0.4.18 bugs fix

Pull/221

.gitignore

@@ -7,3 +7,4 @@ dist/
 .DS_Store
 output/
 venv/
+.vscode/

MANIFEST.in

@@ -2,3 +2,4 @@ include README.md
 include requirements.txt
 include nhentai/viewer/*
 include nhentai/viewer/default/*
+include nhentai/viewer/minimal/*

README.rst

@@ -51,10 +51,17 @@ Installation (Gentoo)
     layman -fa glicOne
     sudo emerge net-misc/nhentai
     
+=====================
+Installation (NixOs)
+=====================
+.. code-block::
+
+    nix-env -iA nixos.nhentai
+    
 =====
 Usage
 =====
-**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--cookie` option to store your cookie.
+**⚠️IMPORTANT⚠️**: To bypass the nhentai frequency limit, you should use `--cookie` and `--useragent` options to store your cookie and your user-agent.
 
 *The default download folder will be the path where you run the command (CLI path).*
 
@@ -63,9 +70,26 @@ Set your nhentai cookie against captcha:
 
 .. code-block:: bash
 
+    nhentai --useragent "USER AGENT of YOUR BROWSER"
     nhentai --cookie "YOUR COOKIE FROM nhentai.net"
 
-**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
+**NOTE**
+
+- The format of the cookie is `"csrftoken=TOKEN; sessionid=ID; cf_clearance=CLOUDFLARE"`
+- `cf_clearance` cookie and useragent must be set if you encounter "blocked by cloudflare captcha" error. Make sure you use the same IP and useragent as when you got it
+
+| To get csrftoken and sessionid, first login to your nhentai account in web browser, then:
+| (Chrome) |ve| |ld| More tools    |ld| Developer tools     |ld| Application |ld| Storage |ld| Cookies |ld| https://nhentai.net
+| (Firefox) |hv| |ld| Web Developer |ld| Web Developer Tools                  |ld| Storage |ld| Cookies |ld| https://nhentai.net
+| 
+
+.. |hv| unicode:: U+2630 .. https://www.compart.com/en/unicode/U+2630
+.. |ve| unicode:: U+22EE .. https://www.compart.com/en/unicode/U+22EE
+.. |ld| unicode:: U+2014 .. https://www.compart.com/en/unicode/U+2014
+
+.. image:: ./images/usage.png?raw=true
+    :alt: nhentai
+    :align: center
 
 Download specified doujinshi:
 
@@ -112,30 +136,41 @@ Supported doujinshi folder formatter:
 - %t: Doujinshi name
 - %s: Doujinshi subtitle (translated name)
 - %a: Doujinshi authors' name
+- %p: Doujinshi pretty name
 
 
 Other options:
 
 .. code-block::
 
+    Usage:
+      nhentai --search [keyword] --download
+      NHENTAI=http://h.loli.club nhentai --id [ID ...]
+      nhentai --file [filename]
+
+    Environment Variable:
+      NHENTAI                 nhentai mirror url
+
     Options:
-      # Operation options
+      # Operation options, control the program behaviors
       -h, --help            show this help message and exit
       -D, --download        download doujinshi (for search results)
       -S, --show            just show the doujinshi information
 
-      # Doujinshi options
+      # Doujinshi options, specify id, keyword, etc.
       --id=ID               doujinshi ids set, e.g. 1,2,3
       -s KEYWORD, --search=KEYWORD
                             search doujinshi by keyword
-      --tag=TAG             download doujinshi by tag
       -F, --favorites       list or download your favorites.
 
-      # Multi-page options
-      --page=PAGE           page number of search results
-      --max-page=MAX_PAGE   The max page when recursive download tagged doujinshi
+      # Page options, control the page to fetch / download
+      --page-all            all search results
+      --page=PAGE, --page-range=PAGE
+                            page number of search results. e.g. 1,2-5,14
+      --sorting=SORTING     sorting of doujinshi (recent / popular /
+                            popular-[today|week])
 
-      # Download options
+      # Download options, the output directory, threads, timeout, delay, etc.
       -o OUTPUT_DIR, --output=OUTPUT_DIR
                             output dir
       -t THREADS, --threads=THREADS
@@ -144,23 +179,36 @@ Other options:
                             timeout for downloading doujinshi
       -d DELAY, --delay=DELAY
                             slow down between downloading every doujinshi
-      -p PROXY, --proxy=PROXY
-                            uses a proxy, for example: 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.
 
-      # Generating options
+      # Generate options, for generate html viewer, cbz file, pdf file, etc
       --html                generate a html viewer at current directory
       --no-html             don't generate HTML after downloading
-      --gen-main            generate a main viewer contain all the doujin in the folder
+      --gen-main            generate a main viewer contain all the doujin in the
+                            folder
       -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.
-
-      # nHentai options
-      --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
+      -P, --pdf             generate PDF file
+      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ or
+                            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
+                            set useragent to bypass Cloudflare captcha
+      --language=LANGUAGE   set default language to parse doujinshis
+      --clean-language      set DEFAULT as language to parse doujinshis
+      --save-download-history
+                            save downloaded doujinshis, whose will be skipped if
+                            you re-download them
+      --clean-download-history
+                            clean download history
+      --template=VIEWER_TEMPLATE
+                            set viewer template
 
