|
1
|
|
|
#! /usr/bin/python3 |
|
2
|
|
|
# vim: set expandtab tabstop=4 shiftwidth=4 : |
|
3
|
|
|
"""Module to create ebooks""" |
|
4
|
|
|
|
|
5
|
|
|
import html |
|
6
|
|
|
import sys |
|
7
|
|
|
import subprocess |
|
8
|
|
|
import os |
|
9
|
|
|
import urllib.parse |
|
10
|
|
|
import datetime |
|
11
|
|
|
from itertools import chain |
|
12
|
|
|
from comic_abstract import get_date_for_comic, get_info_before_comic, get_info_after_comic |
|
13
|
|
|
|
|
14
|
|
|
# http://www.amazon.com/gp/feature.html?ie=UTF8&docId=1000234621 |
|
15
|
|
|
KINDLEGEN_PATH = './kindlegen_linux_2.6_i386_v2_9/kindlegen' |
|
16
|
|
|
HTML_HEADER = """ |
|
17
|
|
|
<html> |
|
18
|
|
|
<head> |
|
19
|
|
|
<title>%s</title> |
|
20
|
|
|
<meta name='book-type' content='comic'/> |
|
21
|
|
|
<meta name='orientation-lock' content='landscape'/> |
|
22
|
|
|
<meta name='cover' content='%s'> |
|
23
|
|
|
</head> |
|
24
|
|
|
<body> |
|
25
|
|
|
Generated with '%s' at %s<br> |
|
26
|
|
|
<a name='TOC'><h1>Table of Contents</h1></a>""" |
|
27
|
|
|
HTML_TOC_ITEM = """ |
|
28
|
|
|
<a href='#%d'>%s</a><br>""" |
|
29
|
|
|
HTML_START = """ |
|
30
|
|
|
<mbp:pagebreak /> |
|
31
|
|
|
<h1>Comics</h1> |
|
32
|
|
|
<a name='start' />""" |
|
33
|
|
|
HTML_COMIC_INFO = """ |
|
34
|
|
|
<mbp:pagebreak /> |
|
35
|
|
|
<a name='%d'/><h2>%s</h2> |
|
36
|
|
|
%s %s<br>""" |
|
37
|
|
|
HTML_COMIC_ADDITIONAL_INFO = """ |
|
38
|
|
|
%s<br>""" |
|
39
|
|
|
HTML_COMIC_IMG = """ |
|
40
|
|
|
<img src='%s' style='width:100%%'><br>""" |
|
41
|
|
|
HTML_FOOTER = """ |
|
42
|
|
|
</body> |
|
43
|
|
|
</html>""" |
|
44
|
|
|
|
|
45
|
|
|
XHTML_HEADER = """ |
|
46
|
|
|
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" |
|
47
|
|
|
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> |
|
48
|
|
|
<html xmlns="http://www.w3.org/1999/xhtml"> |
|
49
|
|
|
|
|
50
|
|
|
<head> |
|
51
|
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> |
|
52
|
|
|
<title>%s</title> |
|
53
|
|
|
<meta name='cover' content='%s'/> |
|
54
|
|
|
</head> |
|
55
|
|
|
|
|
56
|
|
|
<body> |
|
57
|
|
|
Generated with '%s' at %s |
|
58
|
|
|
""" |
|
59
|
|
|
|
|
60
|
|
|
XHTML_TOC_ITEM = """ |
|
61
|
|
|
<a href='#%d'>%s</a><br/>""" |
|
62
|
|
|
|
|
63
|
|
|
XHTML_START = """ |
|
64
|
|
|
<h1>Comics</h1>""" |
|
65
|
|
|
|
|
66
|
|
|
XHTML_COMIC_INFO = """ |
|
67
|
|
|
<a name='%d'/><h2>%s</h2> |
|
68
|
|
|
%s %s<br/>""" |
|
69
|
|
|
|
|
70
|
|
|
XHTML_COMIC_ADDITIONAL_INFO = """ |
|
71
|
|
|
%s<br/>""" |
|
72
|
|
|
|
|
73
|
|
|
XHTML_COMIC_IMG = """ |
|
74
|
|
|
<img src='%s' style='width:100%%'><br>""" |
|
75
|
|
|
|
|
76
|
|
|
XHTML_FOOTER = """ |
|
77
|
|
|
</body> |
|
78
|
|
|
|
|
79
|
|
|
</html>""" |
|
80
|
|
|
|
|
81
|
|
|
HTML_TAGS = HTML_HEADER, HTML_TOC_ITEM, HTML_START, HTML_COMIC_INFO, HTML_COMIC_ADDITIONAL_INFO, HTML_COMIC_IMG, HTML_FOOTER |
|
82
|
|
|
XHTML_TAGS = XHTML_HEADER, XHTML_TOC_ITEM, XHTML_START, XHTML_COMIC_INFO, XHTML_COMIC_ADDITIONAL_INFO, XHTML_COMIC_IMG, XHTML_FOOTER |
|
83
|
|
|
|
|
84
|
|
|
|
|
85
|
|
|
def collect_comics(comic_classes): |
|
86
|
|
|
"""Retrieve all comics for the list of comic classes provided.""" |
|
87
|
|
|
return chain.from_iterable(c.get_comics() for c in comic_classes) |
|
88
|
|
|
|
|
89
|
|
|
|
|
90
|
|
|
def filter_comics(comics): |
|
91
|
|
|
"""Filter comics based on (hardcoded) criterias. |
|
92
|
|
|
|
|
93
|
|
|
On the long run, I'd like the criteria to be provided via command-line |
