def login(username, password):
csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
if os.getenv('DEBUG'):
logger.info('Getting CSRF token ...')
if os.getenv('DEBUG'):
logger.info('CSRF token is {}'.format(csrf_token))
login_dict = {
'csrfmiddlewaretoken': csrf_token,
'username_or_email': username,
'password': password,
}
resp = request('post', url=constant.LOGIN_URL, data=login_dict)
if 'You\'re loading pages way too quickly.' in resp.text:
csrf_token = _get_csrf_token(resp.text)
resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
if 'Invalid username/email or password' in resp.text:
logger.error('Login failed, please check your username and password')
exit(1)
if 'You\'re loading pages way too quickly.' in resp.text:
logger.error('You meet challenge insistently, please submit a issue'
' at https://github.com/RicterZ/nhentai/issues')
exit(2)
def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
try:
import img2pdf
"""Write images to a PDF file using img2pdf."""
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
pdf_filename = os.path.join(
os.path.join(doujinshi_dir, '..'),
'{}.pdf'.format(doujinshi_obj.filename))
else:
pdf_filename = './doujinshi.pdf'
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
logger.info('Writing PDF file to path: {}'.format(pdf_filename))
with open(pdf_filename, 'wb') as pdf_f:
full_path_list = ([
os.path.join(doujinshi_dir, image) for image in file_list
])
pdf_f.write(img2pdf.convert(full_path_list))
if rm_origin_dir:
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(
15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
except ImportError:
logger.error("Please install img2pdf package by using pip.")
def tag_parser(tag_name, max_page=1):
result = []
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
for p in range(1, max_page + 1):
logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
response = request('get', url='%s/%s?page=%d' % (constant.TAG_URL, tag_name, p)).content
html = BeautifulSoup(response, 'html.parser')
doujinshi_items = html.find_all('div', attrs={'class': 'gallery'})
if not doujinshi_items:
logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
for i in doujinshi_items:
doujinshi_id = i.a.attrs['href'].strip('/g')
doujinshi_title = i.a.text.strip()
doujinshi_title = doujinshi_title if len(doujinshi_title) < 85 else doujinshi_title[:82] + '...'
result.append({'title': doujinshi_title, 'id': doujinshi_id})
if not result:
logger.warn('No results for tag \'{}\''.format(tag_name))
return result
def _download(self, url, folder='', filename='', retried=False):
logger.info('Start downloading: {0} ...'.format(url))
filename = filename if filename else os.path.basename(
urlparse(url).path)
base_filename, extension = os.path.splitext(filename)
try:
with open(os.path.join(folder,
base_filename.zfill(3) + extension),
"wb") as f:
response = request('get',
url,
stream=True,
timeout=self.timeout)
length = response.headers.get('content-length')
if length is None:
f.write(response.content)
else:
for chunk in response.iter_content(2048):
f.write(chunk)
except requests.HTTPError as e:
if not retried:
logger.error('Error: {0}, retrying'.format(str(e)))
return self._download(url=url,
folder=folder,
filename=filename,
retried=True)
else:
return None
except Exception as e:
logger.critical(str(e))
return None
return url
def tag_parser(tag_name, max_page=1):
result = []
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
for p in range(1, max_page + 1):
logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(
p, tag_name))
response = request('get',
url='%s/%s?page=%d' %
(constant.TAG_URL, tag_name, p)).content
html = BeautifulSoup(response, 'html.parser')
doujinshi_items = html.find_all('div', attrs={'class': 'gallery'})
if not doujinshi_items:
logger.error(
'Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
for i in doujinshi_items:
doujinshi_id = i.a.attrs['href'].strip('/g')
doujinshi_title = i.a.text.strip()
doujinshi_title = doujinshi_title if len(
doujinshi_title) < 85 else doujinshi_title[:82] + '...'
result.append({'title': doujinshi_title, 'id': doujinshi_id})
if not result:
logger.warn('No results for tag \'{}\''.format(tag_name))
return result
def login(username, password):
csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
if os.getenv('DEBUG'):
logger.info('Getting CSRF token ...')
if os.getenv('DEBUG'):
logger.info('CSRF token is {}'.format(csrf_token))
login_dict = {
'csrfmiddlewaretoken': csrf_token,
'username_or_email': username,
'password': password,
}
resp = request('post', url=constant.LOGIN_URL, data=login_dict)
if 'You\'re loading pages way too quickly.' in resp.text:
csrf_token = _get_csrf_token(resp.text)
resp = request('post',
url=resp.url,
data={
'csrfmiddlewaretoken': csrf_token,
'next': '/'
})
if 'Invalid username/email or password' in resp.text:
logger.error('Login failed, please check your username and password')
exit(1)
if 'You\'re loading pages way too quickly.' in resp.text:
logger.error('You meet challenge insistently, please submit a issue'
' at https://github.com/RicterZ/nhentai/issues')
exit(2)
def check_cookie():
response = request('get', constant.BASE_URL).text
username = re.findall('"/users/\d+/(.*?)"', response)
if not username:
logger.error('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
else:
logger.info('Login successfully! Your username: {}'.format(username[0]))
def login(username, password):
logger.warning(
'This feature is deprecated, please use --cookie to set your cookie.')
csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
if os.getenv('DEBUG'):
logger.info('Getting CSRF token ...')
