Created
March 6, 2014 14:35
-
-
Save gabalese/9391122 to your computer and use it in GitHub Desktop.
Python script to sort a NCX with no gaps in playOrder.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#! /usr/bin/env python | |
from lxml import etree as ET | |
import zipfile as ZIP | |
import sys | |
import os | |
namespaces = { "opf":"http://www.idpf.org/2007/opf", | |
"dc":"http://purl.org/dc/elements/1.1/", | |
"ncx":"http://www.daisy.org/z3986/2005/ncx/" | |
} | |
info = {} | |
def sortncx(file): | |
ncx = parseNCX(file) | |
ncx.xpath("//ncx:navLabel/ncx:text",namespaces=namespaces)[0].text = info["book_title"] | |
ncx.xpath("//ncx:docTitle/ncx:text",namespaces=namespaces)[0].text = info["book_title"] | |
for i in ncx.xpath(".//ncx:navPoint",namespaces=namespaces): | |
if i[0][0].text == None: | |
i.getparent().remove(i) | |
counter = 1 | |
for item in ncx.xpath(".//ncx:navPoint",namespaces=namespaces): | |
item.set("playOrder",str(counter)) | |
counter += 1 | |
else: | |
counter = 1 | |
ncx = ET.ElementTree(ncx) | |
return ET.tostring(ncx) | |
def parseInfo(file): | |
global info | |
try: | |
f = ZIP.ZipFile(file).read("META-INF/container.xml") | |
except KeyError: | |
print "The %s file is not a valid OCF." % str(file) | |
try: | |
m = ET.fromstring(f) | |
info["path_to_opf"] = m[0][0].get("full-path") | |
root_folder = os.path.dirname(info["path_to_opf"]) | |
except Exception as e: | |
print e | |
sys.exit(2) | |
opf = ET.fromstring(ZIP.ZipFile(file).read(info["path_to_opf"])) | |
id = opf.xpath("//opf:spine",namespaces=namespaces)[0].get("toc") | |
info["book_title"] = "".join(opf.xpath("//dc:title/text()",namespaces=namespaces)) | |
info["book_author"] = "".join(opf.xpath("//dc:creator[0]/text()",namespaces=namespaces)) | |
expr = "//*[@id='%s']" % id | |
info["ncx_name"] = opf.xpath(expr)[0].get("href") | |
info["path_to_ncx"] = root_folder + "/" + info["ncx_name"] | |
info.pop("ncx_name") | |
return info | |
def parseNCX(file): | |
ncx = {} | |
ncx = ET.fromstring(ZIP.ZipFile(file).read(parseInfo(file)["path_to_ncx"])) | |
return ncx | |
if __name__ == '__main__': | |
info = parseInfo(sys.argv[1]) | |
sorted_ncx = sortncx(sys.argv[1]) | |
print sorted_ncx |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment