update requirements

README.rst

@@ -95,7 +95,7 @@ Download specified doujinshi:
 
 .. code-block:: bash
 
-    nhentai --id=123855,123866
+    nhentai --id 123855 123866 123877
 
 Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
@@ -145,7 +145,7 @@ Other options:
 
     Usage:
       nhentai --search [keyword] --download
-      NHENTAI=http://h.loli.club nhentai --id [ID ...]
+      NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]
       nhentai --file [filename]
 
     Environment Variable:
@@ -158,10 +158,10 @@ Other options:
       -S, --show            just show the doujinshi information
 
       # Doujinshi options, specify id, keyword, etc.
-      --id=ID               doujinshi ids set, e.g. 1,2,3
+      --id                  doujinshi ids set, e.g. 167680 167681 167682
       -s KEYWORD, --search=KEYWORD
                             search doujinshi by keyword
-      -F, --favorites       list or download your favorites.
+      -F, --favorites       list or download your favorites
 
       # Page options, control the page to fetch / download
       --page-all            all search results
@@ -179,10 +179,10 @@ Other options:
                             timeout for downloading doujinshi
       -d DELAY, --delay=DELAY
                             slow down between downloading every doujinshi
-      --proxy=PROXY         store a proxy, for example: -p 'http://127.0.0.1:1080'
+      --proxy=PROXY         store a proxy, for example: -p "http://127.0.0.1:1080"
       -f FILE, --file=FILE  read gallery IDs from file.
       --format=NAME_FORMAT  format the saved folder name
-      -r, --dry-run         Dry run, skip file download.
+      --dry-run             Dry run, skip file download
 
       # Generate options, for generate html viewer, cbz file, pdf file, etc
       --html                generate a html viewer at current directory
@@ -192,13 +192,13 @@ Other options:
       -C, --cbz             generate Comic Book CBZ File
       -P, --pdf             generate PDF file
       --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ or
-                            PDF file.
+                            PDF file
       --meta                generate a metadata file in doujinshi format
       --regenerate-cbz      regenerate the cbz file if exists
 
       # nhentai options, set cookie, user-agent, language, remove caches, histories, etc
       --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
-      --useragent=USERAGENT
+      --useragent=USERAGENT, --user-agent=USERAGENT
                             set useragent to bypass Cloudflare captcha
       --language=LANGUAGE   set default language to parse doujinshis
       --clean-language      set DEFAULT as language to parse doujinshis
@@ -209,6 +209,7 @@ Other options:
                             clean download history
       --template=VIEWER_TEMPLATE
                             set viewer template
+      --legacy              use legacy searching method
 
 ==============
 nHentai Mirror
@@ -225,7 +226,7 @@ Set `NHENTAI` env var to your nhentai mirror.
 
 .. code-block:: bash
 
-    NHENTAI=http://h.loli.club nhentai --id 123456
+    NHENTAI=https://h.loli.club nhentai --id 123456
 
 
 .. image:: ./images/search.png?raw=true

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.18'
+__version__ = '0.5.0'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -17,13 +17,7 @@ from nhentai.logger import logger
 
 
 def banner():
-    logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
-       _   _            _        _
- _ __ | | | | ___ _ __ | |_ __ _(_)
-| '_ \| |_| |/ _ \ '_ \| __/ _` | |
-| | | |  _  |  __/ | | | || (_| | |
-|_| |_|_| |_|\___|_| |_|\__\__,_|_|
-''' % __version__)
+    logger.debug(f'nHentai ver {__version__}: あなたも変態。 いいね?')
 
 
 def load_config():
@@ -46,11 +40,27 @@ def write_config():
         f.write(json.dumps(constant.CONFIG))
 
 
+def callback(option, opt_str, value, parser):
+    if option == '--id':
+        pass
+    value = []
+
+    for arg in parser.rargs:
+        if arg.isdigit():
+            value.append(int(arg))
+        elif arg.startswith('-'):
+            break
+        else:
+            logger.warning(f'Ignore invalid id {arg}')
+
+    setattr(parser.values, option.dest, value)
+
+
 def cmd_parser():
     load_config()
 
     parser = OptionParser('\n  nhentai --search [keyword] --download'
-                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n  NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]'
                           '\n  nhentai --file [filename]'
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
@@ -60,11 +70,12 @@ def cmd_parser():
     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('--id', dest='id', action='callback', callback=callback,
+                      help='doujinshi ids set, e.g. 167680 167681 167682')
     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.')
+                      help='list or download your favorites')
 