if os.getenv('DEBUG'):
logger.info('CSRF token is {}'.format(csrf_token))
login_dict = {
'csrfmiddlewaretoken': csrf_token,
'username_or_email': username,
'password': password,
}
resp = request('post', url=constant.LOGIN_URL, data=login_dict)
if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
csrf_token = _get_csrf_token(resp.text)
resp = request('post',
url=resp.url,
data={
'csrfmiddlewaretoken': csrf_token,
'next': '/'
})
if 'Invalid username/email or password' in resp.text:
logger.error('Login failed, please check your username and password')
exit(1)
if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
logger.error(
'Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
exit(2)
def load_config():
if not os.path.exists(constant.NHENTAI_CONFIG_FILE):
return
try:
with open(constant.NHENTAI_CONFIG_FILE, 'r') as f:
constant.CONFIG = json.load(f)
except json.JSONDecodeError:
logger.error('Failed to load config file.')
write_config()
def check_cookie():
response = request('get', constant.BASE_URL)
if response.status_code == 503 and 'cf-browser-verification' in response.text:
logger.error(
'Blocked by Cloudflare captcha, please set your cookie and useragent'
)
exit(-1)
username = re.findall('"/users/\d+/(.*?)"', response.text)
if not username:
logger.warning(
'Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie'
)
else:
logger.info('Login successfully! Your username: {}'.format(
username[0]))
def login_parser():
html = BeautifulSoup(
request('get', constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
if not count:
logger.error(
"Can't get your number of favorited doujins. Did the login failed?"
)
return
count = int(count.text.strip('(').strip(')').replace(',', ''))
if count == 0:
logger.warning('No favorites found')
return []
pages = int(count / 25)
if pages:
pages += 1 if count % (25 * pages) else 0
else:
pages = 1
logger.info('You have %d favorites in %d pages.' % (count, pages))
if os.getenv('DEBUG'):
pages = 1
ret = []
doujinshi_id = re.compile('data-id="([\d]+)"')
def _callback(request, result):
ret.append(result)
thread_pool = threadpool.ThreadPool(5)
for page in range(1, pages + 1):
try:
logger.info('Getting doujinshi ids of page %d' % page)
resp = request('get', constant.FAV_URL + '?page=%d' % page).text
ids = doujinshi_id.findall(resp)
requests_ = threadpool.makeRequests(doujinshi_parser, ids,
_callback)
[thread_pool.putRequest(req) for req in requests_]
thread_pool.wait()
except Exception as e:
logger.error('Error: %s, continue', str(e))
return ret
def tag_parser(tag_name, sorting='date', max_page=1, index=0):
result = []
tag_name = tag_name.lower()
if ',' in tag_name:
tag_name = [i.strip().replace(' ', '-') for i in tag_name.split(',')]
else:
tag_name = tag_name.strip().replace(' ', '-')
if sorting == 'date':
sorting = ''
for p in range(1, max_page + 1):
if sys.version_info >= (3, 0, 0):
unicode_ = str
else:
unicode_ = unicode
if isinstance(tag_name, (str, unicode_)):
logger.debug(
'Fetching page {0} for doujinshi with tag \'{1}\''.format(
p, tag_name))
response = request(
'get',
url='%s/%s/%s?page=%d' %
(constant.TAG_URL[index], tag_name, sorting, p)).content
result += _get_title_and_id(response)
else:
for i in tag_name:
logger.debug(
'Fetching page {0} for doujinshi with tag \'{1}\''.format(
p, i))
response = request(
'get',
url='%s/%s/%s?page=%d' %
(constant.TAG_URL[index], i, sorting, p)).content
result += _get_title_and_id(response)
if not result:
logger.error(
'Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
if not result:
logger.warn('No results for tag \'{}\''.format(tag_name))
return result
def login_parser():
html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
if not count:
logger.error("Can't get your number of favorited doujins. Did the login failed?")
return
count = int(count.text.strip('(').strip(')').replace(',', ''))
if count == 0:
logger.warning('No favorites found')
return []
pages = int(count / 25)
if pages:
pages += 1 if count % (25 * pages) else 0
else:
pages = 1
logger.info('You have %d favorites in %d pages.' % (count, pages))
if os.getenv('DEBUG'):
pages = 1
ret = []
doujinshi_id = re.compile('data-id="([\d]+)"')
def _callback(request, result):
ret.append(result)
thread_pool = threadpool.ThreadPool(5)
for page in range(1, pages + 1):
try:
logger.info('Getting doujinshi ids of page %d' % page)
resp = request('get', constant.FAV_URL + '?page=%d' % page).text
ids = doujinshi_id.findall(resp)
requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
[thread_pool.putRequest(req) for req in requests_]
thread_pool.wait()
except Exception as e:
logger.error('Error: %s, continue', str(e))
return ret
def favorites_parser(page=None):
result = []
html = BeautifulSoup(
request('get', constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
if not count:
logger.error(
"Can't get your number of favorited doujins. Did the login failed?"
