Python使用Spire.PDF for Python实现将PDF转换为PDF/A

pip install Spire.PDF

from spire.pdf.common import *
from spire.pdf import *

def ConvertToPDFA():
    """将普通 PDF 转换为 PDF/A 格式"""
    inputFile = "/示例文档.pdf"
    outputFile = "ToPDFA_A1B.pdf"
    
    # 创建标准转换器
    converter = PdfStandardsConverter(inputFile)
    
    # 转换为 PDF/A-1B 格式
    converter.ToPdfA1B(outputFile)
    
    print(f"PDF/A 文件已保存至: {outputFile}")

if __name__ == "__main__":
    ConvertToPDFA()

from spire.pdf.common import *
from spire.pdf import *

def CreatePDFFromScratchAndConvertToPDFA():
    """创建新 PDF 并转换为 PDF/A 格式"""
    outputFile1 = "/output/TempDocument.pdf"
    outputFile2 = "/output/FinalPDFA1B.pdf"
    imageFile = "/Logo1.png"
    
    # 创建新的 PDF 文档
    doc = PdfNewDocument()
    
    # 添加 A4 页面并设置边距
    page = doc.Pages.Add(PdfPageSize.A4(), PdfMargins(40.0))
    
    # 获取页面宽度
    pageWidth = page.Canvas.ClientSize.Width
    y = 0.0
    
    # 绘制标题
    y = y + 5
    brush = PdfSolidBrush(PdfRGBColor(Color.get_Black()))
    font = PdfTrueTypeFont("Arial", 16.0, PdfFontStyle.Bold, True)
    format = PdfStringFormat(PdfTextAlignment.Center)
    format.CharacterSpacing = 1
    text = "AI Integration Module Introduction"
    page.Canvas.DrawString(text, font, brush, pageWidth / 2, y, format)
    size = font.MeasureString(text, format)
    y = y + size.Height + 6
    
    # 绘制图片
    image = PdfImage.FromFile(imageFile)
    page.Canvas.DrawImage(image, PointF(pageWidth - image.PhysicalDimension.Width, y))
    imageLeftSpace = pageWidth - image.PhysicalDimension.Width - 2
    imageBottom = image.PhysicalDimension.Height + y
    
    # 绘制参考信息
    font3 = PdfTrueTypeFont("Arial", 9.0, PdfFontStyle.Regular, True)
    format3 = PdfStringFormat()
    format3.ParagraphIndent = font3.Size * 2
    format3.MeasureTrailingSpaces = True
    format3.LineSpacing = font3.Size * 1.5
    text1 = "(The sample text was made by "
    text2 = "Gemini"
    text3 = ", an AI module of Google.)"
    page.Canvas.DrawString(text1, font3, brush, 0.0, y, format3)
    size = font3.MeasureString(text1, format3)
    x1 = size.Width
    format3.ParagraphIndent = 0.0
    font4 = PdfTrueTypeFont("Arial", 9.0, PdfFontStyle.Underline, True)
    brush3 = PdfBrushes.get_Blue()
    page.Canvas.DrawString(text2, font4, brush3, x1, y, format3)
    size = font4.MeasureString(text2, format3)
    x1 = x1 + size.Width
    page.Canvas.DrawString(text3, font3, brush, x1, y, format3)
    y = y + size.Height
    
    # 绘制正文内容
    format4 = PdfStringFormat()
    with open("/input/Technical Specification AI Integration Module.txt", 'r', encoding='utf-8') as f:
        text = f.read()
    font5 = PdfTrueTypeFont("Arial", 10.0, PdfFontStyle.Regular, True)
    format4.LineSpacing = font5.Size * 1.5
    textLayouter = PdfStringLayouter()
    imageLeftBlockHeight = imageBottom - y
    result = textLayouter.Layout(text, font5, format4, SizeF(imageLeftSpace, imageLeftBlockHeight))
    if result.ActualSize.Height < imageBottom - y:
        imageLeftBlockHeight = imageLeftBlockHeight + result.LineHeight
        result = textLayouter.Layout(text, font5, format4, SizeF(imageLeftSpace, imageLeftBlockHeight))
    for line in result.Lines:
        page.Canvas.DrawString(line.Text, font5, brush, 0.0, y, format4)
        y = y + result.LineHeight
    textWidget = PdfTextWidget(result.Remainder, font5, brush)
    textLayout = PdfTextLayout()
    textLayout.Break = PdfLayoutBreakType.FitPage
    textLayout.Layout = PdfLayoutType.Paginate
    bounds = RectangleF(PointF(0.0, y), page.Canvas.ClientSize)
    textWidget.StringFormat = format4
    textWidget.Draw(page, bounds, textLayout)
    
    # 保存临时文档到流
    stream = Stream(outputFile1)
    doc.Save(stream)
    
    # 使用标准转换器转换为 PDF/A-1B
    converter = PdfStandardsConverter(stream)
    converter.ToPdfA1B(outputFile2)
    
    # 关闭文档
    doc.Close(True)
    
    print(f"PDF/A-1B 文件已保存至: {outputFile2}")

if __name__ == "__main__":
    CreatePDFFromScratchAndConvertToPDFA()

from spire.pdf.common import *
from spire.pdf import *
import os

class PDFAConverter:
    """PDF/A 转换工具类"""
    
    def __init__(self):
        """初始化"""
        pass
    
    def convert_file_to_pdfa1b(self, input_file, output_file):
        """将单个文件转换为 PDF/A-1B 格式"""
        if not os.path.exists(input_file):
            print(f"文件不存在: {input_file}")
            return False
        
        try:
            converter = PdfStandardsConverter(input_file)
            converter.ToPdfA1B(output_file)
            print(f"✓ 转换成功: {os.path.basename(input_file)} -> PDF/A-1B")
            return True
        except Exception as e:
            print(f"✗ 转换失败: {os.path.basename(input_file)} - {str(e)}")
            return False
    
    def convert_file_to_pdfa2b(self, input_file, output_file):
        """将单个文件转换为 PDF/A-2B 格式"""
        if not os.path.exists(input_file):
            print(f"文件不存在: {input_file}")
            return False
        
        try:
            converter = PdfStandardsConverter(input_file)
            converter.ToPdfA2B(output_file)
            print(f"✓ 转换成功: {os.path.basename(input_file)} -> PDF/A-2B")
            return True
        except Exception as e:
            print(f"✗ 转换失败: {os.path.basename(input_file)} - {str(e)}")
            return False
    
    def convert_file_to_pdfa3b(self, input_file, output_file):
        """将单个文件转换为 PDF/A-3B 格式"""
        if not os.path.exists(input_file):
            print(f"文件不存在: {input_file}")
            return False
        
        try:
            converter = PdfStandardsConverter(input_file)
            converter.ToPdfA3B(output_file)
            print(f"✓ 转换成功: {os.path.basename(input_file)} -> PDF/A-3B")
            return True
        except Exception as e:
            print(f"✗ 转换失败: {os.path.basename(input_file)} - {str(e)}")
            return False
    
    def batch_convert_folder(self, input_folder, output_folder, 
                            pdfa_level="A1B"):
        """批量转换文件夹中的所有 PDF 文件"""
        if not os.path.exists(input_folder):
            print(f"输入文件夹不存在: {input_folder}")
            return
        
        # 创建输出文件夹
        if not os.path.exists(output_folder):
            os.makedirs(output_folder)
        
        # 查找所有 PDF 文件
        pdf_files = [f for f in os.listdir(input_folder) 
                    if f.lower().endswith('.pdf')]
        
        if not pdf_files:
            print(f"在 {input_folder} 中未找到 PDF 文件")
            return
        
        print(f"找到 {len(pdf_files)} 个 PDF 文件，开始转换为 PDF/A-{pdfa_level}...")
        
        success_count = 0
        fail_count = 0
        
        for pdf_file in pdf_files:
            input_path = os.path.join(input_folder, pdf_file)
            base_name = os.path.splitext(pdf_file)[0]
            output_path = os.path.join(output_folder, f"{base_name}_PDFA.pdf")
            
            # 根据选择的级别进行转换
            if pdfa_level.upper() == "A1B":
                if self.convert_file_to_pdfa1b(input_path, output_path):
                    success_count += 1
                else:
                    fail_count += 1
            elif pdfa_level.upper() == "A2B":
                if self.convert_file_to_pdfa2b(input_path, output_path):
                    success_count += 1
                else:
                    fail_count += 1
            elif pdfa_level.upper() == "A3B":
                if self.convert_file_to_pdfa3b(input_path, output_path):
                    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: {output_folder}")
    
    def validate_pdfa_compliance(self, pdf_file):
        """验证文件是否符合 PDF/A 标准（基础检查）"""
        if not os.path.exists(pdf_file):
            print(f"文件不存在: {pdf_file}")
            return False
        
        try:
            doc = PdfDocument()
            doc.LoadFromFile(pdf_file)
            
            # 检查文档属性
            info = doc.DocumentInformation
            
            # 基本检查：文件大小不为空
            file_size = os.path.getsize(pdf_file)
            
            doc.Close()
            
            print(f"文件: {os.path.basename(pdf_file)}")
            print(f"大小: {file_size} 字节")
            print(f"页数: {doc.Pages.Count if hasattr(doc, 'Pages') else 'N/A'}")
            
            return True
        except Exception as e:
            print(f"验证失败: {str(e)}")
            return False

def main():
    converter = PDFAConverter()
    
    # 示例 1: 转换单个文件为 PDF/A-1B
    converter.convert_file_to_pdfa1b(
        "./Documents/Report.pdf",
        "./Output/Report_PDFA1B.pdf"
    )
    
    # 示例 2: 转换单个文件为 PDF/A-2B（支持更多特性）
    converter.convert_file_to_pdfa2b(
        "./Documents/Presentation.pdf",
        "./Output/Presentation_PDFA2B.pdf"
    )
    
    # 示例 3: 批量转换文件夹中的所有 PDF
    converter.batch_convert_folder(
        "./Documents/Archive",
        "./Output/PDFA_Archive",
        pdfa_level="A1B"
    )
    
    # 示例 4: 验证转换后的文件
    converter.validate_pdfa_compliance("./Output/Report_PDFA1B.pdf")

if __name__ == "__main__":
    main()

def ArchiveLegalDocuments():
    """归档法律文档为 PDF/A 格式"""
    converter = PDFAConverter()
    
    # 将法院判决书转换为 PDF/A-1B（最严格的合规级别）
    converter.batch_convert_folder(
        "./Legal/Court_Rulings/2024",
        "./Archive/Legal_PDFA1B",
        pdfa_level="A1B"
    )

def ArchiveMedicalRecords():
    """归档医疗记录为 PDF/A 格式"""
    converter = PDFAConverter()
    
    # 将患者病历转换为 PDF/A-2B（支持更多现代特性）
    converter.batch_convert_folder(
        "./Medical/Patient_Records",
        "./Archive/Medical_PDFA2B",
        pdfa_level="A2B"
    )

def ArchiveFinancialReports():
    """归档财务报告为 PDF/A 格式"""
    converter = PDFAConverter()
    
    # 将年度财务报告转换为 PDF/A-1B
    converter.convert_file_to_pdfa1b(
        "./Finance/Annual_Report_2024.pdf",
        "./Archive/Annual_Report_2024_PDFA.pdf"
    )