     # page options
     parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
@@ -85,11 +96,11 @@ def cmd_parser():
     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',
-                      help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
+                      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]')
-    parser.add_option('--dry-run', '-r', action='store_true', dest='dryrun', help='Dry run, skip file download.')
+    parser.add_option('--dry-run', action='store_true', dest='dryrun', help='Dry run, skip file download')
 
     # generate options
     parser.add_option('--html', dest='html_viewer', action='store_true',
@@ -103,7 +114,7 @@ def cmd_parser():
     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.')
+                      help='remove downloaded doujinshi dir when generated CBZ or PDF file')
     parser.add_option('--meta', dest='generate_metadata', action='store_true',
                       help='generate a metadata file in doujinshi format')
     parser.add_option('--regenerate-cbz', dest='regenerate_cbz', action='store_true', default=False,
@@ -127,13 +138,6 @@ def cmd_parser():
     parser.add_option('--legacy', dest='legacy', action='store_true', default=False,
                       help='use legacy searching method')
 
-    try:
-        sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
-    except (NameError, TypeError):
-        pass
-    except UnicodeDecodeError:
-        exit(0)
-
     args, _ = parser.parse_args(sys.argv[1:])
 
     if args.html_viewer:
@@ -165,21 +169,22 @@ def cmd_parser():
     elif args.language is not None:
         constant.CONFIG['language'] = args.language
         write_config()
-        logger.info('Default language now set to \'{0}\''.format(args.language))
+        logger.info(f'Default language now set to "{args.language}"')
         exit(0)
         # TODO: search without language
 
     if args.proxy is not None:
         proxy_url = urlparse(args.proxy)
-        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h', 'socks4', 'socks4a'):
-            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
+        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h',
+                                                             'socks4', 'socks4a'):
+            logger.error(f'Invalid protocol "{proxy_url.scheme}" of proxy, ignored')
             exit(0)
         else:
             constant.CONFIG['proxy'] = {
                 'http': args.proxy,
                 'https': args.proxy,
             }
-            logger.info('Proxy now set to \'{0}\'.'.format(args.proxy))
+            logger.info(f'Proxy now set to "{args.proxy}"')
             write_config()
             exit(0)
 
@@ -188,8 +193,8 @@ def cmd_parser():
             args.viewer_template = 'default'
 
         if not os.path.exists(os.path.join(os.path.dirname(__file__),
-                                           'viewer/{}/index.html'.format(args.viewer_template))):
-            logger.error('Template \'{}\' does not exists'.format(args.viewer_template))
+                                           f'viewer/{args.viewer_template}/index.html')):
+            logger.error(f'Template "{args.viewer_template}" does not exists')
             exit(1)
         else:
             constant.CONFIG['template'] = args.viewer_template
@@ -202,10 +207,6 @@ def cmd_parser():
             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()]

nhentai/command.py

@@ -1,10 +1,8 @@
-#!/usr/bin/env python2.7
 # coding: utf-8
-
 import sys
 import signal
 import platform
-import time
+import urllib3.exceptions
 
 from nhentai import constant
 from nhentai.cmdline import cmd_parser, banner
@@ -25,16 +23,16 @@ def main():
         exit(1)
 
     options = cmd_parser()
-    logger.info('Using mirror: {0}'.format(BASE_URL))
+    logger.info(f'Using mirror: {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']))
+        logger.info(f'Using proxy: {constant.CONFIG["proxy"]["http"]}')
 
     if not constant.CONFIG['template']:
         constant.CONFIG['template'] = 'default'
 
-    logger.info('Using viewer template "{}"'.format(constant.CONFIG['template']))
+    logger.info(f'Using viewer template "{constant.CONFIG["template"]}"')
 
     # check your cookie
     check_cookie()
@@ -53,8 +51,8 @@ def main():
 
     elif options.keyword:
         if constant.CONFIG['language']:
-            logger.info('Using default language: {0}'.format(constant.CONFIG['language']))
-            options.keyword += ' language:{}'.format(constant.CONFIG['language'])
+            logger.info(f'Using default language: {constant.CONFIG["language"]}')
+            options.keyword += f' language:{constant.CONFIG["language"]}'
 
