如何使用poppler提取pdf索引/目錄？

Question

我看到像okular和evince這樣的pdf觀衆能夠很好地顯示PDF文檔（書）的索引，並鏈接到每個段落。 他們怎麼能這樣做？他們使用poppler庫，我怎麼能用poppler提取那個索引，或者一般來說？

Answer 1

它只是停留在第一層（去更深入地需要遞歸）

toc=document->toc(); 

QDomElement docElem = toc->documentElement(); 

QDomNode n = docElem.firstChild(); 
while(!n.isNull()) { 
    QDomElement e = n.toElement(); // try to convert the node to an element. 
    if(!e.isNull()) { 
     qDebug("elem %s\n",qPrintable(e.tagName())); // the node really is an element. 

    } 
    n = n.nextSibling(); 
} 

Answer 2

這裏是一個演示如何使用poppler的Python中做到這一點：

import poppler 

def walk_index(iterp, doc): 
    while iterp.next(): 
     link=iterp.get_action() 
     s = doc.find_dest(link.dest.named_dest) 
     print link.title,' ', doc.get_page(s.page_num).get_label() 
     child = iterp.get_child() 
     if child: 
     walk_index(child, doc) 

def main(): 
    uri = ("file:///"+path_to_pdf) 
    doc = poppler.document_new_from_file(uri, None) 

    iterp = poppler.IndexIter(doc) 
    link = iterp.get_action() 
    s = doc.find_dest(link.dest.named_dest) 
    print link.title,' ', doc.get_page(s.page_num).get_label() 
    walk_index(iterp, doc) 
    return 0 


if __name__ == '__main__': 
    main() 

蟒蛇poppler庫已過時，這裏是怎麼用Gobject做的：

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# walk to table of contents and print titles and pages 

import sys 
from gi.repository import Poppler 

def walk_index(iterp, doc): 
    while iterp.next(): 
     link=iterp.get_action() 
     dest=doc.find_dest(link.goto_dest.dest.named_dest) 
     s = doc.get_page(dest.page_num-1) 
     print link.goto_dest.title, dest.page_num, s.get_label() 
     child = iterp.get_child() 
     if child: 
      walk_index(child, doc) 

def main(): 
    uri = ("file:///"+sys.argv[1]) 
    doc = Poppler.Document.new_from_file(uri, None) 
    iterp = Poppler.IndexIter.new(doc) 
    link = iterp.get_action() 
    dest=doc.find_dest(link.goto_dest.dest.named_dest) 
    s = doc.get_page(dest.page_num-1) 
    print link.goto_dest.title, dest.page_num, s.get_label() 
    walk_index(iterp, doc) 
    return 0 


if __name__ == '__main__': 
    main()