Python实现合并与拆分多个PDF文档中的指定页

from pypdf2 import pdfreader, pdfwriter
# pip install pypdf2 -i https://pypi.tuna.tsinghua.edu.cn/simple

# 定义要处理的pdf文件及其完整路径
pdf_files = {
    '数模.pdf': r'd:\users\documents\wechat files\filestorage\file\2025-03\数学一模每日一练5(3.18).pdf',  # 替换为a.pdf的实际路径
    '数招.pdf': r'd:\users\documents\wechat files\filestorage\file\2025-03\自招考试—数学每日一练5(3.18).pdf',  # 替换为b.pdf的实际路径
    '物模.pdf': r'd:\users\documents\wechat files\filestorage\file\2025-03\物理一模每日一练5(3.18).pdf',  # 替换为c.pdf的实际路径
    '物招.pdf': r'd:\users\documents\wechat files\filestorage\file\2025-03\自招考试—物理每日一练5(3.18).pdf',  # 替换为c.pdf的实际路径
    '化模.pdf': r'd:\users\documents\wechat files\filestorage\file\2025-03\化学一模每日一练5(3.18).pdf',  # 替换为c.pdf的实际路径
    '化招.pdf': r'd:\users\documents\wechat files\filestorage\file\2025-03\自招版—化学每日一练5(3.18）.pdf'    # 替换为c.pdf的实际路径
}

# 定义要提取的页码（注意：页码从0开始）
pages_to_extract = {
    '数模.pdf': [0],  # 提取a.pdf的第1页和第3页
    '数招.pdf': [0],  # 提取b.pdf的第2页
    '物模.pdf': [0],  # 提取c.pdf的第1页和第2页
    '物招.pdf': [0],  # 提取a.pdf的第1页和第3页
    '化模.pdf': [0],  # 提取b.pdf的第2页
    '化招.pdf': [0]  # 提取c.pdf的第1页和第2页
}

# 创建一个pdfwriter对象来保存合并后的pdf
output_pdf = pdfwriter()

# 遍历每个pdf文件
for pdf_name, pdf_path in pdf_files.items():
    # 读取pdf文件
    reader = pdfreader(pdf_path)

    # 获取要提取的页码
    pages = pages_to_extract.get(pdf_name, [])

    # 遍历要提取的页码
    for page_num in pages:
        # 获取指定页
        page = reader.pages[page_num]
        # 将页添加到输出pdf中
        output_pdf.add_page(page)

# 将合并后的pdf写入到输出文件
output_path = r'd:\users\desktop\0319.pdf'  # 替换为输出文件的实际路径
with open(output_path, 'wb') as output_file:
    output_pdf.write(output_file)

print(f"pdf合并完成，已保存为 {output_path}")

from pypdf2 import pdfreader, pdfwriter
import os

# 定义要处理的pdf文件及其完整路径
pdf_files = {
    'a.pdf': '/path/to/a.pdf',  # 替换为a.pdf的实际路径
    'b.pdf': '/path/to/b.pdf',  # 替换为b.pdf的实际路径
    'c.pdf': '/path/to/c.pdf'   # 替换为c.pdf的实际路径
}

# 定义输出目录
output_dir = '/path/to/output'  # 替换为输出目录的实际路径

# 如果输出目录不存在，则创建它
if not os.path.exists(output_dir):
    os.makedirs(output_dir)

# 遍历每个pdf文件
for pdf_name, pdf_path in pdf_files.items():
    # 读取pdf文件
    reader = pdfreader(pdf_path)
    
    # 遍历pdf的每一页
    for page_num, page in enumerate(reader.pages):
        # 创建一个pdfwriter对象
        writer = pdfwriter()
        # 将当前页添加到pdfwriter中
        writer.add_page(page)
        