         _search_parser = legacy_search_parser if options.legacy else search_parser
         doujinshis = _search_parser(options.keyword, sorting=options.sorting, page=page_list,
@@ -107,9 +105,9 @@ def main():
             generate_main_html(options.output_dir)
 
         if not platform.system() == 'Windows':
-            logger.log(15, '🍻 All done.')
+            logger.log(16, '🍻 All done.')
         else:
-            logger.log(15, 'All done.')
+            logger.log(16, 'All done.')
 
     else:
         for doujinshi_id in doujinshi_ids:
@@ -121,6 +119,7 @@ def main():
             doujinshi.show()
 
 
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 signal.signal(signal.SIGINT, signal_handler)
 
 if __name__ == '__main__':

nhentai/constant.py

@@ -1,35 +1,29 @@
 # coding: utf-8
-
 import os
 import tempfile
 
-try:
-    from urlparse import urlparse
-except ImportError:
-    from urllib.parse import urlparse
+from urllib.parse import urlparse
 
 
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-__api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
+DETAIL_URL = f'{BASE_URL}/g'
+LEGACY_SEARCH_URL = f'{BASE_URL}/search/'
+SEARCH_URL = f'{BASE_URL}/api/galleries/search'
 
-DETAIL_URL = '%s/g' % BASE_URL
-LEGACY_SEARCH_URL = '%s/search/' % BASE_URL
-SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+TAG_API_URL = f'{BASE_URL}/api/galleries/tagged'
+LOGIN_URL = f'{BASE_URL}/login/'
+CHALLENGE_URL = f'{BASE_URL}/challenge'
+FAV_URL = f'{BASE_URL}/favorites/'
 
-
-TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
-LOGIN_URL = '%s/login/' % BASE_URL
-CHALLENGE_URL = '%s/challenge' % BASE_URL
-FAV_URL = '%s/favorites/' % BASE_URL
-
-u = urlparse(BASE_URL)
-IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
+IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
 
 NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
 NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
+__api_suspended_DETAIL_URL = f'{BASE_URL}/api/gallery'
+
 CONFIG = {
     'proxy': {'http': '', 'https': ''},
     'cookie': '',
@@ -38,9 +32,9 @@ CONFIG = {
     'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
 }
 
-LANGUAGEISO ={
-    'english' : 'en',
-    'chinese' : 'zh',
-    'japanese' : 'ja',
-    'translated' : 'translated'
+LANGUAGE_ISO = {
+    'english': 'en',
+    'chinese': 'zh',
+    'japanese': 'ja',
+    'translated': 'translated'
 }

nhentai/doujinshi.py

@@ -35,7 +35,7 @@ class Doujinshi(object):
         self.ext = ext
         self.pages = pages
         self.downloader = None
-        self.url = '%s/%d' % (DETAIL_URL, self.id)
+        self.url = f'{DETAIL_URL}/{self.id}'
         self.info = DoujinshiInfo(**kwargs)
 
         name_format = name_format.replace('%i', format_filename(str(self.id)))
@@ -59,23 +59,22 @@ class Doujinshi(object):
         ]
 
     def __repr__(self):
-        return '<Doujinshi: {0}>'.format(self.name)
+        return f'<Doujinshi: {self.name}>'
 
     def show(self):
-
-        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(self.table)))
+        logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
 
     def download(self, regenerate_cbz=False):
-        logger.info('Starting to download doujinshi: %s' % self.name)
+        logger.info(f'Starting to download doujinshi: {self.name}')
         if self.downloader:
             download_queue = []
             if len(self.ext) != self.pages:
                 logger.warning('Page count and ext count do not equal')
 
             for i in range(1, min(self.pages, len(self.ext)) + 1):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i - 1]))
+                download_queue.append(f'{IMAGE_URL}/{self.img_id}/{i}.{self.ext[i-1]}')
 
-            self.downloader.download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
+            self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
         else:
             logger.critical('Downloader has not been loaded')
 
