-
Notifications
You must be signed in to change notification settings - Fork 0
/
jpeg2epub
executable file
·274 lines (252 loc) · 9.76 KB
/
jpeg2epub
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
#!/usr/bin/env python
# coding: utf-8
# jpeg2epub: copyright (C) 2013, RUAMEL bvba, A. van der Neut
import os
import sys
from io import open
from textwrap import dedent
from cStringIO import StringIO
import zipfile
import uuid
import datetime
class Jpeg2Epub(object):
"""simple epub creator for series of JPEG image files
creates the file epub file in memory
"""
version = 1 # class version when used a s library
def __init__(self, title, file_name=None, creator=None, title_sort=None,
series=None, series_idx=None, verbose=0):
self._output_name = file_name if file_name else \
title.replace(' ', '_') + '.epub'
self._files = None
self._zip = None # the in memory zip file
self._zip_data = None
self._content = []
self._count = 0
self._series = series
self._series_idx = series_idx
self.d = dict(
title=title,
title_sort=title_sort if title_sort else title,
creator=creator if creator else 'Unknown',
opf_name="c.opf",
toc_name="toc.ncx",
ncx_ns='http://www.daisy.org/z3986/2005/ncx/',
opf_ns='http://www.idpf.org/2007/opf',
xsi_ns='http://www.w3.org/2001/XMLSchema-instance',
dcterms_ns='http://purl.org/dc/terms/',
dc_ns='http://purl.org/dc/elements/1.1/',
cal_ns='http://calibre.kovidgoyal.net/2009/metadata',
cont_urn='urn:oasis:names:tc:opendocument:xmlns:container',
mt='application/oebps-package+xml', # media-type
style_sheet='stylesheet.css',
uuid=None,
nav_point=None,
nav_uuid=None,
)
def __enter__(self):
return self
def __exit__(self, typ, value, traceback):
if value is None:
if isinstance(self._zip_data, basestring):
return
self._write_toc()
self._write_content()
self._zip.close()
self._zip = None
self.d['nav_point'] = None
with open(self._output_name, 'wb') as ofp:
ofp.write(self._zip_data.getvalue())
# minimal test: listing contents of EPUB
# os.system('unzip -lv ' + self._output_name)
return True
return False
def add_image_file(self, file_name):
self._add_image_file(file_name)
self._count += 1
def _write_toc(self):
self._add_from_bytes(self.d['toc_name'], dedent("""\
<?xml version='1.0' encoding='utf-8'?>
<ncx xmlns="{ncx_ns}" version="2005-1" xml:lang="eng">
<head>
<meta content="{uuid}" name="dtb:uid"/>
<meta content="2" name="dtb:depth"/>
<meta content="ruamel.jpeg2epub (0.1)" name="dtb:generator"/>
<meta content="0" name="dtb:totalPageCount"/>
<meta content="0" name="dtb:maxPageNumber"/>
</head>
<docTitle>
<text>xx</text>
</docTitle>
<navMap>
<navPoint id="{nav_uuid}" playOrder="1">
<navLabel>
<text>Start</text>
</navLabel>
<content src="{nav_point}"/>
</navPoint>
</navMap>
</ncx>
""").format(**self.d))
self._content.append((self.d['toc_name'], 'ncx',
'application/x-dtbncx+xml'))
def _write_content(self):
d = self.d.copy()
manifest = []
spine = []
d['manifest'] = ''
d['spine'] = ''
for f in self._content:
manifest.append(
'<item href="{}" id="{}" media-type="{}"/>'.format(*f))
if f[1].startswith('html'):
spine.append('<itemref idref="{}"/>'.format(f[1]))
d['manifest'] = '\n '.join(manifest)
d['spine'] = '\n '.join(spine)
d['ts'] = datetime.datetime.utcnow().isoformat() + '+00:00'
d['series'] = ''
if self._series:
d['series'] = \
u'\n' \
'<meta name="calibre:series" content="{}"/>' \
'<meta name="calibre:series_index" content="{}"/>'.format(
self._series, self._series_idx)
self._add_from_bytes(self.d["opf_name"], dedent(u"""\
<?xml version='1.0' encoding='utf-8'?>
<package xmlns="{opf_ns}" unique-identifier="uuid_id" version="2.0">
<metadata xmlns:xsi="{xsi_ns}" xmlns:opf="{opf_ns}"
xmlns:dcterms="{dcterms_ns}"
xmlns:calibre="{cal_ns}"
xmlns:dc="{dc_ns}">
<dc:language>en</dc:language>
<dc:creator>{creator}</dc:creator>
<meta name="calibre:timestamp" content="{ts}"/>
