forked from bebound/pixivd
/
pixiv.py
executable file
·387 lines (336 loc) · 14.2 KB
/
pixiv.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
#!/usr/bin/env python3
"""
pixiv
Usage:
pixiv.py
pixiv.py <id>...
pixiv.py -r [-d | --date=<date>]
pixiv.py -u
Arguments:
<id> user_ids
Options:
-r Download by ranking
-d <date> --date <date> Target date
-u Update exist folder
-h --help Show this screen
-v --version Show version
Examples:
pixiv.py 7210261 1980643
pixiv.py -r -d 2016-09-24
"""
import datetime
import math
import os
import queue
import re
import sys
import threading
import time
import requests
from docopt import docopt
from tqdm import tqdm
from api import PixivApi
from i18n import i18n as _
from model import PixivIllustModel
_THREADING_NUMBER = 10
_finished_download = 0
_CREATE_FOLDER_LOCK = threading.Lock()
_PROGRESS_LOCK = threading.Lock()
_SPEED_LOCK = threading.Lock()
_Global_Download = 0
_error_count = {}
_fast_mode_size = 20
_MAX_ERROR_COUNT = 5
def get_default_save_path():
current_path = os.path.dirname(os.path.abspath(sys.argv[0]))
filepath = os.path.join(current_path, 'illustrations')
if not os.path.exists(filepath):
with _CREATE_FOLDER_LOCK:
if not os.path.exists(os.path.dirname(filepath)):
os.makedirs(os.path.dirname(filepath))
os.makedirs(filepath)
return filepath
def get_speed(elapsed):
"""Get current download speed"""
with _SPEED_LOCK:
global _Global_Download
down = _Global_Download
_Global_Download = 0
speed = down / elapsed
if speed == 0:
return '%8.2f /s' % 0
units = [' B', 'KB', 'MB', 'GB', 'TB', 'PB']
unit = math.floor(math.log(speed, 1024.0))
speed /= math.pow(1024.0, unit)
return '%6.2f %s/s' % (speed, units[unit])
def print_progress(max_size):
global _finished_download
pbar = tqdm(total=max_size)
last = 0
while _finished_download != max_size:
pbar.update(_finished_download - last)
last = _finished_download
time.sleep(0.5)
pbar.update(_finished_download - last)
pbar.close()
def download_file(url, filepath):
headers = {'Referer': 'http://www.pixiv.net/'}
r = requests.get(url, headers=headers, stream=True, timeout=PixivApi.timeout)
if r.status_code == requests.codes.ok:
total_length = r.headers.get('content-length')
if total_length:
data = []
for chunk in r.iter_content(1024 * 16):
data.append(chunk)
with _SPEED_LOCK:
global _Global_Download
_Global_Download += len(chunk)
with open(filepath, 'wb') as f:
list(map(f.write, data))
else:
raise ConnectionError('\r', _('Connection error: %s') % r.status_code)
def download_threading(download_queue):
global _finished_download
while not download_queue.empty():
illustration = download_queue.get()
filepath = illustration['path']
filename = illustration['file']
url = illustration['url']
count = _error_count.get(url, 0)
if count < _MAX_ERROR_COUNT:
if not os.path.exists(filepath):
with _CREATE_FOLDER_LOCK:
if not os.path.exists(os.path.dirname(filepath)):
os.makedirs(os.path.dirname(filepath))
try:
download_file(url, filepath)
with _PROGRESS_LOCK:
_finished_download += 1
except Exception as e:
if count < _MAX_ERROR_COUNT:
print(_('%s => %s download error, retry') % (e, filename))
download_queue.put(illustration)
_error_count[url] = count + 1
else:
print(url, 'reach max retries, canceled')
with _PROGRESS_LOCK:
_finished_download += 1
download_queue.task_done()
def start_and_wait_download_threading(download_queue, count):
"""start download threading and wait till complete"""
progress_t = threading.Thread(target=print_progress, args=(count,))
progress_t.daemon = True
progress_t.start()
for i in range(_THREADING_NUMBER):
download_t = threading.Thread(target=download_threading, args=(download_queue,))
download_t.daemon = True
download_t.start()
progress_t.join()
download_queue.join()
def get_filepath(url, illustration, save_path='.', add_user_folder=False, add_rank=False):