)
return []
count = int(count.text.strip('(').strip(')').replace(',', ''))
if count == 0:
logger.warning('No favorites found')
return []
pages = int(count / 25)
if page:
page_range_list = page
else:
if pages:
pages += 1 if count % (25 * pages) else 0
else:
pages = 1
logger.info('You have %d favorites in %d pages.' % (count, pages))
if os.getenv('DEBUG'):
pages = 1
page_range_list = range(1, pages + 1)
for page in page_range_list:
try:
logger.info('Getting doujinshi ids of page %d' % page)
resp = request('get', constant.FAV_URL + '?page=%d' % page).content
result.extend(_get_title_and_id(resp))
except Exception as e:
logger.error('Error: %s, continue', str(e))
return result
def tag_guessing(tag_name):
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
logger.info('Trying to get tag_id of tag \'{0}\''.format(tag_name))
response = request('get', url='%s/%s' % (constant.TAG_URL, tag_name)).content
html = BeautifulSoup(response, 'html.parser')
first_item = html.find('div', attrs={'class': 'gallery'})
if not first_item:
logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
doujinshi_id = re.findall('(\d+)', first_item.a.attrs['href'])
if not doujinshi_id:
logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
ret = doujinshi_parser(doujinshi_id[0])
if 'tag' in ret and tag_name in ret['tag']:
tag_id = ret['tag'][tag_name]
logger.info('Tag id of tag \'{0}\' is {1}'.format(tag_name, tag_id))
else:
logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
return tag_id
def tag_parser(tag_name, max_page=1):
result = []
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
for p in range(1, max_page + 1):
logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(
p, tag_name))
response = request('get',
url='%s/%s?page=%d' %
(constant.TAG_URL, tag_name, p)).content
result = _get_title_and_id(response)
if not result:
logger.error(
'Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
return
if not result:
logger.warn('No results for tag \'{}\''.format(tag_name))
return result
def login_parser(username, password):
s = requests.Session()
s.proxies = constant.PROXY
s.verify = False
s.headers.update({'Referer': constant.LOGIN_URL})
s.get(constant.LOGIN_URL)
content = s.get(constant.LOGIN_URL).content
html = BeautifulSoup(content, 'html.parser')
csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
if not csrf_token_elem:
raise Exception('Cannot find csrf token to login')
csrf_token = csrf_token_elem.attrs['value']
login_dict = {
'csrfmiddlewaretoken': csrf_token,
'username_or_email': username,
'password': password,
}
resp = s.post(constant.LOGIN_URL, data=login_dict)
if 'Invalid username (or email) or password' in resp.text:
logger.error('Login failed, please check your username and password')
exit(1)
html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
if not count:
logger.error('Cannot get count of your favorites, maybe login failed.')
count = int(count.text.strip('(').strip(')'))
pages = count / 25
pages += 1 if count % (25 * pages) else 0
logger.info('Your have %d favorites in %d pages.' % (count, pages))
if os.getenv('DEBUG'):
pages = 1
ret = []
doujinshi_id = re.compile('data-id="([\d]+)"')
def _callback(request, result):
ret.append(result)
thread_pool = threadpool.ThreadPool(5)
for page in range(1, pages+1):
try:
logger.info('Getting doujinshi id of page %d' % page)
resp = s.get(constant.FAV_URL + '?page=%d' % page).content
ids = doujinshi_id.findall(resp)
requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
[thread_pool.putRequest(req) for req in requests_]
thread_pool.wait()
except Exception as e:
logger.error('Error: %s, continue', str(e))
return ret
def page_range_parser(page_range, max_page_num):
pages = set()
ranges = str.split(page_range, ',')
for range_str in ranges:
idx = range_str.find('-')
if idx == -1:
try:
page = int(range_str)
if page <= max_page_num:
pages.add(page)
except ValueError:
logger.error('page range({0}) is not valid'.format(page_range))
else:
try:
left = int(range_str[:idx])
right = int(range_str[idx + 1:])
if right > max_page_num:
right = max_page_num
for page in range(left, right + 1):
pages.add(page)
except ValueError:
logger.error('page range({0}) is not valid'.format(page_range))
return list(pages)
def cmd_parser():
parser = OptionParser()
parser.add_option('--download',
dest='is_download',
action='store_true',
help='download doujinshi or not')
parser.add_option('--id',
type='int',
dest='id',
action='store',
help='doujinshi id of nhentai')
parser.add_option('--ids',
type='str',
dest='ids',
action='store',
help='doujinshi id set, e.g. 1,2,3')
parser.add_option('--search',
type='string',
dest='keyword',
action='store',
help='keyword searched')
parser.add_option('--page',
type='int',
dest='page',
action='store',
default=1,
help='page number of search result')
parser.add_option('--path',
type='string',
dest='saved_path',
action='store',
default='',
help='path which save the doujinshi')
parser.add_option('--threads',
'-t',
type='int',
dest='threads',
action='store',
default=5,
help='thread count of download doujinshi')
parser.add_option('--timeout',
type='int',
dest='timeout',
action='store',
default=30,
help='timeout of download doujinshi')
