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
|
#! /usr/bin/env python
# Copyright (C) 2009 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 logging
import feedparser
import threading
import os
import gobject, gtk
_logger = logging.getLogger('get-ia-books-activity')
_FEEDBOOKS_URI = 'http://feedbooks.com/books/search.atom?query='
_INTERNETARCHIVE_URI = 'http://bookserver.archive.org/catalog/opensearch?q='
_REL_OPDS_ACQUISTION = u'http://opds-spec.org/acquisition'
gobject.threads_init()
class DownloadThread(threading.Thread):
def __init__(self, obj, midway):
threading.Thread.__init__ (self)
self.midway = midway
self.obj = obj
self.stopthread = threading.Event()
def _download(self):
if self.obj._win is not None:
self.obj._win.set_cursor(gtk.gdk.Cursor(gtk.gdk.WATCH))
if not self.obj.is_local() and self.midway == False:
feedobj = feedparser.parse(self.obj._uri + self.obj._queryterm.replace(' ', '+'))
else:
feedobj = feedparser.parse(self.obj._uri)
for entry in feedobj['entries']:
self.obj._booklist.append(Book(entry))
self.obj._feedobj = feedobj
self.obj.emit('updated', self.midway)
self.obj._ready = True
if self.obj._win is not None:
self.obj._win.set_cursor(None)
return False
def run (self):
self._download()
def stop(self):
self.stopthread.set()
class Book(object):
def __init__(self, entry, basepath = None):
self._entry = entry
self._basepath = basepath
def get_title(self):
try:
ret = self._entry['title']
except KeyError:
ret = 'Unknown'
return ret
def get_author(self):
try:
ret = self._entry['author']
except KeyError:
ret = 'Unknown'
return ret
def get_download_links(self):
ret = {}
for link in self._entry['links']:
if link['rel'] == _REL_OPDS_ACQUISTION:
if self._basepath is not None and \
not (link['href'].startswith('http') or \
link['href'].startswith('ftp')):
ret[link['type']] = 'file://' \
+ os.path.join(self._basepath, link['href'])
else:
ret[link['type']] = link['href']
return ret
def get_publisher(self):
try:
ret = self._entry['dcterms_publisher']
except KeyError:
ret = 'Unknown'
return ret
def get_published_year(self):
try:
ret = self._entry['published']
except KeyError:
ret = 'Unknown'
return ret
def get_language(self):
try:
ret = self._entry['dcterms_language']
except KeyError:
ret = 'Unknown'
return ret
def match(self, terms):
#TODO: Make this more comprehensive
for term in terms.split('+'):
if term in self.get_title():
return True
if term in self.get_author():
return True
if term in self.get_publisher():
return True
return False
class QueryResult(gobject.GObject):
__gsignals__ = {
'updated': (gobject.SIGNAL_RUN_FIRST,
gobject.TYPE_NONE,
([gobject.TYPE_BOOLEAN])),
}
def __init__(self, uri, queryterm, win):
gobject.GObject.__init__(self)
self._uri = uri
self._queryterm = queryterm
self._win = win
self._feedobj = None
self._next_uri = ''
self._ready = False
self._booklist = []
self.threads = []
self._start_download()
def _start_download(self, midway = False):
d_thread = DownloadThread(self, midway)
self.threads.append(d_thread)
d_thread.start()
def __len__(self):
return len(self._booklist)
def has_next(self):
'''
Returns True if more result pages are
available for the resultset
'''
if not self._feedobj['feed'].has_key('links'):
return False
for link in self._feedobj['feed']['links']:
if link['rel'] == u'next':
self._next_uri = link['href']
return True
return False
def update_with_next(self):
'''
Updates the booklist with the next resultset
'''
if len(self._next_uri) > 0:
self._ready = False
self._uri = self._next_uri
self.cancel() #XXX: Is this needed ?
self._start_download(midway = True)
def cancel(self):
'''
Cancels the query job
'''
for d_thread in self.threads:
d_thread.stop()
def get_book_n(self, n):
'''
Gets the n-th book
'''
return self._booklist[n]
def get_book_list(self):
'''
Gets the entire booklist
'''
return self._booklist
def is_ready(self):
'''
Returns False if a query is in progress
'''
return self._ready
def is_local(self):
'''
Returns True in case of a local school
server or a local device
(yay! for sneakernet)
'''
return False
class LocalVolumeQueryResult(QueryResult):
def __init__(self, path, queryterm, win):
QueryResult.__init__(self, os.path.join(path, 'catalog.xml'), queryterm, win)
def is_local(self):
return True
def get_book_list(self):
ret = []
if self._queryterm is None or self._queryterm is '':
for entry in self._feedobj['entries']:
ret.append(Book(entry, basepath = os.path.dirname(self._uri)))
else:
for entry in self._feedobj['entries']:
book = Book(entry, basepath = os.path.dirname(self._uri))
if book.match(self._queryterm.replace(' ', '+')):
ret.append(book)
return ret
class FeedBooksQueryResult(QueryResult):
def __init__(self, queryterm, win):
QueryResult.__init__(self, _FEEDBOOKS_URI, queryterm, win)
class InternetArchiveQueryResult(QueryResult):
def __init__(self, queryterm, win):
QueryResult.__init__(self, _INTERNETARCHIVE_URI, queryterm, win)
|