        # 生成输出文件名
        output_filename = os.path.join(output_dir, f'{pdf_name}_page_{page_num + 1}.pdf')
        
        # 将当前页保存为一个单独的pdf文件
        with open(output_filename, 'wb') as output_file:
            writer.write(output_file)
        
        print(f"已保存: {output_filename}")

print("所有页面已拆分为单独的pdf文件！")

import os
from pypdf2 import pdfreader, pdfwriter

class pdfmerge:
    def __init__(self, filelist, dstfile):
        self.filelist = filelist
        self.dstfile = dstfile
       
    def readpdf(self, pdffile, pagerange):
        pagelist = []
        pdf_reader = pdfreader(pdffile)
        for i in range(len(pdf_reader.pages)):
            if i in pagerange:
                pagelist.append(pdf_reader.pages[i])
        return pagelist
    
    def writepdf(self, pagelist): 
        pdf_writer = pdfwriter()
        for page in pagelist:
            pdf_writer.add_page(page)
        with open(self.dstfile, 'wb') as out:
            pdf_writer.write(out)
    
    def getrangelist(self, rangestr):
        rangelist = []
        if rangestr.find(':') >= 0:
            r = rangestr.split(':')
            if len(r) != 2:
                print("rangestr[%s] split [:] failed!"%(rangestr))
                return rangelist
            mi = int(r[0])
            ma = int(r[1])
            for i in range(mi, ma):
                rangelist.append(i)
        elif rangestr.find(',') >= 0:
            r = rangestr.split(',')
            mi = int(r[0])
            ma = int(r[1])
            for i in r:
                rangelist.append(int(i))
        elif rangestr.isnumeric():
            rangelist.append(int(rangestr))
        else:
            print("rangestr split failed! not find [:] and [,]")
        return rangelist
 
    def mergepdf(self):
        pagelist = []
        for pdf in self.filelist:
            file = pdf["file"]
            filerange = self.getrangelist(pdf["range"])
            print("file[{}] rangestr[{}] rangelist{}".format(file, pdf["range"], filerange))
            pagelist.extend(self.readpdf(file, filerange))
        self.writepdf(pagelist)

def main():
    filelist = [{"file":"source/1_任务书.pdf", "range":"0:10"},{"file":"source/20230409074902162.pdf", "range":"0"}]
   # filelist = [{"file":"source/1_任务书.pdf", "range":"0,1,5,6,7"},{"file":"source/20230409074902162.pdf", "range":"0"}]
    fileprocess = pdfmerge(filelist, "source/任务书.pdf")
    fileprocess.mergepdf()

if __name__ == "__main__":
    main()

import os
from pypdf2 import pdffilewriter, pdffilereader


def get_file(path, all_files):
    filenames = os.listdir(path)
    for file_name in filenames:
        cur_path = os.path.join(path, file_name)
        if os.path.isdir(cur_path):
            get_file(cur_path, all_files)
        else:
            if file_name.endswith('.pdf'):
                all_files.append(cur_path)
    return all_files


def extract_one_pdf(pdf_path, save_dir, start_page, end_page):
    pdf_name = pdf_path.split("\\")[-1]
    print(f"processing file -- {pdf_path}")
    if not os.path.exists(save_dir):
        print(save_dir)
        os.makedirs(save_dir)
    pdf_file = pdffilereader(pdf_path, strict=false)
    pdf_pages = pdf_file.getnumpages()
    if not -1 < start_page < end_page < pdf_pages:
        raise valueerror("pages error")

    pdf_output = pdffilewriter()
    for i in range(start_page, end_page):
        page = pdf_file.getpage(i)
        pdf_output.addpage(page)
    with open(save_dir + pdf_name, 'wb') as out:
        pdf_output.write(out)


def extract_many_pdf(pdf_dir_path, save_path, start_page, end_page):

    source_files = get_file(pdf_dir_path, [])
    for i, file in enumerate(source_files):
        file_name = file.split("\\")[-1]
        save_file = file.replace(pdf_dir_path, save_path)
        save_dir = save_file.replace(file_name, '')
        extract_one_pdf(file, save_dir, start_page, end_page)


if __name__ == '__main__':
    path = "c:\\users\\lenovo\\desktop\\test\\"
    out_path = "c:\\users\\lenovo\\desktop\\pdf_out\\"
    extract_many_pdf(path, out_path, 0, 1)