-
Notifications
You must be signed in to change notification settings - Fork 17
/
PodGrab.py
executable file
·700 lines (589 loc) · 24.4 KB
/
PodGrab.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
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
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
#!/usr/bin/env python
# PodGrab - A Python command line audio/video podcast downloader for RSS XML feeds.
# Supported RSS item file types: MP3, M4V, OGG, FLV, MP4, MPG/MPEG, WMA, WMV, WEBM
# Version: 1.1.2 - 06/10/2011
# Jonathan Baker
# [email protected] (http://the-node.org)
# Werner Avenant - added small changes to write M3U file of podcasts downloaded today
# [email protected] (http://www.collectiveminds.co.za)
# Do with this code what you will, it's "open source". As a courtesy,
# I would appreciate credit if you base your code on mine. If you find
# a bug or think the code sucks balls, please let me know :-)
# Outstanding issues:-
# - Video podcasts which which are not direct URLs and are modified by PodGrab
# in order to be grabbed won't display their size as the filenames haven't
# been stripped of their garbage URL info yet. It'll say 0 bytes, but don't
# worry, they've downloaded.
import os
import sys
import argparse
import urllib2
import xml.dom.minidom
import datetime
from time import gmtime, strftime, strptime, mktime
import sqlite3
import shutil
import smtplib
from email.mime.text import MIMEText
import platform
import traceback
import unicodedata
MODE_NONE = 70
MODE_SUBSCRIBE = 71
MODE_DOWNLOAD = 72
MODE_UNSUBSCRIBE = 73
MODE_LIST = 74
MODE_UPDATE = 75
MODE_MAIL_ADD = 76
MODE_MAIL_DELETE = 77
MODE_MAIL_LIST = 78
MODE_EXPORT = 79
MODE_IMPORT = 80
NUM_MAX_DOWNLOADS = 4
DOWNLOAD_DIRECTORY = "podcasts"
# Added 2011-10-06 Werner Avenant - added current_dictory here so it can be global
current_directory = ''
m3u_file = ''
total_item = 0
total_size = 0
has_error = 0
def main(argv):
mode = MODE_NONE
has_error = 0
num_podcasts = 0
error_string = ""
feed_url = ""
feed_name = ""
mail_address = ""
message = ""
mail = ""
# Added 2011-10-06 Werner Avenant
global current_directory
global m3u_file
now = datetime.datetime.now();
m3u_file = str(now)[:10] + '.m3u'
current_directory = os.path.realpath(os.path.dirname(sys.argv[0]))
download_directory = current_directory + os.sep + DOWNLOAD_DIRECTORY
global total_items
global total_size
total_items = 0
total_size = 0
data = ""
parser = argparse.ArgumentParser(description='A command line Podcast downloader for RSS XML feeds')
parser.add_argument('-s', '--subscribe', action="store", dest="sub_feed_url", help='Subscribe to the following XML feed and download latest podcast')
parser.add_argument('-d', '--download', action="store", dest="dl_feed_url", help='Bulk download all podcasts in the following XML feed or file')
parser.add_argument('-un', '--unsubscribe', action="store", dest="unsub_url", help='Unsubscribe from the following Podcast feed')
parser.add_argument('-ma', '--mail-add', action="store", dest="mail_address_add", help='Add a mail address to mail subscription updates to')
parser.add_argument('-md', '--mail-delete', action="store", dest="mail_address_delete", help='Delete a mail address')
parser.add_argument('-l', '--list', action="store_const", const="ALL", dest="list_subs", help='Lists current Podcast subscriptions')
parser.add_argument('-u', '--update', action="store_const", const="UPDATE", dest="update_subs", help='Updates all current Podcast subscriptions')
parser.add_argument('-ml', '--mail-list', action="store_const", const="MAIL", dest="list_mail", help='Lists all current mail addresses')
parser.add_argument('-io', '--import', action="store", dest="opml_import", help='Import subscriptions from OPML file')
parser.add_argument('-eo', '--export', action="store_const", const="OPML_EXPORT", dest="opml_export", help='Export subscriptions to OPML file')
arguments = parser.parse_args()
if arguments.sub_feed_url:
feed_url = arguments.sub_feed_url
data = open_datasource(feed_url)
if not data:
error_string = "Not a valid XML file or URL feed!"
