大数据

python pdf合并

from PyPDF2 import PdfReader, PdfWriter
from common.tools.file import FileTools


def merge_pdf_files(pdf_folder, output_filename):
    """
    :param pdf_folder: 存储pdf的文件夹路径
    :param output_filename: 合并后的pdf目标路径 /xxx/xxx.pdf
    :return:
    """
    pdf_writer = PdfWriter()
    pdf_path_list = FileTools.scan_dir(pdf_folder, ".pdf")

    for file_path in pdf_path_list:
        pdf_reader = PdfReader(file_path)
        for page in pdf_reader.pages:
            pdf_writer.add_page(page)

    with open(output_filename, "wb") as out_file:
        pdf_writer.write(out_file)