@@ -87,4 +86,4 @@ if __name__ == '__main__':
     try:
         test.download()
     except Exception as e:
-        print('Exception: %s' % str(e))
+        print(f'Exception: {e}')

nhentai/downloader.py

@@ -3,23 +3,20 @@
 import multiprocessing
 import signal
 
-from future.builtins import str as text
 import sys
 import os
 import requests
 import time
+import urllib3.exceptions
 
-try:
-    from urllib.parse import urlparse
-except ImportError:
-    from urlparse import urlparse
-
+from urllib.parse import urlparse
 from nhentai import constant
 from nhentai.logger import logger
 from nhentai.parser import request
 from nhentai.utils import Singleton
 
-requests.packages.urllib3.disable_warnings()
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 semaphore = multiprocessing.Semaphore(1)
 
 
@@ -27,6 +24,21 @@ class NHentaiImageNotExistException(Exception):
     pass
 
 
+def download_callback(result):
+    result, data = result
+    if result == 0:
+        logger.warning('fatal errors occurred, ignored')
+    elif result == -1:
+        logger.warning(f'url {data} return status code 404')
+    elif result == -2:
+        logger.warning('Ctrl-C pressed, exiting sub processes ...')
+    elif result == -3:
+        # workers won't be run, just pass
+        pass
+    else:
+        logger.log(16, f'{data} downloaded successfully')
+
+
 class Downloader(Singleton):
 
     def __init__(self, path='', size=5, timeout=30, delay=0):
@@ -35,20 +47,21 @@ class Downloader(Singleton):
         self.timeout = timeout
         self.delay = delay
 
-    def download_(self, url, folder='', filename='', retried=0, proxy=None):
+    def download(self, url, folder='', filename='', retried=0, proxy=None):
         if self.delay:
             time.sleep(self.delay)
-        logger.info('Starting to download {0} ...'.format(url))
+        logger.info(f'Starting to download {url} ...')
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
+
+        save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
         try:
-            if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
-                logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
-                                                                                extension)))
+            if os.path.exists(save_file_path):
+                logger.warning(f'Ignored exists file: {save_file_path}')
                 return 1, url
 
             response = None
-            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
+            with open(save_file_path, "wb") as f:
                 i = 0
                 while i < 10:
                     try:
@@ -77,14 +90,14 @@ class Downloader(Singleton):
 
         except (requests.HTTPError, requests.Timeout) as e:
             if retried < 3:
-                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
-                return 0, self.download_(url=url, folder=folder, filename=filename,
-                                         retried=retried+1, proxy=proxy)
+                logger.warning(f'Warning: {e}, retrying({retried}) ...')
+                return 0, self.download(url=url, folder=folder, filename=filename,
+                                        retried=retried+1, proxy=proxy)
             else:
                 return 0, None
 
         except NHentaiImageNotExistException as e:
-            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            os.remove(save_file_path)
             return -1, url
 
         except Exception as e:
@@ -98,23 +111,8 @@ class Downloader(Singleton):
 
         return 1, url
 
-    def _download_callback(self, result):
-        result, data = result
-        if result == 0:
-            logger.warning('fatal errors occurred, ignored')
-            # exit(1)
-        elif result == -1:
-            logger.warning('url {} return status code 404'.format(data))
-        elif result == -2:
-            logger.warning('Ctrl-C pressed, exiting sub processes ...')
-        elif result == -3:
-            # workers wont be run, just pass
-            pass
-        else:
-            logger.log(15, '{0} downloaded successfully'.format(data))
-
-    def download(self, queue, folder='', regenerate_cbz=False):
-        if not isinstance(folder, text):
+    def start_download(self, queue, folder='', regenerate_cbz=False):
+        if not isinstance(folder, (str, )):
             folder = str(folder)
 
         if self.path:
@@ -122,18 +120,17 @@ class Downloader(Singleton):
 
         if os.path.exists(folder + '.cbz'):
             if not regenerate_cbz:
-                logger.warning('CBZ file \'{}.cbz\' exists, ignored download request'.format(folder))
+                logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
                 return
 
         if not os.path.exists(folder):
-            logger.warning('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
-                logger.critical('{0}'.format(str(e)))
+                logger.critical(str(e))
 
         else:
-            logger.warning('Path \'{0}\' already exist.'.format(folder))
+            logger.warning(f'Path "{folder}" already exist.')
 
         queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
 
@@ -146,7 +143,7 @@ class Downloader(Singleton):
 
 def download_wrapper(obj, url, folder='', proxy=None):
     if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download_(obj, url=url, folder=folder, proxy=proxy)
+        return Downloader.download(obj, url=url, folder=folder, proxy=proxy)
     else:
         return -3, None
 
@@ -155,7 +152,7 @@ def init_worker():
     signal.signal(signal.SIGINT, subprocess_signal)
 
 
-def subprocess_signal(signal, frame):
+def subprocess_signal(sig, frame):
     if semaphore.acquire(timeout=1):
         logger.warning('Ctrl-C pressed, exiting sub processes ...')
 

nhentai/logger.py

@@ -34,7 +34,7 @@ class ColorizingStreamHandler(logging.StreamHandler):
     # levels to (background, foreground, bold/intense)
     level_map = {
         logging.DEBUG: (None, 'blue', False),
-        logging.INFO: (None, 'green', False),
+        logging.INFO: (None, 'white', False),
         logging.WARNING: (None, 'yellow', False),
         logging.ERROR: (None, 'red', False),
         logging.CRITICAL: ('red', 'white', False)
@@ -160,18 +160,18 @@ class ColorizingStreamHandler(logging.StreamHandler):
         return self.colorize(message, record)
 
 
-logging.addLevelName(15, "INFO")
+logging.addLevelName(16, "SUCCESS")
 logger = logging.getLogger('nhentai')
 LOGGER_HANDLER = ColorizingStreamHandler(sys.stdout)
-FORMATTER = logging.Formatter("\r[%(asctime)s] [%(levelname)s] %(message)s", "%H:%M:%S")
+FORMATTER = logging.Formatter("\r[%(asctime)s] %(funcName)s: %(message)s", "%H:%M:%S")
 LOGGER_HANDLER.setFormatter(FORMATTER)
-LOGGER_HANDLER.level_map[logging.getLevelName("INFO")] = (None, "cyan", False)
+LOGGER_HANDLER.level_map[logging.getLevelName("SUCCESS")] = (None, "green", False)
 logger.addHandler(LOGGER_HANDLER)
 logger.setLevel(logging.DEBUG)
 
 
 if __name__ == '__main__':
-    logger.log(15, 'nhentai')
+    logger.log(16, 'nhentai')
     logger.info('info')
     logger.warning('warning')
     logger.debug('debug')

nhentai/parser.py

@@ -26,7 +26,7 @@ def login(username, password):
         logger.info('Getting CSRF token ...')
 
     if os.getenv('DEBUG'):
-        logger.info('CSRF token is {}'.format(csrf_token))
+        logger.info(f'CSRF token is {csrf_token}')
 
     login_dict = {
         'csrfmiddlewaretoken': csrf_token,
@@ -56,7 +56,7 @@ def _get_title_and_id(response):
         doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
         title = doujinshi_container.text.strip()
         title = title if len(title) < 85 else title[:82] + '...'
-        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
+        id_ = re.search('/g/([0-9]+)/', doujinshi.a['href']).group(1)
         result.append({'id': id_, 'title': title})
 
     return result
@@ -67,7 +67,7 @@ def favorites_parser(page=None):
     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?")
+        logger.error("Can't get your number of favorite doujinshis. Did the login failed?")
         return []
 
     count = int(count.text.strip('(').strip(')').replace(',', ''))
@@ -84,7 +84,7 @@ def favorites_parser(page=None):
         else:
             pages = 1
 
-        logger.info('You have %d favorites in %d pages.' % (count, pages))
+        logger.info(f'You have {count} favorites in {pages} pages.')
 
         if os.getenv('DEBUG'):
             pages = 1
@@ -93,40 +93,40 @@ def favorites_parser(page=None):
 