has_error = 1
else:
print "XML data source opened\n"
mode = MODE_SUBSCRIBE
elif arguments.dl_feed_url:
feed_url = arguments.dl_feed_url
data = open_datasource(feed_url)
if not data:
error_string = "Not a valid XML file or URL feed!"
has_error = 1
else:
print "XML data source opened\n"
mode = MODE_DOWNLOAD
elif arguments.unsub_url:
feed_url = arguments.unsub_url
mode = MODE_UNSUBSCRIBE
elif arguments.list_subs:
mode = MODE_LIST
elif arguments.update_subs:
mode = MODE_UPDATE
elif arguments.mail_address_add:
mail_address = arguments.mail_address_add
mode = MODE_MAIL_ADD
elif arguments.mail_address_delete:
mail_address = arguments.mail_address_delete
mode = MODE_MAIL_DELETE
elif arguments.list_mail:
mode = MODE_MAIL_LIST
elif arguments.opml_import:
import_file_name = arguments.opml_import
mode = MODE_IMPORT
elif arguments.opml_export:
mode = MODE_EXPORT
else:
error_string = "No Arguments supplied - for usage run 'PodGrab.py -h'"
has_error = 1
print "Default encoding: " + sys.getdefaultencoding()
todays_date = strftime("%a, %d %b %Y %H:%M:%S", gmtime())
print "Current Directory: ", current_directory
if does_database_exist(current_directory):
connection = connect_database(current_directory)
if not connection:
error_string = "Could not connect to PodGrab database file!"
has_error = 1
else:
cursor = connection.cursor()
else:
print "PodGrab database missing. Creating..."
connection = connect_database(current_directory)
if not connection:
error_string = "Could not create PodGrab database file!"
has_error = 1
else:
print "PodGrab database created"
cursor = connection.cursor()
setup_database(cursor, connection)
print "Database setup complete"
if not os.path.exists(download_directory):
print "Podcast download directory is missing. Creating..."
try:
os.mkdir(download_directory)
print "Download directory '" + download_directory + "' created"
except OSError:
error_string = "Could not create podcast download sub-directory!"
has_error = 1
else:
print "Download directory exists: '" + download_directory + "'"
if not has_error:
if mode == MODE_UNSUBSCRIBE:
feed_name = get_name_from_feed(cursor, connection, feed_url)
if feed_name == "None":
print "Feed does not exist in the database! Skipping..."
else:
feed_name = clean_string(feed_name)
channel_directory = download_directory + os.sep + feed_name
print "Deleting '" + channel_directory + "'..."
delete_subscription(cursor, connection, feed_url)
try :
shutil.rmtree(channel_directory)
except OSError:
print "Subscription directory has not been found - it might have been manually deleted"
print "Subscription '" + feed_name + "' removed"
elif mode == MODE_LIST:
print "Listing current podcast subscriptions...\n"
list_subscriptions(cursor, connection)
elif mode == MODE_UPDATE:
print "Updating all podcast subscriptions..."
subs = get_subscriptions(cursor, connection)
for sub in subs:
feed_name = sub[0]
feed_url = sub[1]
print "Feed for subscription: '" + feed_name + "' from '" + feed_url + "' is updating..."
data = open_datasource(feed_url)
if not data:
print "'" + feed_url + "' for '" + feed_name + "' is not a valid feed URL!"
else:
message = iterate_feed(data, mode, download_directory, todays_date, cursor, connection, feed_url)
print message
mail += message
mail = mail + "\n\n" + str(total_items) + " podcasts totalling " + str(total_size) + " bytes have been downloaded."
if has_mail_users(cursor, connection):
print "Have e-mail address(es) - attempting e-mail..."