parser.add_option('--proxy',
type='string',
dest='proxy',
action='store',
default='',
help='use proxy, example: http://127.0.0.1:1080')
args, _ = parser.parse_args()
if args.ids:
_ = map(lambda id: id.strip(), args.ids.split(','))
args.ids = set(map(int, filter(lambda id: id.isdigit(), _)))
if args.is_download and not args.id and not args.ids and not args.keyword:
logger.critical('Doujinshi id/ids is required for downloading')
parser.print_help()
exit(0)
if args.id:
args.ids = (args.id, ) if not args.ids else args.ids
if not args.keyword and not args.ids:
parser.print_help()
exit(0)
if args.threads <= 0:
args.threads = 1
elif args.threads > 10:
logger.critical('Maximum number of used threads is 10')
exit(0)
if args.proxy:
import urlparse
proxy_url = urlparse.urlparse(args.proxy)
if proxy_url.scheme not in ('http', 'https'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(
proxy_url.scheme))
else:
constant.PROXY = {proxy_url.scheme: args.proxy}
return args
def main():
banner()
if sys.version_info < (3, 0, 0):
logger.error('nhentai now only support Python 3.x')
exit(1)
options = cmd_parser()
logger.info('Using mirror: {0}'.format(BASE_URL))
# CONFIG['proxy'] will be changed after cmd_parser()
if constant.CONFIG['proxy']['http']:
logger.info('Using proxy: {0}'.format(
constant.CONFIG['proxy']['http']))
if not constant.CONFIG['template']:
constant.CONFIG['template'] = 'default'
logger.info('Using viewer template "{}"'.format(
constant.CONFIG['template']))
# check your cookie
check_cookie()
doujinshis = []
doujinshi_ids = []
doujinshi_list = []
page_list = paging(options.page)
if options.favorites:
if not options.is_download:
logger.warning('You do not specify --download option')
doujinshis = favorites_parser(page=page_list)
elif options.keyword:
if constant.CONFIG['language']:
logger.info('Using default language: {0}'.format(
constant.CONFIG['language']))
options.keyword += ' language:{}'.format(
constant.CONFIG['language'])
doujinshis = search_parser(options.keyword,
sorting=options.sorting,
page=page_list,
is_page_all=options.page_all)
elif not doujinshi_ids:
doujinshi_ids = options.id
print_doujinshi(doujinshis)
if options.is_download and doujinshis:
doujinshi_ids = [i['id'] for i in doujinshis]
if options.is_save_download_history:
with DB() as db:
data = map(int, db.get_all())
doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
if doujinshi_ids:
for i, id_ in enumerate(doujinshi_ids):
if options.delay:
time.sleep(options.delay)
doujinshi_info = doujinshi_parser(id_)
if doujinshi_info:
doujinshi_list.append(
Doujinshi(name_format=options.name_format,
**doujinshi_info))
if (i + 1) % 10 == 0:
logger.info('Progress: %d / %d' % (i + 1, len(doujinshi_ids)))
if not options.is_show:
downloader = Downloader(path=options.output_dir,
size=options.threads,
timeout=options.timeout,
delay=options.delay)
for doujinshi in doujinshi_list:
if not options.dryrun:
doujinshi.downloader = downloader
doujinshi.download()
doujinshi.downloader = downloader
doujinshi.download()
if options.generate_metadata:
table = doujinshi.table
generate_metadata_file(options.output_dir, table, doujinshi)
if options.is_save_download_history:
with DB() as db:
db.add_one(doujinshi.id)
if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
generate_html(options.output_dir,
doujinshi,
template=constant.CONFIG['template'])
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi,
options.rm_origin_dir)
elif options.is_pdf:
generate_pdf(options.output_dir, doujinshi,
options.rm_origin_dir)
if options.main_viewer:
generate_main_html(options.output_dir)
if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
def cmd_parser():
parser = OptionParser(
'\n nhentai --search [keyword] --download'
'\n NHENTAI=http://h.loli.club nhentai --id [ID ...]'
'\n nhentai --file [filename]'
'\n\nEnvironment Variable:\n'
' NHENTAI nhentai mirror url')
# operation options
parser.add_option('--download',
'-D',
dest='is_download',
action='store_true',
help='download doujinshi (for search results)')
parser.add_option('--show',
'-S',
dest='is_show',
action='store_true',
help='just show the doujinshi information')
# doujinshi options
parser.add_option('--id',
type='string',
dest='id',
action='store',
help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--search',
'-s',
type='string',
dest='keyword',
action='store',
help='search doujinshi by keyword')
parser.add_option('--tag',
type='string',
dest='tag',
action='store',
help='download doujinshi by tag')
parser.add_option('--artist',
type='string',
dest='artist',
action='store',
help='download doujinshi by artist')
parser.add_option('--character',
type='string',
dest='character',
action='store',
help='download doujinshi by character')
parser.add_option('--parody',
type='string',
dest='parody',
action='store',
help='download doujinshi by parody')
parser.add_option('--group',
type='string',
dest='group',
action='store',
help='download doujinshi by group')
parser.add_option('--language',
type='string',
dest='language',
action='store',
help='download doujinshi by language')
parser.add_option('--favorites',
'-F',
action='store_true',
dest='favorites',
help='list or download your favorites.')
