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
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
|
#! /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
from gi.repository import GObject
from gi.repository import Gtk
from sugar3 import network
import logging
import threading
import os
import urllib
import time
import csv
import sys
sys.path.insert(0, './')
import feedparser
_logger = logging.getLogger('get-ia-books-activity')
_REL_OPDS_ACQUISTION = u'http://opds-spec.org/acquisition'
_REL_SUBSECTION = 'subsection'
_REL_OPDS_POPULAR = u'http://opds-spec.org/sort/popular'
_REL_OPDS_NEW = u'http://opds-spec.org/sort/new'
_REL_ALTERNATE = 'alternate'
_REL_CRAWLABLE = 'http://opds-spec.org/crawlable'
GObject.threads_init()
class ReadURLDownloader(network.GlibURLDownloader):
"""URLDownloader that provides content-length and content-type."""
def get_content_length(self):
"""Return the content-length of the download."""
if self._info is not None:
length = self._info.headers.get('Content-Length')
if length is not None:
return int(length)
else:
return 0
def get_content_type(self):
"""Return the content-type of the download."""
if self._info is not None:
return self._info.headers.get('Content-type')
return None
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):
def entry_type(entry):
for link in entry['links']:
if link['rel'] in \
[_REL_OPDS_POPULAR, _REL_OPDS_NEW, _REL_SUBSECTION]:
return "CATALOG"
else:
return 'BOOK'
logging.debug('feedparser version %s', feedparser.__version__)
if not self.obj.is_local() and self.midway == False:
uri = self.obj._uri + self.obj._queryterm.replace(' ', '+')
headers = {}
if self.obj._language is not None and self.obj._language != 'all':
headers['Accept-Language'] = self.obj._language
uri = uri + '&lang=' + self.obj._language
logging.error('Searching URL %s headers %s' % (uri, headers))
feedobj = feedparser.parse(uri, request_headers=headers)
else:
feedobj = feedparser.parse(self.obj._uri)
# Get catalog Type
CATALOG_TYPE = 'COMMON'
if 'links' in feedobj['feed']:
for link in feedobj['feed']['links']:
if link['rel'] == _REL_CRAWLABLE:
CATALOG_TYPE = 'CRAWLABLE'
break
for entry in feedobj['entries']:
if entry_type(entry) == 'BOOK' and CATALOG_TYPE is not 'CRAWLABLE':
self.obj._booklist.append(Book(self.obj._configuration, entry))
elif entry_type(entry) == 'CATALOG' or CATALOG_TYPE == 'CRAWLABLE':
self.obj._cataloglist.append( \
Book(self.obj._configuration, entry))
self.obj._feedobj = feedobj
self.obj._ready = True
GObject.idle_add(self.obj.notify_updated, self.midway)
return False
def run(self):
self._download()
def stop(self):
self.stopthread.set()
class Book(object):
def __init__(self, configuration, entry, basepath=None):
self._entry = entry
self._basepath = basepath
self._configuration = configuration
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']
elif link['rel'] in \
[_REL_OPDS_POPULAR, _REL_OPDS_NEW, _REL_SUBSECTION]:
ret[link['type']] = link['href']
elif link['rel'] == _REL_ALTERNATE:
ret[link['type']] = link['href']
else:
pass
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 get_image_url(self):
try:
ret = {}
for link in self._entry['links']:
if link['rel'] == self._configuration['opds_cover']:
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']
except KeyError:
ret = 'Unknown'
return ret
def get_summary(self):
if self._configuration is not None \
and 'summary_field' in self._configuration:
try:
ret = self._entry[self._configuration['summary_field']]
except KeyError:
ret = 'Unknown'
else:
ret = 'Unknown'
return ret
def get_object_id(self):
try:
ret = self._entry['object_id']
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.SignalFlags.RUN_FIRST,
None,
([bool])),
}
def __init__(self, configuration, queryterm, language):