"""return (filename,filepath)"""
if add_user_folder:
user_id = illustration.user_id
user_name = illustration.user_name
current_path = get_default_save_path()
cur_dirs = list(filter(os.path.isdir, [os.path.join(current_path, i) for i in os.listdir(current_path)]))
cur_user_ids = [os.path.basename(cur_dir).split()[0] for cur_dir in cur_dirs]
if user_id not in cur_user_ids:
dir_name = re.sub(r'[<>:"/\\|\?\*]', ' ', user_id + ' ' + user_name)
else:
dir_name = list(i for i in cur_dirs if os.path.basename(i).split()[0] == user_id)[0]
save_path = os.path.join(save_path, dir_name)
filename = url.split('/')[-1]
# name, ext = os.path.splitext(filename)
if add_rank:
# name = illustration.rank + ' - ' + name
filename = illustration.rank + ' - ' + filename
# filename = name + ' - ' + illustration.title + ext
filepath = os.path.join(save_path, filename)
return filename, filepath
def check_files(illustrations, save_path='.', add_user_folder=False, add_rank=False):
download_queue = queue.Queue()
index_list = []
count = 0
if illustrations:
last_i = -1
for index, illustration in enumerate(illustrations):
if not illustration.image_urls:
continue
elif illustration.type == 'ugoira':
continue
else:
for url in illustration.image_urls:
filename, filepath = get_filepath(url, illustration, save_path, add_user_folder, add_rank)
if os.path.exists(filepath):
continue
else:
if last_i != index:
last_i = index
index_list.append(index)
download_queue.put({'url': url, 'file': filename, 'path': filepath})
count += 1
return download_queue, count, index_list
def count_illustrations(illustrations):
return sum(len(i.image_urls) for i in illustrations)
def is_manga(illustrate):
return True if illustrate.is_manga or illustrate.type == 'manga' else False
def download_illustrations(user, data_list, save_path='.', add_user_folder=False, add_rank=False, skip_manga=False):
"""Download illustratons
Args:
user: PixivApi()
data_list: json
save_path: str, download path of the illustrations
add_user_folder: bool, whether put the illustration into user folder
add_rank: bool, add illustration rank at the beginning of filename
"""
illustrations = PixivIllustModel.from_data(data_list, user)
if skip_manga:
manga_number = sum([is_manga(i) for i in illustrations])
if manga_number:
print('skip', manga_number, 'manga')
illustrations = list(filter(lambda x: not is_manga(x), illustrations))
download_queue, count = check_files(illustrations, save_path, add_user_folder, add_rank)[0:2]
if count > 0:
print(_('Start download, total illustrations '), count)
global _finished_download, _Global_Download
_finished_download = 0
_Global_Download = 0
start_and_wait_download_threading(download_queue, count)
print()
else:
print(_('There is no new illustration need to download'))
def download_by_user_id(user, user_ids=None):
save_path = get_default_save_path()
if not user_ids:
user_ids = input(_('Input the artist\'s id:(separate with space)')).split(' ')
for user_id in user_ids:
print(_('Artists %s') % user_id)
data_list = user.get_user_illustrations(user_id)
download_illustrations(user, data_list, save_path, add_user_folder=True)
def download_by_ranking(user):
today = str(datetime.date.today())
save_path = os.path.join(get_default_save_path(), today + ' ranking')
data_list = user.get_ranking_illustrations(per_page=100, mode='daily')
download_illustrations(user, data_list, save_path, add_rank=True)
def download_by_history_ranking(user, date=''):
if not date:
date = input(_('Input the date:(eg:2015-07-10)'))
if not (re.search("^\d{4}-\d{2}-\d{2}", date)):
print(_('[invalid]'))
date = str(datetime.date.today())
save_path = os.path.join(get_default_save_path(), date + ' ranking')
data_list = user.get_ranking_illustrations(date=date, per_page=100, mode='daily')
download_illustrations(user, data_list, save_path, add_rank=True)
