从 4up 到 1up 的反向拼版

Question

我有一份标准 pdf 格式的 4-up 拼版文件。我需要将它们反向强加为 1-up pdf。我查看了解决方案here。这可以完美地将pdf分成两半。但我是 python 脚本的新手，不太清楚如何根据我的需要修改它。 我的 PDF 组织为：

[1|3]         [1]
[2|4]         [2]
-----         [3]
[5|6]    ⇒    [4]
[7|8]         [5]
----          [6]...

如果可能的话，最好让它只处理一系列页码，但这只是锦上添花。 我找到了一个名为 [briss here][1] 的带有 gui 的 java 应用程序来实现我所需要的，但是学习一点 Python 来自动完成这项任务会很棒。

所以我已经能够输出我需要的内容，但我不确定如何设置脚本以接受页码范围

import copy
import math
from PyPDF2 import PdfFileReader, PdfFileWriter
import argparse

def split_pages2(src, dst):
    src_f = file(src, 'r+b')
    dst_f = file(dst, 'w+b')

    input = PdfFileReader(src_f)
    output = PdfFileWriter()

    for i in range(input.getNumPages()):
        # make two copies of the input page
        pp = input.getPage(i)
        p = copy.copy(pp)
        q = copy.copy(pp)
        r = copy.copy(pp)
        s = copy.copy(pp)

        # the new media boxes are the previous crop boxes
        p.mediaBox = copy.copy(p.cropBox)
        q.mediaBox = copy.copy(p.cropBox)

        #x1, x2 = p.mediaBox.lowerLeft
    x1, x2 = 72, 71.5
        #x3, x4 = p.mediaBox.upperRight
    x3, x4 = 540.7, 727 

        x1, x2 = math.floor(x1), math.floor(x2)
        x3, x4 = math.floor(x3), math.floor(x4)
        #x5, x6 = x1+math.floor((x3-x1)/2), x2+math.floor((x4-x2)/2)
        x5, x6 = 306, 396
        # vertical
        p.mediaBox.upperRight = (x5, x6)
        p.mediaBox.lowerLeft = (x1, x2)

        q.mediaBox.upperRight = (x5, x4)
        q.mediaBox.lowerLeft = (x1, x6)

        r.mediaBox.upperRight = (x3, x6)
        r.mediaBox.lowerLeft = (x5, x2)

        s.mediaBox.upperRight = (x3, x4)
        s.mediaBox.lowerLeft = (x5, x6)


        p.artBox = p.mediaBox
        p.bleedBox = p.mediaBox
        p.cropBox = p.mediaBox

        q.artBox = q.mediaBox
        q.bleedBox = q.mediaBox
        q.cropBox = q.mediaBox
        
        r.artBox = r.mediaBox
        r.bleedBox = r.mediaBox
        r.cropBox = r.mediaBox
        
        s.artBox = s.mediaBox
        s.bleedBox = s.mediaBox
        s.cropBox = s.mediaBox

        output.addPage(q)
        output.addPage(p)
        output.addPage(s)
        output.addPage(r)


    output.write(dst_f)
    src_f.close()
    dst_f.close()

if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description=("Split up pdf from 4-up "
                     "to single page"))
    parser.add_argument("src", help="Source file")
    parser.add_argument("dst", help="Destination file")
    args = parser.parse_args()
    split_pages2(args.src, args.dst)

Answer 1

更新： 精炼脚本自动处理脚本所在文件夹中的所有pdf文件并自动检测4up页面。所以不需要输入文件名或其他参数。

再次，我对 python 完全陌生，所以我不知道是否需要所有的行。如果我的代码没有意义，需要清理，请随时发表评论。
pdf4-to-1.py

# -*- coding: utf-8 -*-
#   x-y coordinate reference for 4up
#   x1,y3-------x2,y3-------x3,y3
#    |           |           |              
#    |      1    |      3    |              1
#    |           |           |              2
#   x1,y2-------x2,y2-------x3,y2   =>      3
#    |           |           |              4
#    |      2    |      4    |
#    |           |           |
#   x1,y1-------x2,y1-------x3,y1