mail_updates(cursor, connection, mail, str(total_items))
elif mode == MODE_DOWNLOAD or mode == MODE_SUBSCRIBE:
print iterate_feed(data, mode, download_directory, todays_date, cursor, connection, feed_url)
elif mode == MODE_MAIL_ADD:
add_mail_user(cursor, connection, mail_address)
print "E-Mail address: " + mail_address + " has been added"
elif mode == MODE_MAIL_DELETE:
delete_mail_user(cursor, connection, mail_address)
print "E-Mail address: " + mailAddress + " has been deleted"
elif mode == MODE_MAIL_LIST:
list_mail_addresses(cursor, connection)
elif mode == MODE_EXPORT:
export_opml_file(cursor, connection, current_directory)
elif mode == MODE_IMPORT:
import_opml_file(cursor, connection, current_directory, download_directory, import_file_name)
else:
print "Sorry, there was some sort of error: '" + error_string + "'\nExiting...\n"
if connection:
connection.close()
def open_datasource(xml_url):
try:
response = urllib2.urlopen(xml_url)
except ValueError:
try:
response = open(xml_url,'r')
except ValueError:
print "ERROR - Invalid feed!"
response = False
except urllib2.URLError:
print "ERROR - Connection problems. Please try again later"
response = False
except httplib.IncompleteRead:
print "ERROR - Incomplete data read. Please try again later"
response = False
if response != False:
return response.read()
else:
return response
def export_opml_file(cur, conn, cur_dir):
item_count = 0
feed_name = ""
feed_url = ""
last_ep = ""
now = datetime.datetime.now()
file_name = cur_dir + os.sep + "podgrab_subscriptions-" + str(now.year) + "-" + str(now.month) + "-" + str(now.day) + ".opml"
subs = get_subscriptions(cur, conn)
file_handle = open(file_name,"w")
print "Exporting RSS subscriptions database to: '" + file_name + "' OPML file...please wait.\n"
header = "<opml version=\"2.0\">\n<head>\n\t<title>PodGrab Subscriptions</title>\n</head>\n<body>\n"
file_handle.writelines(header)
for sub in subs:
feed_name = sub[0]
feed_url = sub[1]
last_ep = sub[2]
file_handle.writelines("\t<outline title=\"" + feed_name + "\" text=\"" + feed_name + "\" type=\"rss\" xmlUrl=\"" + feed_url + "\" htmlUrl=\"" + feed_url + "\"/>\n")
print "Exporting subscription '" + feed_name + "'...Done.\n"
item_count = item_count + 1
footer = "</body>\n</opml>"
file_handle.writelines(footer)
file_handle.close()
print str(item_count) + " item(s) exported to: '" + file_name + "'. COMPLETE"
def import_opml_file(cur, conn, cur_dir, download_dir, import_file):
count = 0
print "Importing OPML file '" + import_file + "'..."
if import_file.startswith("/") or import_file.startswith(".."):
data = open_datasource(import_file)
if not data:
print "ERROR = Could not open OPML file '" + import_file + "'"
else:
data = open_datasource(cur_dir + os.sep + import_file)
if not data:
print "ERROR - Could not open OPML file '" + cur_dir + os.sep + import_file + "'"
if data:
print "File opened...please wait"
try:
xml_data = xml.dom.minidom.parseString(data)
items = xml_data.getElementsByTagName('outline')
for item in items:
item_feed = item.getAttribute('xmlUrl')
item_name = item.getAttribute('title')
item_name = clean_string(item_name)
print "Subscription Title: " + item_name
print "Subscription Feed: " + item_feed
item_directory = download_dir + os.sep + item_name
if not os.path.exists(item_directory):
os.makedirs(item_directory)
if not does_sub_exist(cur, conn, item_feed):
insert_subscription(cur, conn, item_name, item_feed)
count = count + 1
else:
print "This subscription is already present in the database. Skipping..."
print "\n"
print "\nA total of " + str(count) + " subscriptions have been added from OPML file: '" + import_file + "'"
print "These will be updated on the next update run.\n"
except xml.parsers.expat.ExpatError:
print "ERROR - Malformed XML syntax in feed. Skipping..."
def iterate_feed(data, mode, download_dir, today, cur, conn, feed):
print "Iterating feed..."
message = ""
try:
xml_data = xml.dom.minidom.parseString(data)
for channel in xml_data.getElementsByTagName('channel'):
channel_title = channel.getElementsByTagName('title')[0].firstChild.data
channel_link = channel.getElementsByTagName('link')[0].firstChild.data
print "Channel Title: ===" + channel_title + "==="
print "Channel Link: " + channel_link
channel_title = clean_string(channel_title)
channel_directory = download_dir + os.sep + channel_title
if not os.path.exists(channel_directory):
os.makedirs(channel_directory)
print "Current Date: ", today
if mode == MODE_DOWNLOAD:
print "Bulk download. Processing..."