def artist_folder_scanner(user, user_id_list, save_path, final_list, fast):
while not user_id_list.empty():
user_info = user_id_list.get()
user_id = user_info['id']
folder = user_info['folder']
try:
per_page = 9999
if fast:
per_page = _fast_mode_size
data_list = user.get_user_illustrations(user_id, per_page=per_page)
if len(data_list) > 0:
file_path = os.path.join(save_path, folder, data_list[-1]['image_urls']['large'].split('/')[-1])
while not os.path.exists(file_path) and per_page <= len(data_list):
per_page += _fast_mode_size
data_list = user.get_user_illustrations(user_id, per_page=per_page)
file_path = os.path.join(save_path, folder, data_list[-1]['image_urls']['large'].split('/')[-1])
else:
data_list = user.get_user_illustrations(user_id, per_page=per_page)
illustrations = PixivIllustModel.from_data(data_list, user)
count, checked_list = check_files(illustrations, save_path, add_user_folder=True, add_rank=False)[1:3]
if len(sys.argv) < 2 or count:
try:
print(_('Artists %s [%s]') % (folder, count))
except UnicodeError:
print(_('Artists %s ?? [%s]') % (user_id, count))
with _PROGRESS_LOCK:
for index in checked_list:
final_list.append(data_list[index])
except Exception as e:
print(e)
user_id_list.task_done()
def update_exist(user, fast=True):
current_path = get_default_save_path()
final_list = []
user_id_list = queue.Queue()
for folder in os.listdir(current_path):
if os.path.isdir(os.path.join(current_path, folder)):
user_id = re.search('^(\d+) ', folder)
if user_id:
user_id = user_id.group(1)
user_id_list.put({'id': user_id, 'folder': folder})
for i in range(_THREADING_NUMBER):
scan_t = threading.Thread(target=artist_folder_scanner,
args=(user, user_id_list, current_path, final_list, fast,))
scan_t.daemon = True
scan_t.start()
user_id_list.join()
download_illustrations(user, final_list, current_path, add_user_folder=True)
def remove_repeat(user):
"""Delete xxxxx.img if xxxxx_p0.img exist"""
choice = input(_('Dangerous Action: continue?(y/n)'))
if choice == 'y':
illust_path = get_default_save_path()
for folder in os.listdir(illust_path):
if os.path.isdir(os.path.join(illust_path, folder)):
if re.search('^(\d+) ', folder):
path = os.path.join(illust_path, folder)
for file_name in os.listdir(path):
illustration_id = re.search('^\d+\.', file_name)
if illustration_id:
if os.path.isfile(os.path.join(path
, illustration_id.string.replace('.', '_p0.'))):
os.remove(os.path.join(path, file_name))
print('Delete', os.path.join(path, file_name))
def main():
user = PixivApi()
if len(sys.argv) > 1:
print(datetime.datetime.now().strftime('%X %x'))
ids = arguments['<id>']
is_rank = arguments['-r']
date = arguments['--date']
is_update = arguments['-u']
if ids:
download_by_user_id(user, ids)
elif is_rank:
if date:
date = date[0]
download_by_history_ranking(user, date)
else:
download_by_ranking(user)
elif is_update:
update_exist(user)
print(datetime.datetime.now().strftime('%X %x'))
else:
print(_(' Pixiv Downloader 2.4 ').center(77, '#'))
options = {
'1': download_by_user_id,
'2': download_by_ranking,
'3': download_by_history_ranking,
'4': update_exist,
'5': remove_repeat
}
while True:
print(_('Which do you want to:'))
for i in sorted(options.keys()):
print('\t %s %s' % (i, _(options[i].__name__).replace('_', ' ')))
choose = input('\t e %s \n:' % _('exit'))
if choose in [str(i) for i in range(1, len(options) + 1)]:
print((' ' + _(options[choose].__name__).replace('_', ' ') + ' ').center(60, '#') + '\n')
if choose == 4:
options[choose](user, False)
else:
options[choose](user)
print('\n' + (' ' + _(options[choose].__name__).replace('_', ' ') + _(' finished ')).center(60,
'#') + '\n')
elif choose == 'e':
break
else:
print(_('Wrong input!'))
if __name__ == '__main__':
arguments = docopt(__doc__, version='pixiv 2.4')
sys.exit(main())