     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
+            logger.info(f'Getting doujinshi ids of page {page}')
+            resp = request('get', f'{constant.FAV_URL}?page={page}').content
 
             result.extend(_get_title_and_id(resp))
         except Exception as e:
-            logger.error('Error: %s, continue', str(e))
+            logger.error(f'Error: {e}, continue')
 
     return result
 
 
 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_))
+        raise Exception(f'Doujinshi id({id_}) is not valid')
 
     id_ = int(id_)
-    logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
+    logger.info(f'Fetching doujinshi information of id {id_}')
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
+    url = f'{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_))
+            logger.error(f'Doujinshi with id {id_} cannot be found')
             return []
         else:
-            logger.debug('Slow down and retry ({}) ...'.format(id_))
+            logger.debug(f'Slow down and retry ({id_}) ...')
             time.sleep(1)
             return doujinshi_parser(str(id_))
 
     except Exception as e:
-        logger.warning('Error: {}, ignored'.format(str(e)))
+        logger.warning(f'Error: {e}, ignored')
         return None
 
     html = BeautifulSoup(response, 'html.parser')
@@ -156,6 +156,7 @@ def doujinshi_parser(id_):
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
 
+    pages = 0
     for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
         if re.search('Pages:', _.text):
             pages = _.find('span', class_='name').string
@@ -177,15 +178,38 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def legacy_search_parser(keyword, sorting='date', page=1, is_page_all=False):
-    logger.warning('Using legacy searching method, `--all` options will not be supported')
-    logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
-    response = request('get', url=constant.LEGACY_SEARCH_URL,
-                       params={'q': keyword, 'page': page, 'sort': sorting}).content
+def legacy_search_parser(keyword, sorting, page, is_page_all=False):
+    logger.debug(f'Searching doujinshis of keyword {keyword}')
+
+    response = None
+    result = []
+
+    if is_page_all and len(page) != 1:
+        # `--page-all` option will override the `--page` option
+        page = [1]
+
+    for p in page:
+        logger.debug(f'Fetching page {p} ...')
+        response = request('get', url=constant.LEGACY_SEARCH_URL,
+                           params={'q': keyword, 'page': p, 'sort': sorting}).content
+        result.extend(_get_title_and_id(response))
 
-    result = _get_title_and_id(response)
     if not result:
-        logger.warning('Not found anything of keyword {}'.format(keyword))
+        logger.warning(f'Not found anything of keyword {keyword} on page {page[0]}')
+        return result
+
+    if is_page_all:
+        html = BeautifulSoup(response, 'lxml')
+        pagination = html.find(attrs={'class': 'pagination'})
+        next_page = pagination.find(attrs={'class': 'next'})
+
+        if next_page is None:
+            logger.warning('Reached the last page')
+            return result
+        else:
+            next_page = re.findall('page=([0-9]+)', next_page.attrs['href'])[0]
+            result.extend(legacy_search_parser(keyword, sorting, [next_page], is_page_all))
+            return result
 
     return result
 
@@ -195,12 +219,11 @@ def print_doujinshi(doujinshi_list):
         return
     doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
-    logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
-                tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+    logger.info(f'Search Result || Found {doujinshi_list.__len__()} doujinshis')
+    print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
 def search_parser(keyword, sorting, page, is_page_all=False):
-    # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     result = []
     response = None
     if not page:
@@ -211,12 +234,12 @@ def search_parser(keyword, sorting, page, is_page_all=False):
         init_response = request('get', url.replace('%2B', '+')).json()
         page = range(1, init_response['num_pages']+1)
 
-    total = '/{0}'.format(page[-1]) if is_page_all else ''
+    total = f'/{page[-1]}' if is_page_all else ''
     not_exists_persist = False
     for p in page:
         i = 0
 
-        logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
+        logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
         while i < 3:
             try:
                 url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
@@ -228,7 +251,7 @@ def search_parser(keyword, sorting, page, is_page_all=False):
             break
 
         if response is None or 'result' not in response:
-            logger.warning('No result in response in page {}'.format(p))
+            logger.warning(f'No result in response in page {p}')
             if not_exists_persist is True:
                 break
             continue
@@ -240,20 +263,20 @@ def search_parser(keyword, sorting, page, is_page_all=False):
 
         not_exists_persist = False
         if not result:
-            logger.warning('No results for keywords {}'.format(keyword))
+            logger.warning(f'No results for keywords {keyword}')
 
     return result
 
 
 def __api_suspended_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_))
+        raise Exception(f'Doujinshi id({id_}) is not valid')
 
     id_ = int(id_)
-    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
+    logger.info(f'Fetching information of doujinshi id {id_}')
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    url = f'{constant.DETAIL_URL}/{id_}'
     i = 0
     while 5 > i:
         try:

nhentai/serializer.py

@@ -2,10 +2,10 @@
 import json
 import os
 from xml.sax.saxutils import escape
-from nhentai.constant import LANGUAGEISO
+from nhentai.constant import LANGUAGE_ISO
 