# 2011-10-06 Replaced channel_directory with channel_title - needed for m3u file later
num_podcasts = iterate_channel(channel, today, mode, cur, conn, feed, channel_title)
print "\n", num_podcasts, "have been downloaded"
elif mode == MODE_SUBSCRIBE:
print "Feed to subscribe to: " + feed + ". Checking for database duplicate..."
if not does_sub_exist(cur, conn, feed):
print "Subscribe. Processing..."
# 2011-10-06 Replaced channel_directory with channel_title - needed for m3u file later
num_podcasts = iterate_channel(channel, today, mode, cur, conn, feed, channel_title)
print "\n", num_podcasts, "have been downloaded from your subscription"
else:
print "Subscription already exists! Skipping..."
elif mode == MODE_UPDATE:
print "Updating RSS feeds. Processing..."
num_podcasts = iterate_channel(channel, today, mode, cur, conn, feed, channel_title)
message += str(num_podcasts) + " have been downloaded from your subscription: '" + channel_title + "'\n"
except xml.parsers.expat.ExpatError:
print "ERROR - Malformed XML syntax in feed. Skipping..."
message += "0 podcasts have been downloaded from this feed due to RSS syntax problems. Please try again later"
except UnicodeEncodeError:
print "ERROR - Unicoce encoding error in string. Cannot convert to ASCII. Skipping..."
message += "0 podcasts have been downloaded from this feed due to RSS syntax problems. Please try again later"
return message
def clean_string(str):
new_string = str
if new_string.startswith("-"):
new_string = new_string.lstrip("-")
if new_string.endswith("-"):
new_string = new_string.rstrip("-")
new_string_final = ''
for c in new_string:
if c.isalnum() or c == "-" or c == "." or c.isspace():
new_string_final = new_string_final + ''.join(c)
new_string_final = new_string_final.strip()
new_string_final = new_string_final.replace(' ','-')
new_string_final = new_string_final.replace('---','-')
new_string_final = new_string_final.replace('--','-')
return new_string_final
# Change 2011-10-06 - Changed chan_loc to channel_title to help with relative path names
# in the m3u file
def write_podcast(item, channel_title, date, type):
(item_path, item_file_name) = os.path.split(item)
if len(item_file_name) > 50:
item_file_name = item_file_name[:50]
local_file = current_directory + os.sep + DOWNLOAD_DIRECTORY + os.sep + channel_title + os.sep + clean_string(item_file_name)
if type == "video/quicktime" or type == "audio/mp4" or type == "video/mp4":
if not local_file.endswith(".mp4"):
local_file = local_file + ".mp4"
elif type == "video/mpeg":
if not local_file.endswith(".mpg"):
local_file = local_file + ".mpg"
elif type == "video/x-flv":
if not local_file.endswith(".flv"):
local_file = local_file + ".flv"
elif type == "video/x-ms-wmv":
if not local_file.endswith(".wmv"):
local_file = local_file + ".wmv"
elif type == "video/webm" or type == "audio/webm":
if not local_file.endswith(".webm"):
local_file = local_file + ".webm"
elif type == "audio/mpeg":
if not local_file.endswith(".mp3"):
local_file = local_file + ".mp3"
elif type == "audio/ogg" or type == "video/ogg" or type == "audio/vorbis":
if not local_file.endswith(".ogg"):
local_file = local_file + ".ogg"
elif type == "audio/x-ms-wma" or type == "audio/x-ms-wax":
if not local_file.endswith(".wma"):
local_file = local_file + ".wma"
# Check if file exists, but if the file size is zero (which happens when the user
# presses Crtl-C during a download) - the the code should go ahead and download
# as if the file didn't exist
if os.path.exists(local_file) and os.path.getsize(local_file) != 0:
return 'File Exists'
else:
print "\nDownloading " + item_file_name + " which was published on " + date
try:
item_file = urllib2.urlopen(item)
output = open(local_file, 'wb')
# 2011-10-06 Werner Avenant - For some reason the file name changes when
# saved to disk - probably a python feature (sorry, only wrote my first line of python today)
item_file_name = os.path.basename(output.name)
output.write(item_file.read())
output.close()
print "Podcast: ", item, " downloaded to: ", local_file
