根据大纲分割pdf

Question

我想使用pyPdf基于轮廓分割pdf文件,其中轮廓中的每个目的地引用pdf中的不同页面.

示例大纲:

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

pyPdf中很容易迭代文档的每个页面或文档大纲中的每个目标; 但是,我无法弄清楚如何获取目的地所指向的页码.

有人知道如何找到大纲中每个目的地的参考页码吗？

Answer 1

我想到了:

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)