# page options
parser.add_option('--page',
type='int',
dest='page',
action='store',
default=1,
help='page number of search results')
parser.add_option(
'--max-page',
type='int',
dest='max_page',
action='store',
default=1,
help='The max page when recursive download tagged doujinshi')
parser.add_option('--page-range',
type='string',
dest='page_range',
action='store',
help='page range of favorites. e.g. 1,2-5,14')
parser.add_option('--sorting',
dest='sorting',
action='store',
default='date',
help='sorting of doujinshi (date / popular)',
choices=['date', 'popular'])
# download options
parser.add_option('--output',
'-o',
type='string',
dest='output_dir',
action='store',
default='',
help='output dir')
parser.add_option('--threads',
'-t',
type='int',
dest='threads',
action='store',
default=5,
help='thread count for downloading doujinshi')
parser.add_option('--timeout',
'-T',
type='int',
dest='timeout',
action='store',
default=30,
help='timeout for downloading doujinshi')
parser.add_option('--delay',
'-d',
type='int',
dest='delay',
action='store',
default=0,
help='slow down between downloading every doujinshi')
parser.add_option(
'--proxy',
'-p',
type='string',
dest='proxy',
action='store',
default='',
help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
parser.add_option('--file',
'-f',
type='string',
dest='file',
action='store',
help='read gallery IDs from file.')
parser.add_option('--format',
type='string',
dest='name_format',
action='store',
help='format the saved folder name',
default='[%i][%a][%t]')
# generate options
parser.add_option('--html',
dest='html_viewer',
action='store_true',
help='generate a html viewer at current directory')
parser.add_option('--no-html',
dest='is_nohtml',
action='store_true',
help='don\'t generate HTML after downloading')
parser.add_option(
'--gen-main',
dest='main_viewer',
action='store_true',
help='generate a main viewer contain all the doujin in the folder')
parser.add_option('--cbz',
'-C',
dest='is_cbz',
action='store_true',
help='generate Comic Book CBZ File')
parser.add_option(
'--comic-info',
dest='write_comic_info',
action='store_true',
help='when generating Comic Book CBZ File, also write ComicInfo.xml')
parser.add_option(
'--rm-origin-dir',
dest='rm_origin_dir',
action='store_true',
default=False,
help='remove downloaded doujinshi dir when generated CBZ file.')
# nhentai options
parser.add_option('--cookie',
type='str',
dest='cookie',
action='store',
help='set cookie of nhentai to bypass Google recaptcha')
parser.add_option(
'--save-download-history',
dest='is_save_download_history',
action='store_true',
default=False,
help=
'save downloaded doujinshis, whose will be skipped if you re-download them'
)
parser.add_option('--clean-download-history',
action='store_true',
default=False,
dest='clean_download_history',
help='clean download history')
try:
sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
print()
except (NameError, TypeError):
pass
except UnicodeDecodeError:
exit(0)
args, _ = parser.parse_args(sys.argv[1:])
if args.html_viewer:
generate_html()
exit(0)
if args.main_viewer and not args.id and not args.keyword and \
not args.tag and not args.artist and not args.character and \
not args.parody and not args.group and not args.language and not args.favorites:
generate_main_html()
exit(0)
if args.clean_download_history:
with DB() as db:
db.clean_all()
logger.info('Download history cleaned.')
exit(0)
if os.path.exists(constant.NHENTAI_COOKIE):
with open(constant.NHENTAI_COOKIE, 'r') as f:
constant.COOKIE = f.read()
if args.cookie:
try:
if not os.path.exists(constant.NHENTAI_HOME):
os.mkdir(constant.NHENTAI_HOME)
with open(constant.NHENTAI_COOKIE, 'w') as f:
f.write(args.cookie)
except Exception as e:
logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
exit(1)
logger.info('Cookie saved.')
exit(0)
if os.path.exists(constant.NHENTAI_PROXY):
with open(constant.NHENTAI_PROXY, 'r') as f:
link = f.read()
constant.PROXY = {'http': link, 'https': link}
if args.proxy:
try:
if not os.path.exists(constant.NHENTAI_HOME):
os.mkdir(constant.NHENTAI_HOME)
proxy_url = urlparse(args.proxy)
if proxy_url.scheme not in ('http', 'https'):
logger.error(
'Invalid protocol \'{0}\' of proxy, ignored'.format(
proxy_url.scheme))
else:
with open(constant.NHENTAI_PROXY, 'w') as f:
f.write(args.proxy)
except Exception as e:
logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
exit(1)
logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
exit(0)
if args.favorites:
if not constant.COOKIE:
logger.warning(
'Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.'
)
exit(1)
if args.id:
_ = [i.strip() for i in args.id.split(',')]
args.id = set(int(i) for i in _ if i.isdigit())
if args.file:
with open(args.file, 'r') as f:
_ = [i.strip() for i in f.readlines()]
args.id = set(int(i) for i in _ if i.isdigit())
if (args.is_download or args.is_show) and not args.id and not args.keyword and \
not args.tag and not args.artist and not args.character and \
not args.parody and not args.group and not args.language and not args.favorites:
logger.critical('Doujinshi id(s) are required for downloading')
parser.print_help()
exit(1)
if not args.keyword and not args.id and not args.tag and not args.artist and \
not args.character and not args.parody and not args.group and not args.language and not args.favorites:
parser.print_help()
exit(1)
if args.threads <= 0:
args.threads = 1
elif args.threads > 15:
logger.critical('Maximum number of used threads is 15')
exit(1)
return args
def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Quit.')
exit(1)
def cmd_parser():
load_config()
parser = OptionParser(
'\n nhentai --search [keyword] --download'
'\n NHENTAI=http://h.loli.club nhentai --id [ID ...]'