# 2011-11-06 Append to m3u file
output = open(current_directory + os.sep + m3u_file, 'a')
output.write(DOWNLOAD_DIRECTORY + os.sep + channel_title + os.sep + item_file_name + "\n")
output.close()
return 'Successful Write'
except urllib2.URLError as e:
print "ERROR - Could not write item to file: ", e
return 'Write Error'
def does_database_exist(curr_loc):
db_name = "PodGrab.db"
if os.path.exists(curr_loc + os.sep + db_name):
return 1
else:
return 0
def add_mail_user(cur, conn, address):
row = (address,)
cur.execute('INSERT INTO email(address) VALUES (?)', row)
conn.commit()
def delete_mail_user(cur, conn, address):
row = (address,)
cur.execute('DELETE FROM email WHERE address = ?', row)
conn.commit()
def get_mail_users(cur, conn):
cur.execute('SELECT address FROM email')
return cur.fetchall()
def list_mail_addresses(cur, conn):
cur.execute('SELECT * from email')
result = cur.fetchall()
print "Listing mail addresses..."
for address in result:
print "Address:\t" + address[0]
def has_mail_users(cur, conn):
cur.execute('SELECT COUNT(*) FROM email')
if cur.fetchone() == "0":
return 0
else:
return 1
def mail_updates(cur, conn, mess, num_updates):
addresses = get_mail_users(cur, conn)
for address in addresses:
try:
subject_line = "PodGrab Update"
if int(num_updates) > 0:
subject_line += " - NEW updates!"
else:
subject_line += " - nothing new..."
mail('localhost', 'podgrab@' + platform.node(), address[0], subject_line, mess)
print "Successfully sent podcast updates e-mail to: " + address[0]
except smtplib.SMTPException:
traceback.print_exc()
print "Could not send podcast updates e-mail to: " + address[0]
def mail(server_url=None, sender='', to='', subject='', text=''):
headers = "From: %s\r\nTo: %s\r\nSubject: %s\r\n\r\n" % (sender, to, subject)
message = headers + text
mail_server = smtplib.SMTP(server_url)
mail_server.sendmail(sender, to, message)
mail_server.quit()
def connect_database(curr_loc):
conn = sqlite3.connect(curr_loc + os.sep + "PodGrab.db")
return conn
def setup_database(cur, conn):
cur.execute("CREATE TABLE subscriptions (channel text, feed text, last_ep text)")
cur.execute("CREATE TABLE email (address text)")
conn.commit()
def insert_subscription(cur, conn, chan, feed):
chan.replace(' ', '-')
chan.replace('---','-')
row = (chan, feed, "Thu, 01 Jan 1970 00:00:00") # Added a correctly formatted date here so we can avoid an ugly "if date == null" in update_subscription later
cur.execute('INSERT INTO subscriptions(channel, feed, last_ep) VALUES (?, ?, ?)', row)
conn.commit()
def iterate_channel(chan, today, mode, cur, conn, feed, channel_title):
global total_items
global total_size
num = 0
saved = 0
size = 0
last_ep = "NULL"
print "Iterating channel..."
if does_sub_exist(cur, conn, feed):
print "Podcast subscription exists"
else:
print "Podcast subscription is new - getting previous podcast"
insert_subscription(cur, conn, chan.getElementsByTagName('title')[0].firstChild.data, feed)
last_ep = get_last_subscription_downloaded(cur, conn, feed)
### NB NB - The logic here is that we get the "last_ep" before we enter the loop
### The result is that it allows the code to "catch up" on missed episodes because
### we never update the "last_ep" while inside the loop.
for item in chan.getElementsByTagName('item'):
try:
item_title = item.getElementsByTagName('title')[0].firstChild.data
item_date = item.getElementsByTagName('pubDate')[0].firstChild.data
item_file = item.getElementsByTagName('enclosure')[0].getAttribute('url')
item_size = item.getElementsByTagName('enclosure')[0].getAttribute('length')
item_type = item.getElementsByTagName('enclosure')[0].getAttribute('type')
struct_time_today = strptime(today, "%a, %d %b %Y %H:%M:%S")
try:
struct_time_item = strptime(fix_date(item_date), "%a, %d %b %Y %H:%M:%S")
has_error = 0
except TypeError:
has_error = 1
except ValueError:
has_error = 1
try:
struct_last_ep = strptime(last_ep, "%a, %d %b %Y %H:%M:%S")
has_error = 0
except TypeError:
has_error = 1
print "This item has a badly formatted date. Cannot download!"
