Turning a couple of HTML files into an ePub

Prerequisites

You need to run this script next to a folder called chapters, that contains your HTML files
The files you want to add must be valid XHTML
You need to use the attached skeleton that does not contain any HTML files

Code

#!/usr/bin/python
import os, shutil

# Remove previous epub files
if os.path.isdir("/tmp/epub"):
    shutil.rmtree("/tmp/epub")

# Copy ePub skeleton
shutil.copytree("epub-raw-files", "/tmp/epub")

# Copy chapters
for chapter in os.listdir("chapters"):
    shutil.copyfile("chapters/" + chapter, "/tmp/epub/OEBPS/" + chapter)

###
# Create item list
manifest = ""
spine = ""
nav = ""
playorder = 1
for file in sorted(os.listdir("/tmp/epub/OEBPS/")):
    if file.split(".")[-1] == "html":
        manifest += '<item id="' + file[:-5]  + '" href="' + file + '" media-type="application/xhtml+xml"/>'
        spine += '<itemref idref="' + file[:-5] + '"/>'
        nav += '<navPoint id="' + file[:-5] + '" playOrder="' + str(playorder) + '"><navLabel><text>' + file[:-5] + '</text></navLabel><content src="' + file + '"/></navPoint>'
        playorder += 1

# Add chapters to catalogue
opf = open("/tmp/epub/OEBPS/content.opf", "w")

content = """<?xml version='1.0' encoding='utf-8'?>
<package xmlns="http://www.idpf.org/2007/opf" 
            xmlns:dc="http://purl.org/dc/elements/1.1/" 
            unique-identifier="bookid" version="2.0">
  <metadata>
    <dc:title>Book of Chapters</dc:title>
    <dc:creator>Anonymous</dc:creator>
    <dc:identifier id="bookid">urn:uuid:12345</dc:identifier>
    <dc:language>en-US</dc:language>
    <meta name="cover" content="cover-image" /> 
  </metadata>
  <manifest>
    <item id="ncx" href="toc.ncx" media-type="text/xml"/>
    <item id="cover" href="title.html" media-type="application/xhtml+xml"/>
    <item id="cover-image" href="images/cover.png" media-type="image/png"/>
    <item id="css" href="stylesheet.css" media-type="text/css"/>
""" + manifest + """
  </manifest>
  <spine toc="ncx">
    <itemref idref="cover" linear="no"/>
""" + spine + """
  </spine>
  <guide>
    <reference href="title.html" type="cover" title="Cover"/>
  </guide>
</package>"""

opf.write(content)
### Write the TOC of our book
# 

ncx = open("/tmp/epub/OEBPS/toc.ncx", "w")

content = """<?xml version='1.0' encoding='utf-8'?>
<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN" 
                 "http://www.daisy.org/z3986/2005/ncx-2005-1.dtd">
<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1">
  <head>
    <meta name="dtb:uid" content="urn:uuid:12345"/>
    <meta name="dtb:depth" content="1"/>
    <meta name="dtb:totalPageCount" content="0"/>
    <meta name="dtb:maxPageNumber" content="0"/>
  </head>
  <docTitle>
    <text>Book of Chapters</text>
  </docTitle>
  <navMap>
""" + nav + """
  </navMap>
</ncx>"""

ncx.write(content)

Don't forget the magic words:

cd /tmp/epub
zip -0X img.epub mimetype
zip -Xr9D img.epub *

Attachments

File:EPubChapters epub-raw-files.zip