pdf文件处理

常用库

库名称	特点	备注
pypdf	简单纯净的pdf操作	pdm add pypdf
fitz（前名称：pymupdf ）		pip install pymupdf
COM接口调用 - comtypes	要求系统中安装了Adobe Acrobat DC

COM调用

获取 PDF 文件的页码

import comtypes.client

def list_pdf_page(folder: str):
    """
    @Description 打印指定目录下pdf文件的页码
    """
    # 创建 Adobe Acrobat 的 COM 对象
    av_doc = comtypes.client.CreateObject("AcroExch.AVDoc")
    app = comtypes.client.CreateObject("AcroExch.App")

    pdf_list = os.listdir(folder)
    for e in range(2, 25, 2):
        pdf_path = path.join(folder, f"BS·22·01-009-{e}.pdf")
        print("pdf_path: ", pdf_path)

        if av_doc.Open(pdf_path, ""):
            pd_doc = av_doc.GetPDDoc()
            page_count = pd_doc.GetNumPages()
            # print( page_count)
            print(pdf_path, page_count)

            av_doc.Close(False)
    app.Exit()

导出为图片

import comtypes.client
import os

def export_pdf_to_images(pdf_path: str, output_folder: str) -> None:
    """
    将 PDF 文件的每一页导出为 JPG 图片。

    :param pdf_path: PDF 文件的路径
    :param output_folder: 输出图片的文件夹路径
    """
    try:
        # 创建 Adobe Acrobat 的 COM 对象
        av_doc = comtypes.client.CreateObject("AcroExch.AVDoc")
        app = comtypes.client.CreateObject("AcroExch.App")

        # 打开 PDF 文件
        if av_doc.Open(pdf_path, ""):
            pd_doc = av_doc.GetPDDoc()
            page_count = pd_doc.GetNumPages()

            # 确保输出文件夹存在
            if not os.path.exists(output_folder):
                os.makedirs(output_folder)

            # 导出每一页为 JPG 图片
            for page_num in range(page_count):
                page = pd_doc.AcquirePage(page_num)
                rect = page.GetSize()
                output_path = os.path.join(output_folder, f"page_{page_num + 1}.jpg")
                page.DrawEx(rect, 0, 0, 0, output_path, "jpg", 300, 300)

            # 关闭文档
            av_doc.Close(False)
            app.Exit()

            print(f"Exported {page_count} pages to {output_folder}")
        else:
            print("Failed to open PDF file.")

    except Exception as e:
        print(f"Error: {e}")

# 使用示例
pdf_path = "example.pdf"
output_folder = "output_images"
export_pdf_to_images(pdf_path, output_folder)

合并pdf

from pypdf import PdfWriter
import pathlib

def merge_pdfs(pdf_list, output_pdf: str = None):
    merger = PdfWriter()

    for pdf in pdf_list:
        merger.append(pdf)

    if output_pdf is None:
        pdf_file = pathlib.Path(pdf_list[0])
        output_pdf = str(pdf_file.resolve()).replace(pdf_file.suffix, "_merge.pdf")

    merger.write(output_pdf)
    merger.close()


if __name__ == "__main__":
    pdf_list = [
        r"Z:\work\2024\其他\加章\工作实绩-林芯伊、刘珊霞、周舜轩整理(1)\封面人员页-P章\2022年博罗水文站旱警水位-1.pdf",
        r"Z:\work\2024\其他\加章\工作实绩-林芯伊、刘珊霞、周舜轩整理(1)\封面人员页-P章\2022年博罗水文站旱警水位-2.pdf",
    ]

    merge_pdfs(pdf_list, r"Z:\work\2024\其他\加章\工作实绩-林芯伊、刘珊霞、周舜轩整理(1)\output.pdf")

导出jpg

pdf2image + Poppler

使用pdf2image需要确保系统中已安装 Poppler：

下载地址：https://github.com/oschwartz10612/poppler-windows/releases/

from pdf2image import convert_from_path
import os

def pdf_to_jpg_with_pdf2image(pdf_path: str, output_folder: str, dpi: int = 300):
    """
    使用 pdf2image 将 PDF 转换为 JPG 格式。
    
    Args:
        pdf_path (str): PDF 文件路径。
        output_folder (str): 导出图片的保存文件夹。
        dpi (int): 输出图片的分辨率。
    
    Returns:
        None
    """
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    
    # 转换 PDF 每一页为图像
    images = convert_from_path(pdf_path, dpi=dpi)
    
    # 保存每一页为 JPG
    for i, image in enumerate(images):
        output_file = os.path.join(output_folder, f"page_{i + 1}.jpg")
        image.save(output_file, "JPEG")
        print(f"保存: {output_file}")

