def main():
from mylib.osutil import ensure_sigint_signal
ensure_sigint_signal()
ap = argument_parser()
args = ap.parse_args()
try:
func = args.func
except AttributeError:
func = cmd_mode_func
func(args)
#!/usr/bin/env python
import sys
import logging
from mylib.hentai import HentaiCafeKit
from mylib.misc import LOG_FMT_MESSAGE_ONLY
from mylib.osutil import ensure_sigint_signal
logging.basicConfig(level=logging.INFO, format=LOG_FMT_MESSAGE_ONLY)
if __name__ == '__main__':
ensure_sigint_signal()
uri = sys.argv[1]
if len(sys.argv) >= 3:
hc = HentaiCafeKit(int(sys.argv[2]))
else:
hc = HentaiCafeKit(5)
hc.save_entry_to_cbz(uri)
def main(url: str = None):
ensure_sigint_signal()
args = parse_args()
# Get verbose level from args
if args.verbose:
lvl = logging.DEBUG
fmt = LOG_FMT
else:
lvl = logging.INFO
fmt = LOG_FMT_MESSAGE_ONLY
logging.basicConfig(
stream=sys.stderr,
level=lvl,
format=fmt,
)
# Get URL from args
if url:
album_url = url
else:
album_url = args.url
if re.search(r'photosmasters\.com/thumbnails\.php\?album=', album_url):
album_url = re.sub(r'(^.*?album=\d*).*$', r'\1', album_url)
else:
_logger.warning('NOT A PHOTOSMASTERS.COM URL!')
sys.exit()
db['url'] = album_url
global server
server, _ = url_split(album_url)
# Parse album page
album_soup, _ = soup(album_url)
if album_soup('div', class_='cpg_message_warning'):
_logger.warning('ALBUM NOT EXISTS!')
sys.exit()
album_title = album_soup.title.contents[0]
album_name = re.sub(r'^(.*) - photosmasters\.com', r'\1', album_title)
album_name = re.sub(r'^.* \((.*)\)', r'\1', album_name)
album_name = album_name.strip()
db['name'] = album_name
_logger.info(album_title)
# Get album directory to store downloaded photos
album_id = get_query_dict(album_url)['album']
album_dir = os.path.join(args.dir, 'photosmasters',
'{} - {}'.format(album_id, album_name))
if not os.path.exists(album_dir):
os.makedirs(album_dir)
_logger.info('{} -->> {}'.format(album_url, album_dir))
# Meta
info_file = os.path.join(album_dir, INFO_FILE)
db_file = os.path.join(album_dir, DB_FILE)
restore_db(db_file)
totals = album_soup('td', class_='tableh1')[0].contents[0]
_, total_images, _, _, total_pages = totals.split()
global stat
stat = {
'dd': album_dir, # download directory
'at': album_title, # title
'ti': int(total_images), # total images
'tp': int(total_pages), # total pages
'li': 0, # last image
'lp': 0, # last page
}
display_stat()
# Let's roll out
try:
for _ in range(stat['tp']):
stat['lp'] += 1
page_url = '{}&page={}'.format(album_url, stat['lp'])
_logger.debug('Page: {}'.format(page_url))
page_soup, _ = soup(page_url)
thumbnails = page_soup('td', class_='thumbnails')
for thumb in thumbnails:
if not thumb.td:
break
stat['li'] += 1
thumb_title = thumb.td.span.contents[0]
photo_url = server + '/' + thumb.a['href'].replace(
'#top_display_media', '&fullsize=1')
_logger.debug('Photo: {}'.format(photo_url))
photo_id = get_query_dict(photo_url)['pid']
# Go!
th = Thread(target=download,
args=(photo_id, photo_url, thumb_title))
while len(thl) >= args.threads:
for t in thl:
if not t.is_alive():
thl.remove(t)
sleep(0.1)
display_stat()
th.start()
thl.append(th)
sleep(0.1)
except KeyboardInterrupt:
_logger.info('Wait: {} threads to finish.'.format(len(thl)))
sys.exit(ExitCode.CTRL_C)
finally:
for th in thl:
th.reunion()
save_db(db_file)
save_info(info_file)