GObject.GObject.__init__(self)
self._configuration = configuration
self._uri = self._configuration['query_uri']
self._queryterm = queryterm
self._language = language
self._feedobj = None
self._next_uri = ''
self._ready = False
self._booklist = []
self._cataloglist = []
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 notify_updated(self, midway):
self.emit('updated', midway)
def __len__(self):
return len(self._booklist)
def has_next(self):
'''
Returns True if more result pages are
available for the resultset
'''
if not 'links' in self._feedobj['feed']:
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 get_catalog_list(self):
'''
Gets the entire catalog list
'''
return self._cataloglist
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, language):
configuration = {'query_uri': os.path.join(path, 'catalog.xml')}
QueryResult.__init__(self, configuration, queryterm, language)
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 RemoteQueryResult(QueryResult):
def __init__(self, configuration, queryterm, language):
QueryResult.__init__(self, configuration, queryterm, language)
class IABook(Book):
def __init__(self, configuration, entry, basepath=None):
Book.__init__(self, configuration, entry, basepath=None)
def get_download_links(self):
return self._entry['links']
def get_image_url(self):
return {'jpg': self._entry['cover_image']}
class DownloadIAThread(threading.Thread):
def __init__(self, obj, midway):
threading.Thread.__init__(self)
self.midway = midway
self.obj = obj
self._download_content_length = 0
self._download_content_type = None
self._booklist = []
queryterm = self.obj._queryterm
# search_tuple = queryterm.lower().split()
FL = urllib.quote('fl[]')
SORT = urllib.quote('sort[]')
self.search_url = 'http://www.archive.org/advancedsearch.php?q=' + \
urllib.quote('(title:(' + self.obj._queryterm.lower() + ') OR ' + \
'creator:(' + queryterm.lower() + ')) AND format:(DJVU)')
self.search_url += '&' + FL + '=creator&' + FL + '=description&' + \
FL + '=format&' + FL + '=identifier&' + FL + '=language'
self.search_url += '&' + FL + '=publisher&' + FL + '=title&' + \
FL + '=volume'
self.search_url += '&' + SORT + '=title&' + SORT + '&' + \
SORT + '=&rows=500&save=yes&fmt=csv&xmlsearch=Search'
self.stopthread = threading.Event()
def _download(self):
GObject.idle_add(self.download_csv, self.search_url)
def download_csv(self, url):
logging.error('get csv from %s', url)
path = os.path.join(self.obj._activity.get_activity_root(), 'instance',
'tmp%i.csv' % time.time())
print 'path=', path
getter = ReadURLDownloader(url)
getter.connect("finished", self._get_csv_result_cb)
getter.connect("progress", self._get_csv_progress_cb)
getter.connect("error", self._get_csv_error_cb)
_logger.debug("Starting download to %s...", path)
try:
getter.start(path)
except:
pass
self._download_content_type = getter.get_content_type()
def _get_csv_progress_cb(self, getter, bytes_downloaded):
if self._download_content_length > 0:
_logger.debug("Downloaded %u of %u bytes...",
bytes_downloaded, self._download_content_length)
else:
_logger.debug("Downloaded %u bytes...",
bytes_downloaded)
def _get_csv_error_cb(self, getter, err):
_logger.debug("Error getting CSV: %s", err)
self._download_content_length = 0
self._download_content_type = None
def _get_csv_result_cb(self, getter, tempfile, suggested_name):
print 'Content type:', self._download_content_type
if self._download_content_type.startswith('text/html'):
# got an error page instead
self._get_csv_error_cb(getter, 'HTTP Error')
return
self.process_downloaded_csv(tempfile, suggested_name)
def process_downloaded_csv(self, tempfile, suggested_name):
reader = csv.reader(open(tempfile, 'rb'))
reader.next() # skip the first header row.