<meta name="calibre:title_sort" content="{title_sort}"/>
<meta name="cover" content="cover"/>
<dc:date>0101-01-01T00:00:00+00:00</dc:date>
<dc:title>{title}</dc:title>{series}
<dc:identifier id="uuid_id" opf:scheme="uuid">{uuid}
</dc:identifier>
<dc:identifier opf:scheme="calibre">{uuid}</dc:identifier>
</metadata>
<manifest>
{manifest}
</manifest>
<spine toc="ncx">
{spine}
</spine>
</package>
""").format(**d).encode('utf-8'))
def _add_html(self, title):
file_name = self._name(False)
d = self.d.copy()
d['title'] = title
d['img_name'] = self._name()
self._add_from_bytes(file_name, dedent(u"""\
<?xml version='1.0' encoding='utf-8'?>
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>{title}</title>
<meta http-equiv="Content-Type" content="text/html; \
charset=utf-8"/>
<link href="{style_sheet}" rel="stylesheet" type="text/css"/>
</head>
<body class="album">
<div>
<img src="{img_name}" class="albumimg" alt="{title}"/>
</div>
</body>
</html>
""").format(**d).encode('utf-8'))
self._content.append((file_name, 'html{}'.format(self._count),
'application/xhtml+xml'))
if self.d['nav_point'] is None:
self.d['nav_point'] = file_name
self._write_style_sheet()
def _write_style_sheet(self):
file_name = self.d['style_sheet']
self._add_from_bytes(file_name, dedent("""\
.album {
display: block;
font-size: 1em;
padding: 0;
margin: 0;
}
.albumimg {
height: auto;
max-height: 100%;
max-width: 100%;
width: auto
}
"""))
self._content.append((file_name, 'css', 'text/css'))
def _name(self, image=True):
"""no leading zero's necessary in zip internal filenames"""
return '{}.{}'.format(self._count, 'jpg' if image else 'xhtml')
def _add_image_file(self, file_name, width=None, height=None,
strip=None, max_strip_pixel=None, z=None):
z = z if z else self.zip # initializes if not done yet
self._add_html(file_name)
# you can compress JPEGs, but with little result (1-8%) and
# more complex/slow decompression (zip then jpeg)
# Gain 2.836 Mb -> 2.798 Mb ( ~ 1% difference )
if width:
im = EpubImage(file_name)
z.writestr(self._name(), im.read(), zipfile.ZIP_STORED)
else:
z.write(file_name, self._name())
self._content.append((self._name(), 'img{}'.format(self._count),
'image/jpeg'))
@property
def zip(self):
if self._zip is not None:
return self._zip
self._zip_data = StringIO()
# create zip with default compression
#self._zip_data = '/var/tmp/epubtmp/yy.zip'
self._zip = zipfile.ZipFile(self._zip_data, "a",
zipfile.ZIP_DEFLATED, False)
self.d['uuid'] = uuid.uuid4()
self.d['nav_uuid'] = uuid.uuid4()
self._add_mimetype()
self._add_container()
return self._zip
def _add_from_bytes(self, file_name, data, no_compression=False):
self._zip.writestr(
file_name, data,
compress_type=zipfile.ZIP_STORED if no_compression else None)
def _add_mimetype(self):
self._add_from_bytes('mimetype', dedent("""\
application/epub+zip
""").rstrip(), no_compression=True)
def _add_container(self):
self._add_from_bytes('META-INF/container.xml', dedent("""\
<?xml version="1.0"?>
<container version="1.0" xmlns="{cont_urn}">
<rootfiles>
<rootfile full-path="{opf_name}" media-type="{mt}"/>
</rootfiles>
</container>
""").rstrip().format(**self.d))
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--title", "-t", required=True)
parser.add_argument("--title-sort", help="alternative title for sorting")
parser.add_argument(
"--output", "-o",
help="epub name if not specified, derived from title",
)
parser.add_argument("--series", help="series name")
parser.add_argument("--index", help="series index")
parser.add_argument("--creator", help="Creator/Author")
parser.add_argument("file_names", nargs="+")
args = parser.parse_args()
with Jpeg2Epub(args.title, title_sort=args.title_sort,
file_name=args.output,
series=args.series, series_idx=args.index,
creator=args.creator, verbose=0) as j2e:
for file_name in args.file_names:
j2e.add_image_file(file_name)
if __name__ == "__main__":
main()