根据大纲拆分PDF

Question

我想用pyPdf这个工具来根据PDF文件的目录结构，把一个PDF文件拆分开来。目录里的每个目标都指向PDF中的不同页面。

举个例子，目录结构如下：

main       --> points to page 1
  sect1    --> points to page 1
  sect2    --> points to page 15
  sect3    --> points to page 22

在pyPdf里，逐页查看文档或查看文档目录中的每个目标是很简单的；不过，我就是搞不清楚怎么找到每个目标所指向的页面号码。

有没有人知道怎么找到目录中每个目标对应的页面号码呢？

Answer 1

这是对@darrell类的小更新，目的是让它能够解析UTF-8格式的目录。我把这个更新放在这里作为回答，因为在评论里说可能不太好理解。

问题出在pyPdf.pdf.Destination.title这个地方，它可能会有两种返回形式：

• pyPdf.generic.TextStringObject
• pyPdf.generic.ByteStringObject

所以从_setup_outline_page_ids()这个函数返回的title对象也会有这两种类型。如果目录标题里包含了ASCII以外的字符，就会出现UnicodeDecodeError的错误。

为了解决这个问题，我添加了以下代码：

if isinstance(title, pyPdf.generic.TextStringObject):
    title = title.encode('utf-8')

这是整个类的代码：

class PdfOutline(pyPdf.PdfFileReader):

    def getDestinationPageNumbers(self):

        def _setup_outline_page_ids(outline, _result=None):
            if _result is None:
                _result = {}
            for obj in outline:
                if isinstance(obj, pyPdf.pdf.Destination):
                    _result[(id(obj), obj.title)] = obj.page.idnum
                elif isinstance(obj, list):
                    _setup_outline_page_ids(obj, _result)
            return _result

        def _setup_page_id_to_num(pages=None, _result=None, _num_pages=None):
            if _result is None:
                _result = {}
            if pages is None:
                _num_pages = []
                pages = self.trailer["/Root"].getObject()["/Pages"].getObject()
            t = pages["/Type"]
            if t == "/Pages":
                for page in pages["/Kids"]:
                    _result[page.idnum] = len(_num_pages)
                    _setup_page_id_to_num(page.getObject(), _result, _num_pages)
            elif t == "/Page":
                _num_pages.append(1)
            return _result

        outline_page_ids = _setup_outline_page_ids(self.getOutlines())
        page_id_to_page_numbers = _setup_page_id_to_num()

        result = {}
        for (_, title), page_idnum in outline_page_ids.iteritems():
            if isinstance(title, pyPdf.generic.TextStringObject):
                title = title.encode('utf-8')
            result[title] = page_id_to_page_numbers.get(page_idnum, '???')
        return result

Answer 2

这正是我想要的。Darrell对PdfFileReader的改进应该加入到PyPDF2里。

我写了一个小程序，利用PyPDF2和sejda-console来根据书签拆分PDF。在我的情况下，有几个一级章节我想要保持在一起。这个脚本让我可以做到这一点，并给生成的文件起个有意义的名字。

import operator
import os
import subprocess
import sys
import time

import PyPDF2 as pyPdf

# need to have sejda-console installed
# change this to point to your installation
sejda = 'C:\\sejda-console-1.0.0.M2\\bin\\sejda-console.bat'

class Darrell(pyPdf.PdfFileReader):
    ...

if __name__ == '__main__':
    t0= time.time()

    # get the name of the file to split as a command line arg
    pdfname = sys.argv[1]

    # open up the pdf
    pdf = Darrell(open(pdfname, 'rb'))

    # build list of (pagenumbers, newFileNames)
    splitlist = [(1,'FrontMatter')] # Customize name of first section

    template = '%-5s  %s'
    print template % ('Page', 'Title')
    print '-'*72
    for t,p in sorted(pdf.getDestinationPageNumbers().iteritems(),
                      key=operator.itemgetter(1)):

        # Customize this to get it to split where you want
        if t.startswith('Chapter') or \
           t.startswith('Preface') or \
           t.startswith('References'):

            print template % (p+1, t)

            # this customizes how files are renamed
            new = t.replace('Chapter ', 'Chapter')\
                   .replace(':  ', '-')\
                   .replace(': ', '-')\
                   .replace(' ', '_')
            splitlist.append((p+1, new))

    # call sejda tools and split document
    call = sejda
    call += ' splitbypages'
    call += ' -f "%s"'%pdfname
    call += ' -o ./'
    call += ' -n '
    call += ' '.join([str(p) for p,t in splitlist[1:]])
    print '\n', call
    subprocess.call(call)
    print '\nsejda-console has completed.\n\n'

    # rename the split files
    for p,t in splitlist:
        old ='./%i_'%p + pdfname
        new = './' + t + '.pdf'
        print 'renaming "%s"\n      to "%s"...'%(old, new),

        try:
            os.remove(new)
        except OSError:
            pass

        try:
            os.rename(old, new)
            print' succeeded.\n'
        except:
            print' failed.\n'

    print '\ndone. Spliting took %.2f seconds'%(time.time() - t0)

Answer 3

我搞明白了：

class Darrell(pyPdf.PdfFileReader):

    def getDestinationPageNumbers(self):
        def _setup_outline_page_ids(outline, _result=None):
            if _result is None:
                _result = {}
            for obj in outline:
                if isinstance(obj, pyPdf.pdf.Destination):
                    _result[(id(obj), obj.title)] = obj.page.idnum
                elif isinstance(obj, list):
                    _setup_outline_page_ids(obj, _result)
            return _result

        def _setup_page_id_to_num(pages=None, _result=None, _num_pages=None):
            if _result is None:
                _result = {}
            if pages is None:
                _num_pages = []
                pages = self.trailer["/Root"].getObject()["/Pages"].getObject()
            t = pages["/Type"]
            if t == "/Pages":
                for page in pages["/Kids"]:
                    _result[page.idnum] = len(_num_pages)
                    _setup_page_id_to_num(page.getObject(), _result, _num_pages)
            elif t == "/Page":
                _num_pages.append(1)
            return _result

        outline_page_ids = _setup_outline_page_ids(self.getOutlines())
        page_id_to_page_numbers = _setup_page_id_to_num()

        result = {}
        for (_, title), page_idnum in outline_page_ids.iteritems():
            result[title] = page_id_to_page_numbers.get(page_idnum, '???')
        return result

pdf = Darrell(open(PATH-TO-PDF, 'rb'))
template = '%-5s  %s'
print template % ('page', 'title')
for p,t in sorted([(v,k) for k,v in pdf.getDestinationPageNumbers().iteritems()]):
    print template % (p+1,t)