for row in reader:
if len(row) < 7:
_logger.debug("Server Error: %s", self.search_url)
return
entry = {}
entry['author'] = row[0]
entry['description'] = row[1]
entry['format'] = row[2]
entry['identifier'] = row[3]
entry['dcterms_language'] = row[4]
entry['dcterms_publisher'] = row[5]
entry['title'] = row[6]
volume = row[7]
if volume is not None and len(volume) > 0:
entry['title'] = row[6] + 'Volume ' + volume
entry['links'] = {}
url_base = 'http://www.archive.org/download/' + \
row[3] + '/' + row[3]
if entry['format'].find('DjVu') > -1:
entry['links']['image/x.djvu'] = url_base + '.djvu'
if entry['format'].find('Grayscale LuraTech PDF') > -1:
# Fake mime type
entry['links']['application/pdf-bw'] = url_base + '_bw.pdf'
if entry['format'].find('PDF') > -1:
entry['links']['application/pdf'] = url_base + '_text.pdf'
if entry['format'].find('EPUB') > -1:
entry['links']['application/epub+zip'] = url_base + '.epub'
entry['cover_image'] = 'http://www.archive.org/download/' + \
row[3] + '/page/cover_thumb.jpg'
self.obj._booklist.append(IABook(None, entry, ''))
os.remove(tempfile)
GObject.idle_add(self.obj.notify_updated, self.midway)
self.obj._ready = True
return False
def run(self):
self._download()
def stop(self):
self.stopthread.set()
class InternetArchiveQueryResult(QueryResult):
# Search in internet archive does not use OPDS
# because the server implementation is not working very well
def __init__(self, queryterm, language, activity):
GObject.GObject.__init__(self)
self._activity = activity
self._queryterm = queryterm
self._language = language
self._next_uri = ''
self._ready = False
self._booklist = []
self._cataloglist = []
self.threads = []
self._start_download()
def notify_updated(self, midway):
self.emit('updated', midway)
def _start_download(self, midway=False):
d_thread = DownloadIAThread(self, midway)
self.threads.append(d_thread)
d_thread.start()
class ImageDownloaderThread(threading.Thread):
def __init__(self, obj):
threading.Thread.__init__(self)
self.obj = obj
self._getter = ReadURLDownloader(self.obj._url)
self._download_content_length = 0
self._download_content_type = None
self.stopthread = threading.Event()
def _download_image(self):
path = os.path.join(self.obj._activity.get_activity_root(),
'instance', 'tmp%i' % time.time())
self._getter.connect("finished", self._get_image_result_cb)
self._getter.connect("progress", self._get_image_progress_cb)
self._getter.connect("error", self._get_image_error_cb)
_logger.debug("Starting download to %s...", path)
try:
self._getter.start(path)
except:
_logger.debug("Connection timed out for")
GObject.idle_add(self.obj.notify_updated, None)
self._download_content_length = \
self._getter.get_content_length()
self._download_content_type = self._getter.get_content_type()
def _get_image_result_cb(self, getter, tempfile, suggested_name):
_logger.debug("Got Cover Image %s (%s)", tempfile, suggested_name)
self._getter = None
if not self.stopthread.is_set():
GObject.idle_add(self.obj.notify_updated, tempfile)
def _get_image_progress_cb(self, getter, bytes_downloaded):
if self.stopthread.is_set():
try:
_logger.debug('The download %s was cancelled' % getter._fname)
getter.cancel()
except:
_logger.debug('Got an exception while trying ' + \
'to cancel download')
if self._download_content_length > 0:
_logger.debug("Downloaded %u of %u bytes...", bytes_downloaded,
self._download_content_length)
else:
_logger.debug("Downloaded %u bytes...",
bytes_downloaded)
while Gtk.events_pending():
Gtk.main_iteration()
def _get_image_error_cb(self, getter, err):
_logger.debug("Error getting image: %s", err)
self._download_content_length = 0
self._download_content_type = None
self._getter = None
GObject.idle_add(self.obj.notify_updated, None)
def run(self):
self._download_image()
def stop(self):
self.stopthread.set()
class ImageDownloader(GObject.GObject):
__gsignals__ = {
'updated': (GObject.SignalFlags.RUN_FIRST,
None,
([GObject.TYPE_STRING])),
}
def __init__(self, activity, url):
GObject.GObject.__init__(self)
self.threads = []
self._activity = activity
self._url = url
self._start_download()
def _start_download(self):
d_thread = ImageDownloaderThread(self)
self.threads.append(d_thread)
d_thread.start()
def notify_updated(self, temp_file):
self.emit('updated', temp_file)
def stop_download(self):
for thread in self.threads:
thread.stop()
|