except ValueError:
has_error = 1
print "This item has a badly formatted date. Cannot download!"
if not has_error:
if mktime(struct_time_item) > mktime(struct_last_ep) or mode == MODE_DOWNLOAD:
saved = write_podcast(item_file, channel_title, item_date, item_type)
if saved == 'File Exists':
print "File Existed - updating local database's Last Episode";
update_subscription(cur, conn, feed, fix_date(item_date))
if saved == 'Successful Write':
print "\nTitle: " + item_title
print "Date: " + item_date
print "File: " + item_file
print "Size: " + item_size + " bytes"
print "Type: " + item_type
update_subscription(cur, conn, feed, fix_date(item_date))
num += 1
size = size + int(item_size)
total_size += size
total_items += 1
if (mode == MODE_SUBSCRIBE): # In subscribe mode we only want 1 this loop to execute once
break;
if (num >= NUM_MAX_DOWNLOADS):
print "Maximum session download of " + str(NUM_MAX_DOWNLOADS) + " podcasts has been reached. Exiting."
break
else:
print "According to database we already have the episode dated " + item_date
break
except IndexError, e:
#traceback.print_exc()
print "This RSS item has no downloadable URL link for the podcast for '" + item_title + "'. Skipping..."
return str(num) + " podcasts totalling " + str(size) + " bytes"
def fix_date(date):
new_date = ""
split_array = date.split(' ')
for i in range(0,5):
new_date = new_date + split_array[i] + " "
return new_date.rstrip()
def does_sub_exist(cur, conn, feed):
row = (feed,)
cur.execute('SELECT COUNT (*) FROM subscriptions WHERE feed = ?', row)
return_string = str(cur.fetchone())[1]
if return_string == "0":
return 0
else:
return 1
def delete_subscription(cur, conn, url):
row = (url,)
cur.execute('DELETE FROM subscriptions WHERE feed = ?', row)
conn.commit()
def get_name_from_feed(cur, conn, url):
row = (url,)
cur.execute('SELECT channel from subscriptions WHERE feed = ?', row)
return_string = cur.fetchone()
try:
return_string = ''.join(return_string)
except TypeError:
return_string = "None"
return str(return_string)
def list_subscriptions(cur, conn):
count = 0
try:
result = cur.execute('SELECT * FROM subscriptions')
for sub in result:
print "Name:\t\t", sub[0]
print "Feed:\t\t", sub[1]
print "Last Ep:\t", sub[2], "\n"
count += 1
print str(count) + " subscriptions present"
except sqlite3.OperationalError:
print "There are no current subscriptions or there was an error"
def get_subscriptions(cur, conn):
try:
cur.execute('SELECT * FROM subscriptions')
return cur.fetchall()
except sqlite3.OperationalError:
print "There are no current subscriptions"
return null
def update_subscription(cur, conn, feed, date):
# Make sure that the date we are trying to write is newer than the last episode
# Presumes that "null" dates will be saved in DB as 1970-01-01 (unix "start" time)
existing_last_ep = get_last_subscription_downloaded(cur, conn, feed)
if mktime(strptime(existing_last_ep, "%a, %d %b %Y %H:%M:%S")) <= mktime(strptime(date, "%a, %d %b %Y %H:%M:%S")):
row = (date, feed)
cur.execute('UPDATE subscriptions SET last_ep = ? where feed = ?', row)
conn.commit()
def get_last_subscription_downloaded(cur, conn, feed):
row = (feed,)
cur.execute('SELECT last_ep FROM subscriptions WHERE feed = ?', row)
rec = cur.fetchone()
return rec[0]
if __name__ == "__main__":
main(sys.argv[1:])