Web   ·   Wiki   ·   Activities   ·   Blog   ·   Lists   ·   Chat   ·   Meeting   ·   Bugs   ·   Git   ·   Translate   ·   Archive   ·   People   ·   Donate
summaryrefslogtreecommitdiffstats
path: root/epubview/epub.py
blob: 71267aa842436df98c66fd2ca96e16139e1c1de5 (plain)
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
150
151
152
# Copyright 2009 One Laptop Per Child
# Author: Sayamindu Dasgupta <sayamindu@laptop.org>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA

import zipfile
import tempfile
import os, os.path
from lxml import etree
import shutil

import navmap, epubinfo


class _Epub(object):
    def __init__(self, filepath):
        self._filepath = filepath
        self._zobject = None
        self._opfpath = None
        self._ncxpath = None
        self._basepath = None
        self._tempdir = tempfile.mkdtemp()
        
        if not self._verify():
            print 'Warning: This does not seem to be a valid epub file'
        
        self._get_opf()
        self._get_ncx()
        
        ncxfile = self._zobject.open(self._ncxpath)
        opffile = self._zobject.open(self._opfpath)        
        self._navmap = navmap.NavMap(opffile, ncxfile, self._basepath)
        
        opffile = self._zobject.open(self._opfpath)
        self._info = epubinfo.EpubInfo(opffile) 
        
        self._unzip()
        
    def _unzip(self):
        #self._zobject.extractall(path = self._tempdir) # This is broken upto python 2.7
        orig_cwd = os.getcwd()
        os.chdir(self._tempdir)
        for name in self._zobject.namelist():
            if name.startswith(os.path.sep): # Some weird zip file entries start with a slash, and we don't want to write to the root directory
                name = name[1:]
            if name.endswith(os.path.sep) or name.endswith('\\'):
                os.makedirs(name)
            else:
                self._zobject.extract(name)
        os.chdir(orig_cwd)

                
    def _get_opf(self):
        containerfile = self._zobject.open('META-INF/container.xml')
        
        tree = etree.parse(containerfile)
        root = tree.getroot()
        
        for element in root.iterfind('.//{urn:oasis:names:tc:opendocument:xmlns:container}rootfile'):
            if element.get('media-type') == 'application/oebps-package+xml':
                self._opfpath = element.get('full-path')
        
        if self._opfpath.rpartition('/')[0]:        
            self._basepath = self._opfpath.rpartition('/')[0] + '/'
        else:
            self._basepath = ''
            
        containerfile.close()


    def _get_ncx(self):
        opffile = self._zobject.open(self._opfpath)
        
        tree = etree.parse(opffile)
        root = tree.getroot()

        spine = root.find('.//{http://www.idpf.org/2007/opf}spine')
        tocid = spine.get('toc')

        for element in root.iterfind('.//{http://www.idpf.org/2007/opf}item'):
            if element.get('id') == tocid:
                self._ncxpath = self._basepath + element.get('href')
        
        opffile.close()

    def _verify(self):
        '''
        Method to crudely check to verify that what we 
        are dealing with is a epub file or not
        '''
        if not os.path.exists(self._filepath):
            return False
        
        self._zobject = zipfile.ZipFile(self._filepath)
        
        if not 'mimetype' in self._zobject.namelist():
            return False
        
        mtypefile = self._zobject.open('mimetype')
        mimetype = mtypefile.readline()
        
        if not mimetype.startswith('application/epub+zip'): # Some files seem to have trailing characters
            return False
        
        return True
    
    def get_toc_model(self):
        '''
        Returns a GtkTreeModel representation of the
        Epub table of contents
        '''        
        return self._navmap.get_gtktreestore()
    
    def get_flattoc(self):
        '''
        Returns a flat (linear) list of files to be
        rendered.
        '''                
        return self._navmap.get_flattoc()
    
    def get_basedir(self):
        '''
        Returns the base directory where the contents of the
        epub has been unzipped
        '''
        return self._tempdir
    
    def get_info(self):
        '''
        Returns a EpubInfo object for the open Epub file
        '''        
        return self._info
    
    def close(self):
        '''
        Cleans up (closes open zip files and deletes uncompressed content of Epub. 
        Please call this when a file is being closed or during application exit. 
        '''                
        self._zobject.close()
        shutil.rmtree(self._tempdir)