'\n nhentai --file [filename]'
'\n\nEnvironment Variable:\n'
' NHENTAI nhentai mirror url')
# operation options
parser.add_option('--download',
'-D',
dest='is_download',
action='store_true',
help='download doujinshi (for search results)')
parser.add_option('--show',
'-S',
dest='is_show',
action='store_true',
help='just show the doujinshi information')
# doujinshi options
parser.add_option('--id',
type='string',
dest='id',
action='store',
help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--search',
'-s',
type='string',
dest='keyword',
action='store',
help='search doujinshi by keyword')
parser.add_option('--favorites',
'-F',
action='store_true',
dest='favorites',
help='list or download your favorites.')
# page options
parser.add_option('--page-all',
dest='page_all',
action='store_true',
default=False,
help='all search results')
parser.add_option('--page',
'--page-range',
type='string',
dest='page',
action='store',
default='',
help='page number of search results. e.g. 1,2-5,14')
parser.add_option(
'--sorting',
dest='sorting',
action='store',
default='recent',
help='sorting of doujinshi (recent / popular / popular-[today|week])',
choices=['recent', 'popular', 'popular-today', 'popular-week'])
# download options
parser.add_option('--output',
'-o',
type='string',
dest='output_dir',
action='store',
default='./',
help='output dir')
parser.add_option('--threads',
'-t',
type='int',
dest='threads',
action='store',
default=5,
help='thread count for downloading doujinshi')
parser.add_option('--timeout',
'-T',
type='int',
dest='timeout',
action='store',
default=30,
help='timeout for downloading doujinshi')
parser.add_option('--delay',
'-d',
type='int',
dest='delay',
action='store',
default=0,
help='slow down between downloading every doujinshi')
parser.add_option(
'--proxy',
type='string',
dest='proxy',
action='store',
default='',
help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
parser.add_option('--file',
'-f',
type='string',
dest='file',
action='store',
help='read gallery IDs from file.')
parser.add_option('--format',
type='string',
dest='name_format',
action='store',
help='format the saved folder name',
default='[%i][%a][%t]')
# generate options
parser.add_option('--html',
dest='html_viewer',
action='store_true',
help='generate a html viewer at current directory')
parser.add_option('--no-html',
dest='is_nohtml',
action='store_true',
help='don\'t generate HTML after downloading')
parser.add_option(
'--gen-main',
dest='main_viewer',
action='store_true',
help='generate a main viewer contain all the doujin in the folder')
parser.add_option('--cbz',
'-C',
dest='is_cbz',
action='store_true',
help='generate Comic Book CBZ File')
parser.add_option('--pdf',
'-P',
dest='is_pdf',
action='store_true',
help='generate PDF file')
parser.add_option(
'--rm-origin-dir',
dest='rm_origin_dir',
action='store_true',
default=False,
help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
# nhentai options
parser.add_option('--cookie',
type='str',
dest='cookie',
action='store',
help='set cookie of nhentai to bypass Google recaptcha')
parser.add_option('--language',
type='str',
dest='language',
action='store',
help='set default language to parse doujinshis')
parser.add_option('--clean-language',
dest='clean_language',
action='store_true',
default=False,
help='set DEFAULT as language to parse doujinshis')
parser.add_option(
'--save-download-history',
dest='is_save_download_history',
action='store_true',
default=False,
help=
'save downloaded doujinshis, whose will be skipped if you re-download them'
)
parser.add_option('--clean-download-history',
action='store_true',
default=False,
dest='clean_download_history',
help='clean download history')
try:
sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
print()
except (NameError, TypeError):
pass
except UnicodeDecodeError:
exit(0)
args, _ = parser.parse_args(sys.argv[1:])
if args.html_viewer:
generate_html()
exit(0)
if args.main_viewer and not args.id and not args.keyword and not args.favorites:
generate_main_html()
exit(0)
if args.clean_download_history:
with DB() as db:
db.clean_all()
logger.info('Download history cleaned.')
exit(0)
# --- set config ---
if args.cookie is not None:
constant.CONFIG['cookie'] = args.cookie
logger.info('Cookie saved.')
write_config()
exit(0)
if args.language is not None:
constant.CONFIG['language'] = args.language
logger.info('Default language now set to \'{0}\''.format(
args.language))
write_config()
exit(0)
# TODO: search without language
if args.proxy:
proxy_url = urlparse(args.proxy)
if not args.proxy == '' and proxy_url.scheme not in ('http', 'https'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(
proxy_url.scheme))
exit(0)
else:
constant.CONFIG['proxy'] = {
'http': args.proxy,
'https': args.proxy,
}
logger.info('Proxy now set to \'{0}\'.'.format(args.proxy))
write_config()
exit(0)
# --- end set config ---
if args.favorites:
if not constant.CONFIG['cookie']:
logger.warning(
'Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.'
)
exit(1)
if args.id:
_ = [i.strip() for i in args.id.split(',')]
args.id = set(int(i) for i in _ if i.isdigit())
if args.file:
with open(args.file, 'r') as f:
_ = [i.strip() for i in f.readlines()]
args.id = set(int(i) for i in _ if i.isdigit())
if (args.is_download or args.is_show
) and not args.id and not args.keyword and not args.favorites:
logger.critical('Doujinshi id(s) are required for downloading')
parser.print_help()
exit(1)
if not args.keyword and not args.id and not args.favorites:
parser.print_help()
exit(1)
if args.threads <= 0:
args.threads = 1
elif args.threads > 15:
logger.critical('Maximum number of used threads is 15')
exit(1)
return args
def cmd_parser():
parser = OptionParser(
'\n nhentai --search [keyword] --download'
'\n NHENTAI=http://h.loli.club nhentai --id [ID ...]'
