/
duoMain.py
executable file
·225 lines (193 loc) · 7.74 KB
/
duoMain.py
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
__author__ = 'vin@misday.com'
import os, webbrowser, ConfigParser, traceback
from pyvin.core import Commading
from duoPdf import DuoPdf
from duoPersist import Persist
from pyvin.core import Log
class Duokan:
def __init__(self):
self.TAG = Duokan.__name__
Duokan.ensureDir(os.path.join(os.path.curdir, 'tmp'))
Duokan.ensureDir(os.path.join(os.path.curdir, 'books'))
Duokan.ensureDir(os.path.join(os.path.curdir, 'books', 'new'))
Duokan.ensureDir(os.path.join(os.path.curdir, 'cache'))
self.persist = Persist()
def openInNewTab(self, url):
'''open in browser with new tab'''
if len(url) > 0:
webbrowser.open(url, new=2, autoraise=True)
else:
Log.e(self.TAG, 'url is empty')
def cleanTmp(self):
'''clean the tmp dir'''
path = os.path.join(os.path.curdir, 'tmp')
for item in os.listdir(path):
filename = os.path.join(path, item)
Log.e(self.TAG, 'deleting %s' % (filename, ))
self.deleteFileFolder(filename)
def deleteFileFolder(self, src):
'''delete files and folders'''
if os.path.isfile(src):
try:
os.remove(src)
except:
Log.e(self.TAG, 'delete [%s] failed...' % (src, ))
elif os.path.isdir(src):
for item in os.listdir(src):
itemsrc=os.path.join(src,item)
self.deleteFileFolder(itemsrc)
try:
os.rmdir(src)
except:
Log.e(self.TAG, 'delete [%s] failed...' % (src, ))
def rename(self, id, title = ''):
if len(title) < 1:
title = self.persist.getTitle(id)
path = os.path.join(os.path.curdir, 'books', 'new', id+'.pdf')
newPath = os.path.join(os.path.curdir, 'books', 'new', title+'.pdf')
if os.path.exists(path):
os.rename(path, newPath)
def renameAll(self):
path = os.path.join(os.path.curdir, 'books', 'new')
for item in os.listdir(path):
bid, extname = os.path.splitext(item)
title = self.persist.getTitle(bid)
if title:
newName = '%s%s' % (title, extname)
os.rename(os.path.join(path, item), os.path.join(path, newName))
Log.i(self.TAG, '%s -> %s' % (item, newName))
def openNewFolder(self):
path = os.path.join(os.path.curdir, 'books', 'new')
self.openInNewTab(path)
@staticmethod
def ensureDir(path):
'''check dir exist or not, create it if not exist'''
if not os.path.exists(path):
os.mkdir(path)
@staticmethod
def merge(id):
'''merge pdf files in tmp/${id}, to books/new/${id}.pdf'''
srcPath = os.path.join(os.path.curdir, 'tmp', id)
destPath = os.path.join(os.path.curdir, 'books', 'new', id+'.pdf')
DuoPdf.clean(srcPath) # clean pdf
DuoPdf.merge(destPath, srcPath)
@staticmethod
def mergeSingle(src):
if not os.path.isdir(src):
Log.w(Duokan.__name__, '[%s] is not a diractory, exit...' % (src, ))
return
path = os.path.split(src)
id = path[1]
destPath = os.path.join(path[0], id+'.pdf')
DuoPdf.clean(src)
DuoPdf.merge(destPath, src)
@staticmethod
def crop(id):
'''crop pdf file in books/new/${id}.pdf'''
srcPath = os.path.join(os.path.curdir, 'books', 'new', id+'.pdf')
destPath = os.path.join(os.path.curdir, 'books', 'new', id+'.cropped.pdf')
DuoPdf.cropWH(destPath, srcPath, 500, 666)
os.remove(srcPath)
os.rename(destPath, srcPath)
@staticmethod
def cropSingle(src):
'''crop pdf file'''