|
94
|
|
|
arguments.""" |
|
95
|
|
|
return [c for c in comics if 'new' in c] |
|
96
|
|
|
|
|
97
|
|
|
|
|
98
|
|
|
def sort_comics(comics): |
|
99
|
|
|
"""Sort comics based on (hardcoded) criterias. |
|
100
|
|
|
|
|
101
|
|
|
On the long run, I'd like the criteria to be provided via command-line |
|
102
|
|
|
arguments.""" |
|
103
|
|
|
return sorted(comics, key=get_date_for_comic, reverse=True) |
|
104
|
|
|
|
|
105
|
|
|
|
|
106
|
|
|
def truncate_comics(comics): |
|
107
|
|
|
"""Truncate the list of comics based on (hardcoded) criterias. |
|
108
|
|
|
|
|
109
|
|
|
On the long run, I'd like the criteria to be provided via command-line |
|
110
|
|
|
arguments.""" |
|
111
|
|
|
return comics[:3000] |
|
112
|
|
|
|
|
113
|
|
|
|
|
114
|
|
|
def make_book(comic_classes): |
|
115
|
|
|
"""Create ebook - not finished.""" |
|
116
|
|
|
comics = truncate_comics(sort_comics(filter_comics(collect_comics(comic_classes)))) |
|
117
|
|
|
for i, c in enumerate(comics): |
|
118
|
|
|
print(i, c['url'], get_date_for_comic(c)) |
|
119
|
|
|
if comics: |
|
120
|
|
|
make_book_from_comic_list( |
|
121
|
|
|
comics, |
|
122
|
|
|
'%s from %s to %s' % |
|
123
|
|
|
(' - '.join(sorted({c['comic'] for c in comics})), |
|
124
|
|
|
min(get_date_for_comic(c) for c in comics).strftime('%x'), |
|
125
|
|
|
max(get_date_for_comic(c) for c in comics).strftime('%x')), |
|
126
|
|
|
'book.html') |
|
127
|
|
|
|
|
128
|
|
|
|
|
129
|
|
|
def convert_unicode_to_html(text): |
|
130
|
|
|
"""Convert unicode text to HTML by escaping it.""" |
|
131
|
|
|
return html.escape(text).encode('ascii', 'xmlcharrefreplace').decode() |
|
132
|
|
|
|
|
133
|
|
|
|
|
134
|
|
|
def make_book_from_comic_list(comics, title, file_name, mobi=True): |
|
135
|
|
|
"""Create book from a list of comics.""" |
|
136
|
|
|
cover = 'empty.jpg' |
|
137
|
|
|
output_dir = 'generated_books' |
|
138
|
|
|
os.makedirs(output_dir, exist_ok=True) |
|
139
|
|
|
html_book = os.path.join(output_dir, file_name) |
|
140
|
|
|
|
|
141
|
|
|
header, toc_item, start, com_info, com_add_info, com_img, footer = HTML_TAGS if mobi else XHTML_TAGS |
|
142
|
|
|
|
|
143
|
|
|
with open(html_book, 'w+') as book: |
|
144
|
|
|
book.write(header % ( |
|
145
|
|
|
title, |
|
146
|
|
|
cover, |
|
147
|
|
|
' '.join(sys.argv), |
|
148
|
|
|
datetime.datetime.now().strftime('%c') |
|
149
|
|
|
)) |
|
150
|
|
|
|
|
151
|
|
|
for i, com in enumerate(comics): |
|
152
|
|
|
book.write(toc_item % (i, com['url'])) |
|
153
|
|
|
|
|
154
|
|
|
book.write(start) |
|
155
|
|
|
|
|
156
|
|
|
for i, com in enumerate(comics): |
|
157
|
|
|
book.write(com_info % ( |
|
158
|
|
|
i, com['url'], com['comic'], get_date_for_comic(com).strftime('%x'))) |
|
159
|
|
|
for info in get_info_before_comic(com): |
|
160
|
|
|
book.write(com_add_info % convert_unicode_to_html(info)) |
|
161
|
|
|
for path in com['local_img']: |
|
162
|
|
|
if path is not None: |
|
163
|
|
|
assert os.path.isfile(path) |
|
164
|
|
|
book.write( |
|
165
|
|
|
com_img % urllib.parse.quote(os.path.relpath(path, output_dir))) |
|
166
|
|
|
for info in get_info_after_comic(com): |
|
167
|
|
|
book.write(com_add_info % convert_unicode_to_html(info)) |
|
168
|
|
|
book.write(footer) |
|
169
|
|
|
|
|
170
|
|
|
if mobi: |
|
171
|
|
|
subprocess.call([KINDLEGEN_PATH, '-verbose', '-dont_append_source', html_book]) |
|
172
|
|
|
|
SylvainDe /
ComicBookMaker