'\n\nEnvironment Variable:\n'
' NHENTAI nhentai mirror url')
parser.add_option('--download',
dest='is_download',
action='store_true',
help='download doujinshi (for search results)')
parser.add_option('--show-info',
dest='is_show',
action='store_true',
help='just show the doujinshi information')
parser.add_option('--id',
type='string',
dest='id',
action='store',
help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--search',
type='string',
dest='keyword',
action='store',
help='search doujinshi by keyword')
parser.add_option('--page',
type='int',
dest='page',
action='store',
default=1,
help='page number of search results')
parser.add_option('--tag',
type='string',
dest='tag',
action='store',
help='download doujinshi by tag')
parser.add_option(
'--max-page',
type='int',
dest='max_page',
action='store',
default=1,
help='The max page when recursive download tagged doujinshi')
parser.add_option('--output',
type='string',
dest='output_dir',
action='store',
default='',
help='output dir')
parser.add_option('--threads',
'-t',
type='int',
dest='threads',
action='store',
default=5,
help='thread count for downloading doujinshi')
parser.add_option('--timeout',
type='int',
dest='timeout',
action='store',
default=30,
help='timeout for downloading doujinshi')
parser.add_option('--proxy',
type='string',
dest='proxy',
action='store',
default='',
help='uses a proxy, for example: http://127.0.0.1:1080')
parser.add_option('--html',
dest='html_viewer',
action='store_true',
help='generate a html viewer at current directory')
parser.add_option('--login',
'-l',
type='str',
dest='login',
action='store',
help='username:password pair of nhentai account')
parser.add_option('--nohtml',
dest='is_nohtml',
action='store_true',
help='Don\'t generate HTML')
parser.add_option('--cbz',
dest='is_cbz',
action='store_true',
help='Generate Comic Book CBZ File')
parser.add_option(
'--rm-origin-dir',
dest='rm_origin_dir',
action='store_true',
default=False,
help='Remove downloaded doujinshi dir when generated CBZ file.')
try:
sys.argv = list(
map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
except (NameError, TypeError):
pass
except UnicodeDecodeError:
exit(0)
args, _ = parser.parse_args(sys.argv[1:])
if args.html_viewer:
generate_html()
exit(0)
if args.login:
try:
_, _ = args.login.split(':', 1)
except ValueError:
logger.error('Invalid `username:password` pair.')
exit(1)
if not args.is_download:
logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
if args.id:
_ = map(lambda id: id.strip(), args.id.split(','))
args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
if (args.is_download or args.is_show) and not args.id and not args.keyword and \
not args.login and not args.tag:
logger.critical('Doujinshi id(s) are required for downloading')
parser.print_help()
exit(1)
if not args.keyword and not args.id and not args.login and not args.tag:
parser.print_help()
exit(1)
if args.threads <= 0:
args.threads = 1
elif args.threads > 15:
logger.critical('Maximum number of used threads is 15')
exit(1)
if args.proxy:
proxy_url = urlparse(args.proxy)
if proxy_url.scheme not in ('http', 'https'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(
proxy_url.scheme))
else:
constant.PROXY = {'http': args.proxy, 'https': args.proxy}
return args
def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Stopping...')
exit(1)
def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Quit.')
exit(1)
def doujinshi_parser(id_):
if not isinstance(id_,
(int, )) and (isinstance(id_,
(str, )) and not id_.isdigit()):
raise Exception('Doujinshi id({0}) is not valid'.format(id_))
id_ = int(id_)
logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
doujinshi = dict()
doujinshi['id'] = id_
url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
try:
response = request('get', url)
if response.status_code in (200, ):
response = response.content
elif response.status_code in (404, ):
logger.error("Doujinshi with id {0} cannot be found".format(id_))
return []
else:
logger.debug('Slow down and retry ({}) ...'.format(id_))
time.sleep(1)
return doujinshi_parser(str(id_))
except Exception as e:
logger.warning('Error: {}, ignored'.format(str(e)))
return None
html = BeautifulSoup(response, 'html.parser')
doujinshi_info = html.find('div', attrs={'id': 'info'})
title = doujinshi_info.find('h1').text
pretty_name = doujinshi_info.find('h1').find('span',
attrs={
'class': 'pretty'
}).text
subtitle = doujinshi_info.find('h2')
doujinshi['name'] = title
doujinshi['pretty_name'] = pretty_name
doujinshi['subtitle'] = subtitle.text if subtitle else ''
doujinshi_cover = html.find('div', attrs={'id': 'cover'})
img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
doujinshi_cover.a.img.attrs['data-src'])
ext = []
for i in html.find_all('div', attrs={'class': 'thumb-container'}):
_, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
ext.append(ext_name)
if not img_id:
logger.critical('Tried yo get image id failed')
exit(1)
doujinshi['img_id'] = img_id.group(1)
doujinshi['ext'] = ext
for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
if re.search('Pages:', _.text):
pages = _.find('span', class_='name').string
doujinshi['pages'] = int(pages)
# gain information of the doujinshi
information_fields = doujinshi_info.find_all('div',
attrs={'class': 'field-name'})
needed_fields = [
'Characters', 'Artists', 'Languages', 'Tags', 'Parodies', 'Groups',
'Categories'
]
for field in information_fields:
field_name = field.contents[0].strip().strip(':')
if field_name in needed_fields:
data = [
sub_field.find('span', attrs={
'class': 'name'
}).contents[0].strip()
for sub_field in field.find_all('a', attrs={'class': 'tag'})
]
doujinshi[field_name.lower()] = ', '.join(data)
time_field = doujinshi_info.find('time')
if time_field.has_attr('datetime'):
doujinshi['date'] = time_field['datetime']
return doujinshi
def cmd_parser():
parser = OptionParser('\n nhentai --search [keyword] --download'
'\n NHENTAI=http://h.loli.club nhentai --id [ID ...]'
