頁/秒")
            
            return True
            
        except Exception as e:
            print(f"\n? 合并過程中出錯(cuò): {str(e)}")
            return False
        
        finally:
            merger.close()
    
    def run_from_cli(self):
        """命令行界面"""
        parser = argparse.ArgumentParser(
            description="PDF文件合并工具",
            formatter_class=argparse.RawDescriptionHelpFormatter,
            epilog="""
使用示例:
  %(prog)s file1.pdf file2.pdf -o merged.pdf
  %(prog)s "*.pdf" -o all_documents.pdf
  %(prog)s ./documents/ -o combined.pdf
  %(prog)s filelist.txt -o output.pdf
            """
        )
        
        parser.add_argument(
            'input',
            nargs='+',
            help='輸入文件、文件夾或通配符模式'
        )
        
        parser.add_argument(
            '-o', '--output',
            default='merged.pdf',
            help='輸出文件名 (默認(rèn): merged.pdf)'
        )
        
        parser.add_argument(
            '-b', '--no-bookmarks',
            action='store_true',
            help='不添加書簽'
        )
        
        parser.add_argument(
            '-v', '--verbose',
            action='store_true',
            help='顯示詳細(xì)輸出'
        )
        
        args = parser.parse_args()
        
        # 處理輸入?yún)?shù)
        input_source = ' '.join(args.input)
        
        # 獲取PDF文件列表
        pdf_files = self.get_pdf_list(input_source)
        
        if not pdf_files:
            print("錯(cuò)誤：未找到PDF文件")
            sys.exit(1)
        
        # 執(zhí)行合并
        success = self.merge_pdfs(
            pdf_files,
            args.output,
            add_bookmarks=not args.no_bookmarks
        )
        
        sys.exit(0 if success else 1)

def main():
    """主函數(shù)"""
    print("=" * 60)
    print("?? PDF合并工具 v1.0")
    print("=" * 60)
    
    tool = PDFMergerTool()
    
    # 檢查是否通過命令行調(diào)用
    if len(sys.argv) > 1:
        tool.run_from_cli()
    else:
        # 交互式模式
        print("\n?? 請(qǐng)選擇輸入方式:")
        print("1. 輸入文件列表（用空格分隔）")
        print("2. 輸入文件夾路徑")
        print("3. 使用通配符（如 *.pdf）")
        print("4. 從文本文件讀取文件列表")
        
        choice = input("\n請(qǐng)選擇 (1-4): ").strip()
        
        if choice == '1':
            files = input("請(qǐng)輸入PDF文件路徑（空格分隔）: ").split()
            pdf_files = [f.strip() for f in files]
        elif choice == '2':
            folder = input("請(qǐng)輸入文件夾路徑: ").strip()
            pdf_files = tool.get_pdf_list(folder)
        elif choice == '3':
            pattern = input("請(qǐng)輸入通配符模式（如 *.pdf）: ").strip()
            pdf_files = tool.get_pdf_list(pattern)
        elif choice == '4':
            txt_file = input("請(qǐng)輸入文本文件路徑: ").strip()
            pdf_files = tool.get_pdf_list(txt_file)
        else:
            print("無效選擇")
            return
        
        output_file = input("輸出文件名 (默認(rèn): merged.pdf): ").strip()
        if not output_file:
            output_file = "merged.pdf"
        
        add_bookmarks = input("添加書簽? (y/n, 默認(rèn): y): ").strip().lower()
        add_bookmarks = add_bookmarks != 'n'
        
        tool.merge_pdfs(pdf_files, output_file, add_bookmarks)

if __name__ == "__main__":
    main()

def merge_large_pdfs(pdf_list, output_path, chunk_size=100):
    """
    分批處理大型PDF文件以減少內(nèi)存使用
    
    參數(shù):
        chunk_size: 每次處理的文件數(shù)
    """
    from pypdf import PdfMerger
    import tempfile
    import os
    
    temp_files = []
    
    try:
        # 分批處理
        for i in range(0, len(pdf_list), chunk_size):
            chunk = pdf_list[i:i+chunk_size]
            merger = PdfMerger()
            
            for pdf in chunk:
                merger.append(pdf)
            
            # 保存臨時(shí)文件
            temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.pdf')
            merger.write(temp_file.name)
            merger.close()
            
            temp_files.append(temp_file.name)
        
        # 合并所有臨時(shí)文件
        final_merger = PdfMerger()
        for temp_file in temp_files:
            final_merger.append(temp_file)
        
        final_merger.write(output_path)
        final_merger.close()
        
    finally:
        # 清理臨時(shí)文件
        for temp_file in temp_files:
            try:
                os.unlink(temp_file)
            except:
                pass

def safe_merge_pdfs(pdf_list, output_path):
    """帶有完善錯(cuò)誤處理的合并函數(shù)"""
    import traceback
    
    try:
        # 參數(shù)驗(yàn)證
        if not pdf_list:
            raise ValueError("PDF文件列表不能為空")
        
        for pdf in pdf_list:
            if not os.path.exists(pdf):
                raise FileNotFoundError(f"文件不存在: {pdf}")
            
            if not pdf.lower().endswith('.pdf'):
                print(f"警告：文件可能不是PDF格式: {pdf}")
        
        # 執(zhí)行合并
        merge_pdfs_pypdf(pdf_list, output_path)
        return True
        
    except PermissionError:
        print("錯(cuò)誤：文件訪問被拒絕，請(qǐng)檢查權(quán)限")
        return False
    except MemoryError:
        print("錯(cuò)誤：內(nèi)存不足，嘗試分批處理")
        return False
    except Exception as e:
        print(f"未知錯(cuò)誤: {str(e)}")
        if DEBUG_MODE:
            traceback.print_exc()
        return False

from pypdf import PdfWriter, PdfReader

def add_page_numbers(input_pdf, output_pdf):
    """在合并后的PDF中添加頁碼"""
    reader = PdfReader(input_pdf)
    writer = PdfWriter()
    
    for i, page in enumerate(reader.pages, 1):
        # 這里可以添加自定義的頁碼繪制邏輯
        # 實(shí)際實(shí)現(xiàn)需要使用reportlab等庫繪制文本
        writer.add_page(page)
    
    with open(output_pdf, 'wb') as f:
        writer.write(f)

def merge_selective_pages(pdf_list, page_ranges, output_path):
    """合并指定頁面范圍"""
    merger = PdfMerger()
    
    for pdf, page_range in zip(pdf_list, page_ranges):
        # page_range格式: "1-3,5,7-9"
        merger.append(pdf, pages=page_range)
    
    merger.write(output_path)
    merger.close()