Welcome, guest | Sign In | My Account | Store | Cart

Create a Table of Contents for an ebook with XMLtoPDFBook (Python recipe) by Vasudev Ram
ActiveState Code (http://code.activestate.com/recipes/578791/)

XMLtoPDFBook is a tool that allows you to create simple PDF ebooks from XML content. It is a part of the xtpodf toolkit.

You can now create PDF ebooks with XMLtoPDFBook, that include a Table of Contents (TOC).

Python, 149 lines
Download
  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
# XMLtoPDFBook2.py

# A program to convert a book in XML text format to a PDF book.
# Uses xtopdf and ReportLab.

# Author: Vasudev Ram - http://www.dancingbison.com
# Version: v0.2

#--------------------------------------------------------------------

# imports

import sys
import os
import string
import time

from PDFWriter import PDFWriter

try:
    import xml.etree.cElementTree as ET
except ImportError:
    import xml.etree.ElementTree as ET

#--------------------------------------------------------------------

# global variables

sysargv = None

#--------------------------------------------------------------------

def debug(message):
    sys.stderr.write(message + "\n")

#--------------------------------------------------------------------

def get_xml_filename(sysargv):
    return sysargv[1]

#--------------------------------------------------------------------

def get_pdf_filename(sysargv):
    return sysargv[2]

#--------------------------------------------------------------------

def XMLtoPDFBook():

    debug("Entered XMLtoPDFBook()")

    global sysargv

    # Get command-line arguments.
    xml_filename = get_xml_filename(sysargv)
    debug("xml_filename: " + xml_filename)
    pdf_filename = get_pdf_filename(sysargv)
    debug("pdf_filename: " + pdf_filename)

    # Parse the XML file.
    try:
        tree = ET.ElementTree(file=xml_filename)
        debug("tree = " + repr(tree))
    except Exception:
        sys.stderr.write("Error: caught exception in ET.ElementTree(file)")
        sys.exit(1)

    # Get the tree root.
    root = tree.getroot()
    debug("root.tag = " + root.tag)
    if root.tag != "book":
        debug("Error: Root tag is not 'book'")
        sys.exit(1)

    # Initialize the table of contents list.
    toc = []
    # Initialize the chapters list.
    chapters = []

    # Traverse the tree, extracting needed data into variables.
    debug("-" * 60)
    for root_child in root:
        if root_child.tag != "chapter":
            debug("Error: root_child tag is not 'chapter'")
            sys.exit(1)
        chapter = root_child
        #debug(chapter.text)
        chapters.append(chapter.text)
        try:
            chapter_name = chapter.attrib['name']
        except KeyError:
            chapter_name = ""
        toc.append(chapter_name)
        debug("-" * 60)

    # Create and set some fields of a PDFWriter.
    pw = PDFWriter(pdf_filename)
    pw.setFont("Courier", 12)
    pw.setFooter("Generated by XMLtoPDFBook. Copyright 2013 Vasudev Ram")

    # Write the TOC.
    pw.setHeader("Table of Contents")
    chapter_num = 0
    debug("Chapter names")
    for chapter_name in toc:
        debug(chapter_name)
        chapter_num += 1
        pw.writeLine(str(chapter_num) + ": " + chapter_name)
    pw.savePage()

    # Write the chapters.
    chapter_num = 0
    for chapter in chapters:
        chapter_num += 1
        pw.setHeader("Chapter " + str(chapter_num) + ": " + toc[chapter_num - 1])
        lines = chapter.split("\n")
        for line in lines:
            pw.writeLine(line)
        pw.savePage()

    pw.close()

    debug("Exiting XMLtoPDFBook()")

def main():

    debug("Entered main()")

    global sysargv
    sysargv = sys.argv

    # Check for right number of arguments.
    if len(sysargv) != 3:
        sys.exit(1)

    XMLtoPDFBook()

    debug("Exiting main()")

#--------------------------------------------------------------------

if __name__ == "__main__":
    try:
        main()
    except Exception, e:
        sys.stderr.write("Error: caught Exception" + str(e))
        sys.exit(1)

#--------------------------------------------------------------------

More details are available here:

http://jugad2.blogspot.in/2013/12/added-table-of-contents-feature-to.html

This allows you to include a Table of Contents (TOC) at the beginning of the PDF ebooks you create with XMLtoPDFBook.

XMLtoPDFBook is a part of the xtopdf toolkit:

https://bitbucket.org/vasudevram/xtopdf

Tags: ebooks, pdf, publishing, python, reportlab, xtopdf