 
-def serialize_json(doujinshi, dir):
+def serialize_json(doujinshi, output_dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
     if doujinshi.info.date:
@@ -26,13 +26,13 @@ def serialize_json(doujinshi, dir):
     metadata['URL'] = doujinshi.url
     metadata['Pages'] = doujinshi.pages
 
-    with open(os.path.join(dir, 'metadata.json'), 'w') as f:
+    with open(os.path.join(output_dir, 'metadata.json'), 'w') as f:
         json.dump(metadata, f, separators=(',', ':'))
 
 
-def serialize_comic_xml(doujinshi, dir):
+def serialize_comic_xml(doujinshi, output_dir):
     from iso8601 import parse_date
-    with open(os.path.join(dir, 'ComicInfo.xml'), 'w', encoding="utf-8") as f:
+    with open(os.path.join(output_dir, 'ComicInfo.xml'), 'w', encoding="utf-8") as f:
         f.write('<?xml version="1.0" encoding="utf-8"?>\n')
         f.write('<ComicInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" '
                 'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">\n')
@@ -67,14 +67,14 @@ def serialize_comic_xml(doujinshi, dir):
         if doujinshi.info.languages:
             languages = [i.strip() for i in doujinshi.info.languages.split(',')]
             xml_write_simple_tag(f, 'Translated', 'Yes' if 'translated' in languages else 'No')
-            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGEISO[i]) for i in languages
-                if (i != 'translated' and i in LANGUAGEISO)]
+            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGE_ISO[i]) for i in languages
+             if (i != 'translated' and i in LANGUAGE_ISO)]
 
         f.write('</ComicInfo>')
 
 
 def xml_write_simple_tag(f, name, val, indent=1):
-    f.write('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
+    f.write(f'{" "*indent}<{name}>{escape(str(val))}</{name}>\n')
 
 
 def merge_json():

nhentai/utils.py

@@ -36,11 +36,11 @@ def check_cookie():
         logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
         exit(-1)
 
-    username = re.findall('"/users/\d+/(.*?)"', response.text)
+    username = re.findall('"/users/[0-9]+/(.*?)"', 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]))
+        logger.log(16, f'Login successfully! Your username: {username[0]}')
 
 
 class _Singleton(type):
@@ -82,11 +82,11 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
         doujinshi_dir = '.'
 
     if not os.path.exists(doujinshi_dir):
-        logger.warning('Path \'{0}\' does not exist, creating.'.format(doujinshi_dir))
+        logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
         try:
             os.makedirs(doujinshi_dir)
         except EnvironmentError as e:
-            logger.critical('{0}'.format(str(e)))
+            logger.critical(e)
 
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
@@ -94,18 +94,15 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     for image in file_list:
         if not os.path.splitext(image)[1] in ('.jpg', '.png'):
             continue
+        image_html += f'<img src="{image}" class="image-item"/>\n'
 
-        image_html += '<img src="{0}" class="image-item"/>\n' \
-            .format(image)
-    html = readfile('viewer/{}/index.html'.format(template))
-    css = readfile('viewer/{}/styles.css'.format(template))
-    js = readfile('viewer/{}/scripts.js'.format(template))
+    html = readfile(f'viewer/{template}/index.html')
+    css = readfile(f'viewer/{template}/styles.css')
+    js = readfile(f'viewer/{template}/scripts.js')
 
     if doujinshi_obj is not None:
         serialize_json(doujinshi_obj, doujinshi_dir)
         name = doujinshi_obj.name
-        if sys.version_info < (3, 0):
-            name = doujinshi_obj.name.encode('utf-8')
     else:
         name = {'title': 'nHentai HTML Viewer'}
 
@@ -118,14 +115,14 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
             with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
                 f.write(data.encode('utf-8'))
 
