使用python对PDF文件进行等页数分割

AllStarGIS 2021-09-04 原文

用到了pyPDF库，很简单的脚步，废话不多说了。直接上代码

 1 # coding:utf8
 2 import os
 3 from pyPdf import PdfFileWriter, PdfFileReader
 4 def split(pdf_file, delta, output_dir):
 5     if not os.path.exists(output_dir):
 6         os.makedirs(output_dir)
 7     if not os.path.exists(pdf_file):
 8         return
 9     input_stream = file(pdf_file, \'rb\')
10     pdf_input = PdfFileReader(input_stream)
11     page_count = pdf_input.getNumPages()
12     sum_page_count = int(page_count / (delta * 1.0))
13     remind_page = page_count % delta
14     for i in range(0, sum_page_count + 1):
15         start = i * delta
16         end = (i + 1) * delta 
17         pdf_out = PdfFileWriter()
18         file_path = os.path.join(output_dir, os.path.split(pdf_file)[1]) #
19         if i < sum_page_count:
20             file_path = os.path.join(output_dir, str(start + 1) + \'-\' + str(end) + ".pdf")
21             for j in range(start, end):
22                 page = pdf_input.getPage(j)
23                 pdf_out.addPage(page)
24         else:
25             file_path = os.path.join(output_dir, str(delta * sum_page_count + 1) + \'-\' + str(page_count) + ".pdf")
26             for j in range(delta * (sum_page_count), page_count):
27                 page = pdf_input.getPage(j)
28                 pdf_out.addPage(page)
29         out_stream = file(file_path, \'wb\')
30         pdf_out.write(out_stream)
31         out_stream.close()
32     input_stream.close()
33 
34 if __name__ == \'__main__\':
35     import sys
36     #split(u\'C:/Users/sky/Desktop/17.pdf\', 50, u\'C:/Users/sky/Desktop/RES\')
37     try:
38         pdf_path = sys.argv[1]
39         page_count = int(sys.argv[2])
40         out_dir = sys.argv[3]
41         split(pdf_path, page_count, out_dir)
42     except:
43         pass
44         
45