'\n\nEnvironment Variable:\n'
' NHENTAI nhentai mirror url')
parser.add_option('--download', dest='is_download', action='store_true',
help='download doujinshi (for search result)')
parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information')
parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--search', type='string', dest='keyword', action='store', help='search doujinshi by keyword')
parser.add_option('--page', type='int', dest='page', action='store', default=1,
help='page number of search result')
parser.add_option('--tags', type='string', dest='tags', action='store', help='download doujinshi by tags')
parser.add_option('--output', type='string', dest='output_dir', action='store', default='',
help='output dir')
parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
help='thread count of download doujinshi')
parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
help='timeout of download doujinshi')
parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
help='use proxy, example: http://127.0.0.1:1080')
parser.add_option('--html', dest='html_viewer', action='store_true',
help='generate a html viewer at current directory')
parser.add_option('--login', '-l', type='str', dest='login', action='store',
help='username:password pair of nhentai account')
try:
sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
except (NameError, TypeError):
pass
except UnicodeDecodeError:
exit(0)
args, _ = parser.parse_args(sys.argv[1:])
if args.html_viewer:
generate_html()
exit(0)
if args.login:
try:
_, _ = args.login.split(':', 1)
except ValueError:
logger.error('Invalid `username:password` pair.')
exit(1)
if not args.is_download:
logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
if args.tags:
logger.warning('`--tags` is under construction')
exit(1)
if args.id:
_ = map(lambda id: id.strip(), args.id.split(','))
args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.login:
logger.critical('Doujinshi id(s) are required for downloading')
parser.print_help()
exit(1)
if not args.keyword and not args.id and not args.login:
parser.print_help()
exit(1)
if args.threads <= 0:
args.threads = 1
elif args.threads > 15:
logger.critical('Maximum number of used threads is 15')
exit(1)
if args.proxy:
proxy_url = urlparse(args.proxy)
if proxy_url.scheme not in ('http', 'https'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
else:
constant.PROXY = {'http': args.proxy, 'https': args.proxy}
return args
def cmd_parser():
parser = OptionParser(
'\n nhentai --search [keyword] --download'
'\n NHENTAI=http://h.loli.club nhentai --id [ID ...]'
'\n\nEnvironment Variable:\n'
' NHENTAI nhentai mirror url')
parser.add_option('--download',
dest='is_download',
action='store_true',
help='download doujinshi (for search result)')
parser.add_option('--show-info',
dest='is_show',
action='store_true',
help='just show the doujinshi information')
parser.add_option('--id',
type='string',
dest='id',
action='store',
help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--search',
type='string',
dest='keyword',
action='store',
help='search doujinshi by keyword')
parser.add_option('--page',
type='int',
dest='page',
action='store',
default=1,
help='page number of search result')
parser.add_option('--tags',
type='string',
dest='tags',
action='store',
help='download doujinshi by tags')
parser.add_option('--output',
type='string',
dest='output_dir',
action='store',
default='',
help='output dir')
parser.add_option('--threads',
'-t',
type='int',
dest='threads',
action='store',
default=5,
help='thread count of download doujinshi')
parser.add_option('--timeout',
type='int',
dest='timeout',
action='store',
default=30,
help='timeout of download doujinshi')
parser.add_option('--proxy',
type='string',
dest='proxy',
action='store',
default='',
help='use proxy, example: http://127.0.0.1:1080')
try:
sys.argv = list(
map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
except (NameError, TypeError):
pass
except UnicodeDecodeError:
exit(0)
args, _ = parser.parse_args(sys.argv[1:])
if args.tags:
logger.warning('`--tags` is under construction')
exit(0)
if args.id:
_ = map(lambda id: id.strip(), args.id.split(','))
args.id = set(map(int, filter(lambda id: id.isdigit(), _)))
if (args.is_download or args.is_show) and not args.id and not args.keyword:
logger.critical('Doujinshi id(s) are required for downloading')
parser.print_help()
exit(0)
if not args.keyword and not args.id:
parser.print_help()
exit(0)
if args.threads <= 0:
args.threads = 1
elif args.threads > 15:
logger.critical('Maximum number of used threads is 15')
exit(0)
if args.proxy:
proxy_url = urlparse(args.proxy)
if proxy_url.scheme not in ('http', 'https'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(
proxy_url.scheme))
else:
constant.PROXY = {proxy_url.scheme: args.proxy}
return args
def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Stopping...')
exit(1)