-        logger.log(15, 'HTML Viewer has been written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(16, f'HTML Viewer has been written to "{os.path.join(doujinshi_dir, "index.html")}"')
     except Exception as e:
-        logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing HTML Viewer failed ({e})')
 
 
 def generate_main_html(output_dir='./'):
     """
-    Generate a main html to show all the contain doujinshi.
+    Generate a main html to show all the contains doujinshi.
     With a link to their `index.html`.
     Default output folder will be the CLI path.
     """
@@ -154,7 +151,7 @@ def generate_main_html(output_dir='./'):
         files.sort()
 
         if 'index.html' in files:
-            logger.info('Add doujinshi \'{}\''.format(folder))
+            logger.info(f'Add doujinshi "{folder}"')
         else:
             continue
 
@@ -178,10 +175,9 @@ def generate_main_html(output_dir='./'):
                 f.write(data.encode('utf-8'))
         shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
         set_js_database()
-        logger.log(
-            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
+        logger.log(16, f'Main Viewer has been written to "{output_dir}main.html"')
     except Exception as e:
-        logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing Main Viewer failed ({e})')
 
 
 def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True):
@@ -189,7 +185,7 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
         if write_comic_info:
             serialize_comic_xml(doujinshi_obj, doujinshi_dir)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
+        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), f'{doujinshi_obj.filename}.cbz')
     else:
         cbz_filename = './doujinshi.cbz'
         doujinshi_dir = '.'
@@ -197,7 +193,7 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
-    logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
+    logger.info(f'Writing CBZ file to path: {cbz_filename}')
     with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
         for image in file_list:
             image_path = os.path.join(doujinshi_dir, image)
@@ -206,7 +202,7 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
-    logger.log(15, 'Comic Book CBZ file has been written to \'{0}\''.format(doujinshi_dir))
+    logger.log(16, f'Comic Book CBZ file has been written to "{doujinshi_dir}"')
 
 
 def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
@@ -218,7 +214,7 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
             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)
+                f'{doujinshi_obj.filename}.pdf'
             )
         else:
             pdf_filename = './doujinshi.pdf'
@@ -227,7 +223,7 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
         file_list = os.listdir(doujinshi_dir)
         file_list.sort()
 
-        logger.info('Writing PDF file to path: {}'.format(pdf_filename))
+        logger.info(f'Writing PDF file to path: {pdf_filename}')
         with open(pdf_filename, 'wb') as pdf_f:
             full_path_list = (
                 [os.path.join(doujinshi_dir, image) for image in file_list]
@@ -237,19 +233,12 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
         if rm_origin_dir:
             shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
-        logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
+        logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
 
     except ImportError:
         logger.error("Please install img2pdf package by using pip.")
 
 
-def unicode_truncate(s, length, encoding='utf-8'):
-    """https://stackoverflow.com/questions/1809531/truncating-unicode-so-it-fits-a-maximum-size-when-encoded-for-wire-transfer
-    """
-    encoded = s.encode(encoding)[:length]
-    return encoded.decode(encoding, 'ignore')
-
-
 def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
     """
     It used to be a whitelist approach allowed only alphabet and a part of symbols.
@@ -323,7 +312,7 @@ def generate_metadata_file(output_dir, table, doujinshi_obj=None):
                       'LANGUAGE', 'TAGS', 'URL', 'PAGES']
 
     for i in range(len(fields)):
-        f.write('{}: '.format(fields[i]))
+        f.write(f'{fields[i]}: ')
         if fields[i] in special_fields:
             f.write(str(table[special_fields.index(fields[i])][1]))
         f.write('\n')

requirements.txt

@@ -2,5 +2,5 @@ requests>=2.5.0
 soupsieve
 BeautifulSoup4>=4.0.0
 tabulate>=0.7.5
-future>=0.15.2
 iso8601 >= 0.1
+urllib3

setup.py

@@ -1,6 +1,4 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
-import sys
 import codecs
 from setuptools import setup, find_packages
 from nhentai import __version__, __author__, __email__
@@ -11,9 +9,8 @@ with open('requirements.txt') as f:
 
 
 def long_description():
-    with codecs.open('README.rst', 'rb') as readme:
-        if not sys.version_info < (3, 0, 0):
-            return readme.read().decode('utf-8')
+    with codecs.open('README.rst', 'r') as readme:
+        return readme.read()
 
 
 setup(