import copy
import math
from PyPDF2 import PdfFileReader, PdfFileWriter
import argparse
from pdf2image import convert_from_path
import cv2
from imutils import perspective
from imutils import contours
import numpy as np
import imutils
from operator import itemgetter
import os
#src = "ST.pdf"
curdir = os.path.dirname(os.path.realpath(__file__))
os.chdir(curdir)
files = os.listdir(curdir)
if os.environ.get('OS','') == 'Windows_NT':
    dstdir = os.path.join(curdir, '1up\\')
else:
    dstdir = os.path.join(curdir, '1up/')
if not os.path.exists(dstdir):
   os.makedirs(dstdir)
pdffiles = [f for f in files if f.endswith('.pdf')]
for p in pdffiles: 
    pages=convert_from_path(p)  
    ind = []
    for i in range(len(pages)):
     page = pages[i]
     gray = np.array(page)
     gray = cv2.cvtColor(gray, cv2.COLOR_BGR2GRAY)
     #gray = cv2.GaussianBlur(gray, (1, 1), 0)
     (thresh, bw) = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
     edges = cv2.Canny(bw,0,255)
     #edged = cv2.erode(edges, None, iterations=5)
     minLineLength=1100
     lines = cv2.HoughLinesP(image=edges,rho=5,theta=np.pi/90, threshold=1000,lines=np.array([]), minLineLength=minLineLength,maxLineGap=3)
     linessub = lines[((lines[:,0,0]>750) & (lines[:,0,0]<950))|((lines[:,0,1]>1000) & (lines[:,0,1]<1200))]
     if len(linessub) > 1: ind.append(i)
    startpg = min(ind)
    endpg = max(ind)
    page = pages[startpg]
    image = np.array(page)
    height = int(math.floor(image.shape[0])/2)
    width = int(math.floor(image.shape[1])/2)
    # convert to gray
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray, (7, 7), 0)
    # perform edge detection, then perform a dilation + erosion to
    # close gaps in between object edges
    edged = cv2.Canny(gray,0,255)
    edged = cv2.dilate(edged, None, iterations=1)
    edged = cv2.erode(edged, None, iterations=1)
    
    # find contours in the edge map
    cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
        cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] #if imutils.is_cv2() else cnts[1]
    
    # loop over the contours individually
    c = max(cnts, key = cv2.contourArea)
    
    # compute the rotated bounding box of the contour
    box = cv2.minAreaRect(c)
    box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
    box = np.array(box, dtype="int")
    
    # order the points in the contour such that they appear
    # in top-left, top-right, bottom-right, and bottom-left
    # order, then draw the outline of the rotated bounding
    # box
    box = perspective.order_points(box)
    
    x1 = round(((min(box, key=itemgetter(0))[0])/2.777777778),1)
    y3 = round(792-((min(box, key=itemgetter(1))[1])/2.77777778),1)
    x3 = round(((max(box, key=itemgetter(0))[0])/2.777777778),1)
    y1 = round(792-((max(box, key=itemgetter(1))[1])/2.77777778),1)
    
    src_f = open(p, 'r+b')
    dst_f = open(dstdir+p, 'w+b')
    input = PdfFileReader(src_f)
    output = PdfFileWriter()
    if startpg >= 1: 
        for x in range(startpg):
            output.addPage(input.getPage(x))  
            
            #print(x)
    
    for i in range(startpg,endpg+1): #input.getNumPages()):
        # make two copies of the input page
        pp = input.getPage(i)
        p = copy.copy(pp)
        q = copy.copy(pp)
        r = copy.copy(pp)
        s = copy.copy(pp)
    
        # the new media boxes are the previous crop boxes
        p.mediaBox = copy.copy(p.cropBox)
        q.mediaBox = copy.copy(p.cropBox)
    
        # x1, y1 = math.floor(x1), math.floor(y1)
        # x3, y3 = math.floor(x3), math.floor(y3)
        x2, y2 = round(x1+math.floor((x3-x1)/2),1), round(y1+math.floor((y3-y1)/2),1)
        #x2, y2 = 306, 396
        # vertical
        p.mediaBox.upperRight = (x2, y3)
        p.mediaBox.lowerLeft = (x1, y2)
    
        q.mediaBox.upperRight = (x2, y2)
        q.mediaBox.lowerLeft = (x1, y1)
    
        r.mediaBox.upperRight = (x3, y3)
        r.mediaBox.lowerLeft = (x2, y2)
    
        s.mediaBox.upperRight = (x3, y2)
        s.mediaBox.lowerLeft = (x2, y1)
    
    
        p.artBox = p.mediaBox
        p.bleedBox = p.mediaBox
        p.cropBox = p.mediaBox
    
        q.artBox = q.mediaBox
        q.bleedBox = q.mediaBox
        q.cropBox = q.mediaBox
        
        r.artBox = r.mediaBox
        r.bleedBox = r.mediaBox
        r.cropBox = r.mediaBox
        
        s.artBox = s.mediaBox
        s.bleedBox = s.mediaBox
        s.cropBox = s.mediaBox
    
        output.addPage(p)
        output.addPage(q)
        output.addPage(r)
        output.addPage(s)
    
    if len(pages) >= endpg: 
        for a in range(endpg+1,len(pages)):
            output.addPage(input.getPage(a))
            
            #print(a)
    
    output.write(dst_f)
    src_f.close()
    dst_f.close()
        #print(x1,y3,x3,y1, x2,y2)