我正在尝试使用pyPDF编写几个

python脚本将PDF页面分成六个单独的页面,正确排序(通常是正面和背面打印,因此每隔一页需要对其子页面进行不同的排序),并删除生成的空白页面输出文档的结尾.

我编写了以下脚本来剪切PDF页面并重新排序.将每个页面分成两列,每列分成三页.我对python不是很有经验,所以请原谅我做得不对的任何事情.

#!/usr/bin/env python

import copy, sys

from pyPdf import PdfFileWriter, PdfFileReader

input = PdfFileReader(sys.stdin)

output = PdfFileWriter()

for i in range(0,input.getNumPages(),2):

p = input.getPage(i)

q = copy.copy(p)

r = copy.copy(p)

s = copy.copy(p)

t = copy.copy(p)

u = copy.copy(p)

(x, y) = p.mediaBox.lowerLeft

(w, h) = p.mediaBox.upperRight

p.mediaBox.lowerLeft = (x, 2 * h / 3)

p.mediaBox.upperRight = (w / 2, h)

q.mediaBox.lowerLeft = (w / 2, 2 * h / 3)

q.mediaBox.upperRight = (w, h)

r.mediaBox.lowerLeft = (x, h / 3)

r.mediaBox.upperRight = (w / 2, 2 * h / 3)

s.mediaBox.lowerLeft = (w / 2, h / 3)

s.mediaBox.upperRight = (w, 2 * h / 3)

t.mediaBox.lowerLeft = (x, y)

t.mediaBox.upperRight = (w / 2, h / 3)

u.mediaBox.lowerLeft = (w / 2, y)

u.mediaBox.upperRight = (w, h / 3)

a = input.getPage(i+1)

b = copy.copy(a)

c = copy.copy(a)

d = copy.copy(a)

e = copy.copy(a)

f = copy.copy(a)

(x, y) = a.mediaBox.lowerLeft

(w, h) = a.mediaBox.upperRight

a.mediaBox.lowerLeft = (x, 2 * h / 3)

a.mediaBox.upperRight = (w / 2, h)

b.mediaBox.lowerLeft = (w / 2, 2 * h / 3)

b.mediaBox.upperRight = (w, h)

c.mediaBox.lowerLeft = (x, h / 3)

c.mediaBox.upperRight = (w / 2, 2 * h / 3)

d.mediaBox.lowerLeft = (w / 2, h / 3)

d.mediaBox.upperRight = (w, 2 * h / 3)

e.mediaBox.lowerLeft = (x, y)

e.mediaBox.upperRight = (w / 2, h / 3)

f.mediaBox.lowerLeft = (w / 2, y)

f.mediaBox.upperRight = (w, h / 3)

output.addPage(p)

output.addPage(b)

output.addPage(q)

output.addPage(a)

output.addPage(r)

output.addPage(d)

output.addPage(s)

output.addPage(c)

output.addPage(t)

output.addPage(f)

output.addPage(u)

output.addPage(e)

output.write(sys.stdout)

然后我使用以下脚本删除空白页.

#!/usr/bin/env python

import copy, sys

from pyPdf import PdfFileWriter, PdfFileReader

input = PdfFileReader(sys.stdin)

output = PdfFileWriter()

for i in range(0,input.getNumPages()):

p = input.getPage(i)

text = p.extractText()

if (len(text) > 10):

output.addPage(p)

output.write(sys.stdout)

问题似乎是,当页面被明显裁剪下来时,文本绘制命令仍然存在.这些页面都不会被扫描,因此如果它们是空白的,则它们实际上是空白的.有没有人对我可以做的不同的事情有任何想法,或者可能采取完全不同的方法来删除空白页？我真的很感激任何帮助.