1.拆分PDF
import os
from PyPDF2 import PdfFileWriter, PdfFileReader
def split_pdf(filename, filepath, save_dirpath, step=5):
"""
拆分PDF为多个小的PDF文件,
@param filename:文件名
@param filepath:文件路径
@param save_dirpath:保存小的PDF的文件路径
@param step: 每step间隔的页面生成一个文件,例如step=5,表示0-4页、5-9页...为一个文件
@return:
"""
if not os.path.exists(save_dirpath):
os.mkdir(save_dirpath)
pdf_reader = PdfFileReader(filepath)
pages = pdf_reader.getNumPages()
for page in range(0, pages, step):
pdf_writer = PdfFileWriter()
for index in range(page, page+step):
if index < pages:
pdf_writer.addPage(pdf_reader.getPage(index))
save_path = os.path.join(save_dirpath, filename+str(int(page/step)+1)+'.pdf')
print(save_path)
with open(save_path, "wb") as out:
pdf_writer.write(out)
print("文件已成功拆分,保存路径为:"+save_dirpath)
filename = '易方达中小盘混合型证券投资基金2020年中期报告.pdf'
filepath = os.path.join(os.getcwd(), filename)
save_dirpath = os.path.join(os.getcwd(), '易方达中小盘混合型证券投资基金2020年中期报告【拆分】')
split_pdf(filename, filepath, save_dirpath, step=5)
![在这里插入图片描述](https://i-blog.csdnimg.cn/blog_migrate/ce6021c71d7b29074733f36f525907a4.png#pic_center)
2.批量合并
import os
from PyPDF2 import PdfFileReader, PdfFileWriter
def concat_pdf(filename, read_dirpath, save_filepath):
"""
合并多个PDF文件
@param filename:文件名
@param read_dirpath:要合并的PDF目录
@param save_filepath:合并后的PDF文件路径
@return:
"""
pdf_writer = PdfFileWriter()
list_filename = os.listdir(read_dirpath)
list_filename.sort(key=lambda x: int(x[:-4].replace(filename,