srcPath, ext = os.path.splitext(src)
destPath = srcPath + '_c' + ext
DuoPdf.cropWH(destPath, src, 500, 666)
@staticmethod
def crop4Print(src):
'''crop blank edge except first page'''
srcPath, ext = os.path.splitext(src)
destPath = srcPath + '_p' + ext
# print destPath
DuoPdf.crop2(destPath, src, (0, 12, 48, 12), (48, 12, 0, 12))
@staticmethod
def crop4Kindle(src):
'''crop blank edge'''
srcPath, ext = os.path.splitext(src)
destPath = srcPath + '_k' + ext
# print destPath
DuoPdf.crop(destPath, src, 50, 12, 50, 12)
@staticmethod
def crop4Nook(src):
'''crop blank edge'''
srcPath, ext = os.path.splitext(src)
destPath = srcPath + '_n' + ext
# print destPath
DuoPdf.crop(destPath, src, 56, 40, 56, 40)
def addBook(self, id, title, author, link):
return self.persist.addBook(id, title, author, link)
def isDownload(self, id):
return self.persist.isDownload(id)
def setDownload(self, id):
self.persist.setDownload(id)
class Downloader(Commading):
EVT_LOG = 11
EVT_PROG = 12
EVT_START = Commading.ON_START
EVT_STOP = 14
def __init__(self, bid, name, proxyHost='', proxyAuthUser='', proxyAuthPswd=''):
'''phantomjs --proxy=host --proxy-auth=username:password duokan.js %1 %ddd%/%2 4'''
self.TAG = Downloader.__name__
cmd = ['plugin/phantomjs',]
if len(proxyHost) > 0:
cmd.append('--proxy=%s' % (proxyHost, ))
if len(proxyAuthUser) > 0 and len(proxyAuthPswd):
cmd.append('--proxy-auth=%s:%s' % (proxyAuthUser, proxyAuthPswd))
cmd.append('--disk-cache=true') # enable cache to speed up downloading
cmd.append('--disk-cache-path=cache') # set cache path
# cmd.append('--debug=true')
cmd.append('duokan.js')
cmd.append(bid)
cmd.append('tmp/%s' % (name, ))
cmd.append('4')
print cmd
Commading.__init__(self, cmd)
self.init([Downloader.EVT_LOG, Downloader.EVT_PROG, Downloader.EVT_START, Downloader.EVT_STOP])
self.bind(Commading.ON_LOG, self.onLog)
self.bind(Commading.ON_STOP, self.onStop)
self.persist = Persist()
self.id = bid
def onStop(self, event):
Log.i(self.TAG, 'phantomjs finished...')
self.persist.setDownload(self.id)
Duokan.merge(self.id)
Log.i(self.TAG, 'merged pdf...')
Duokan.crop(self.id)
Log.i(self.TAG, 'croped pdf...')
self.dispatch(Downloader.EVT_STOP)
def onLog(self, event, str):
# self.hdl.cbLog(str)
self.dispatch(Downloader.EVT_LOG, str)
prefix = 'progress, '
if str.startswith(prefix):
str = str[len(prefix):]
str = str.lstrip('\n').lstrip('\r')
str = str.split('/')
prog = int(str[0]) * 100 / int(str[1])
# self.hdl.cbProgress(prog)
self.dispatch(Downloader.EVT_PROG, prog)
class Config:
KEY_PROXY = 'proxy'
KEY_PROXY_HOST = 'host'
KEY_PROXY_USER = 'user'
KEY_PROXY_PAWD = 'pswd'
def __init__(self, name = 'config.conf'):
self.TAG = Config.__name__
self.conf = ConfigParser.ConfigParser()
self.conf.read(name)
self._getProxy()
def _getProxy(self):
self.host = ''
self.user = ''
self.pswd = ''
try:
self.host = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_HOST)
self.user = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_USER)
self.pswd = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_PAWD)
except:
Log.w(self.TAG, 'read proxy failed')
traceback.print_exc()
def getProxy(self):
return (self.host, self.user, self.pswd)