# 示例调用
pdf_to_jpg_with_pdf2image(
    pdf_path="example.pdf",
    output_folder="output_images_pdf2image",
    dpi=300
)

指定导出A4、A3尺寸的jpg

pip install pymupdf pillow

python -m pip isntall pymupdf pillow

pdm add pymupdf pillow

def export_pdf_to_paper_size(pdf_path, output_path, dpi=300, paper_size="A4"):
    # 定义A4和A3的尺寸（毫米）并转换为像素
    paper_sizes = {"A4": (210, 297), "A3": (297, 420)}
    width_mm, height_mm = paper_sizes.get(paper_size, ("A4"))

    # 毫米转英寸再乘以DPI
    target_width = int(width_mm / 25.4 * dpi)
    target_height = int(height_mm / 25.4 * dpi)

    # 打开PDF并获取页面
    doc = fitz.open(pdf_path)
    for page in doc:
        original_width = page.rect.width  # 原始宽度（点）
        original_height = page.rect.height  # 原始高度（点）

        # 计算适应目标尺寸的缩放比例
        scale_w = target_width / original_width
        scale_h = target_height / original_height
        scale = min(scale_w, scale_h)  # 保持宽高比

        # 生成缩放后的图像
        matrix = fitz.Matrix(scale, scale)
        pix = page.get_pixmap(matrix=matrix, dpi=dpi)
        # pix.save(output_path + f"page-{page.number}.jpg", "jpg", jpg_quality=70)

        img = Image.open(io.BytesIO(pix.tobytes()))

        # 创建目标尺寸画布并居中粘贴
        canvas = Image.new("RGB", (target_width, target_height), (255, 255, 255))
        x = (target_width - img.width) // 2
        y = (target_height - img.height) // 2
        canvas.paste(img, (x, y))

        # 保存结果
        canvas.info["dpi"] = (dpi, dpi)  # 写入DPI信息
        canvas.save(output_path + f"page-{page.number}.jpg", "JPEG", quality=95, dpi=(dpi, dpi))

    doc.close()

使用

if __name__ == "__main__":
    tar = r"D:\Work\大藤峡\归档\电子版\卷001\BS·22·01-001-1.pdf"

    pdf_to_jpg(tar)

修改尺寸比例（A4）

# -*- coding: utf-8 -*-
#
# @Author: CPS
# @email: 373704015@qq.com
# @Date:
# @Last Modified by: CPS
# @Last Modified time: 2025-04-10 23:25:27.768326
# @file_path "D:\CPS\MyProject\Projects_Personal\GG_wx_fapiao_download"
# @Filename "test.py"
# @Description: 修改pdf文件的尺寸为A4 置顶对齐，方便打印
#
import os, sys

sys.path.append("..")

from os import path
import fitz


def get_page_display_size(page):
    """获取考虑旋转后的页面显示尺寸"""
    rotation = page.rotation
    if rotation in (90, 270):
        return page.rect.height, page.rect.width
    return page.rect.width, page.rect.height


def is_a4_portrait(page, tolerance=5):
    """检查页面是否为A4纵向"""
    a4_width, a4_height = 595, 842  # A4尺寸（单位：点）
    width, height = get_page_display_size(page)
    return abs(width - a4_width) <= tolerance and abs(height - a4_height) <= tolerance


def convert_pdf_to_a4_portrait(input_path, output_path, vertical_align="top"):
    """
    将PDF转换为A4纵向格式，支持置顶对齐
    :param input_path: 输入PDF路径
    :param output_path: 输出PDF路径
    :param vertical_align: 垂直对齐方式（"top" 或 "center"）
    """
    src_doc = fitz.open(input_path)
    new_doc = fitz.open()  # 创建新文档

    a4_width, a4_height = 595, 842

    for page_num in range(len(src_doc)):
        page = src_doc[page_num]
        display_width, display_height = get_page_display_size(page)

        if is_a4_portrait(page):
            new_page = new_doc.new_page(width=a4_width, height=a4_height)
            new_page.show_pdf_page(new_page.rect, src_doc, page_num)
        else:
            new_page = new_doc.new_page(width=a4_width, height=a4_height)
            scale = min(a4_width / display_width, a4_height / display_height)

            scaled_width = display_width * scale
            scaled_height = display_height * scale

            # 水平居中计算
            x = (a4_width - scaled_width) / 2

            # 垂直对齐方式判断
            if vertical_align.lower() == "top":
                y = 0  # 置顶对齐
            else:  # 默认居中
                y = (a4_height - scaled_height) / 2

            dest_rect = fitz.Rect(x, y, x + scaled_width, y + scaled_height)
            new_page.show_pdf_page(dest_rect, src_doc, page_num)

    new_doc.save(output_path)
    new_doc.close()
    src_doc.close()


if __name__ == "__main__":
    # 使用示例
    input_pdf = path.abspath(
        r"D:\CPS\MyProject\Projects_Personal\GG_wx_fapiao_download\data\粉盒，硒鼓.pdf"
    )
    convert_pdf_to_a4_portrait(input_pdf, "output.pdf")