本文实例讲述了Python实现简单拆分PDF文件的方法。分享给大家供大家参考。具体如下：
依赖pyPdf处理PDF文件
切分pdf文件
使用方法：
1）将要切分的文件放在input_dir目录下
2）在configure.txt文件中设置要切分的份数（如要切分4份，则设置part_num=4）
3）执行程序
4）切分后的文件保存在output_dir目录下
5）运行日志写在pp_log.txt中
P.S. 本程序可以批量切割多个pdf文件
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
from pyPdf import PdfFileWriter, PdfFileReader
import os
import time
import sys
def part_pdf(input_file, output_file, config_count, f_w, now, file_name):
file1 = file(input_file, 'rb')
pdf = PdfFileReader(file1)
pdf_pages_len = len(pdf.pages)
if config_count <= pdf_pages_len:
ye = pdf_pages_len / config_count
lst_ye = pdf_pages_len % config_count
part_count = 0
part_count_ye = 0
for fen in range(config_count):
part_count += 1
if part_count == config_count:
part_ye = ye + lst_ye
else:
part_ye = ye
write_pdf(pdf, part_count_ye, part_count_ye+part_ye, fen, output_file)
part_count_ye += ye
else:
f_w.writelines('time: '+now+' file name: '+file_name+' status: part_num > pdf pages [error]\n')
sys.exit(1)
def write_pdf(pdf, part_count_ye, part_count_ye_end, fen, output_file):
out = PdfFileWriter()
for pp in range(part_count_ye, part_count_ye_end):
out.addPage(pdf.getPage(pp))
ous = file(output_file+'_'+str(fen+1)+'.pdf', 'wb')
out.write(ous)
ous.close()
def pdf_main():
f = open('configure.txt', 'r')
f_w = open('pp_log.txt', 'a')
now = time.strftime('%Y-%m-%d %H:%M:%S')
for i in f:
i_ = i.strip()
aa = i_.split('=')[1]
if i_.find('part_num=') != -1 and aa.isdigit():
config_count = int(aa)
else:
f_w.writelines('time: '+now+' status: part_num in configure.txt is error [error]\n')
sys.exit(1)
files = os.listdir('input_dir/')
for each in files:
input_file = 'input_dir/'+each
file_name = input_file[input_file.index('/'):input_file.index('.')]
output_file = 'output_dir/'+file_name
part_pdf(input_file, output_file, config_count, f_w, now, file_name)
f_w.writelines('time: '+now+' file name: '+file_name+' status: success\n')
pdf_main()
|
希望本文所述对大家的Python程序设计有所帮助。