 ==============
 nHentai Mirror
@@ -190,14 +238,6 @@ Set `NHENTAI` env var to your nhentai mirror.
     :alt: nhentai
     :align: center
 
-============
-あなたも変態
-============
-.. image:: ./images/image.jpg?raw=true
-    :alt: nhentai
-    :align: center
-
-
 
 .. |travis| image:: https://travis-ci.org/RicterZ/nhentai.svg?branch=master
    :target: https://travis-ci.org/RicterZ/nhentai

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.12'
+__version__ = '0.4.18'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -71,9 +71,9 @@ def cmd_parser():
                       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',
+    parser.add_option('--sorting', dest='sorting', action='store', default='popular',
                       help='sorting of doujinshi (recent / popular / popular-[today|week])',
-                      choices=['recent', 'popular', 'popular-today', 'popular-week'])
+                      choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
     parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='./',
@@ -84,11 +84,12 @@ def cmd_parser():
                       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='',
+    parser.add_option('--proxy', type='string', dest='proxy', action='store',
                       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.')
 
     # generate options
     parser.add_option('--html', dest='html_viewer', action='store_true',
@@ -103,10 +104,16 @@ def cmd_parser():
                       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.')
+    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,
+                      help='regenerate the cbz file if exists')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
-                      help='set cookie of nhentai to bypass Google recaptcha')
+                      help='set cookie of nhentai to bypass Cloudflare captcha')
+    parser.add_option('--useragent', '--user-agent', type='str', dest='useragent', action='store',
+                      help='set useragent to bypass Cloudflare captcha')
     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,
@@ -117,6 +124,8 @@ def cmd_parser():
                       help='clean download history')
     parser.add_option('--template', dest='viewer_template', action='store',
                       help='set viewer template', default='')
+    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]
@@ -128,7 +137,7 @@ def cmd_parser():
     args, _ = parser.parse_args(sys.argv[1:])
 
     if args.html_viewer:
-        generate_html()
+        generate_html(template=constant.CONFIG['template'])
         exit(0)
 
     if args.main_viewer and not args.id and not args.keyword and not args.favorites:
@@ -145,20 +154,24 @@ def cmd_parser():
     # --- set config ---
     if args.cookie is not None:
         constant.CONFIG['cookie'] = args.cookie
+        write_config()
         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))
+    elif args.useragent is not None:
+        constant.CONFIG['useragent'] = args.useragent
         write_config()
+        logger.info('User-Agent saved.')
+        exit(0)
+    elif args.language is not None:
+        constant.CONFIG['language'] = args.language
+        write_config()
+        logger.info('Default language now set to \'{0}\''.format(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'):
+        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))
             exit(0)
         else:
@@ -214,4 +227,8 @@ def cmd_parser():
         logger.critical('Maximum number of used threads is 15')
         exit(1)
 
+    if args.dryrun and (args.is_cbz or args.is_pdf):
+        logger.critical('Cannot generate PDF or CBZ during dry-run')
+        exit(1)
+
     return args

nhentai/command.py

@@ -8,12 +8,12 @@ import time
 
 from nhentai import constant
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser
+from nhentai.parser import doujinshi_parser, search_parser, legacy_search_parser, print_doujinshi, favorites_parser
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
     paging, check_cookie, signal_handler, DB
 
 
@@ -55,7 +55,9 @@ def main():
         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,
+
+        _search_parser = legacy_search_parser if options.legacy else search_parser
+        doujinshis = _search_parser(options.keyword, sorting=options.sorting, page=page_list,
                                     is_page_all=options.page_all)
 
     elif not doujinshi_ids:
@@ -69,29 +71,27 @@ def main():
         with DB() as db:
             data = map(int, db.get_all())
 
-            doujinshi_ids = list(set(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)))
+        doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
 
     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:
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
 
+            if not options.dryrun:
                 doujinshi.downloader = downloader
-            doujinshi.download()
+                doujinshi.download(regenerate_cbz=options.regenerate_cbz)
+
+            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)
@@ -112,11 +112,16 @@ def main():
             logger.log(15, 'All done.')
 
     else:
-        [doujinshi.show() for doujinshi in doujinshi_list]
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
+            doujinshi.show()
 
 
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/constant.py

@@ -14,6 +14,7 @@ BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 __api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
 
 DETAIL_URL = '%s/g' % BASE_URL
+LEGACY_SEARCH_URL = '%s/search/' % BASE_URL
 SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
 
@@ -29,10 +30,17 @@ 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')
 
-
 CONFIG = {
     'proxy': {'http': '', 'https': ''},
     'cookie': '',
     'language': '',
     'template': '',
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
+}
+
+LANGUAGEISO ={
+    'english' : 'en',
+    'chinese' : 'zh',
+    'japanese' : 'ja',
+    'translated' : 'translated'
 }

nhentai/doujinshi.py

@@ -26,8 +26,10 @@ class DoujinshiInfo(dict):
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
+    def __init__(self, name=None, pretty_name=None, id=None, img_id=None,
+                 ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
+        self.pretty_name = pretty_name
         self.id = id
         self.img_id = img_id
         self.ext = ext
@@ -36,17 +38,15 @@ class Doujinshi(object):
         self.url = '%s/%d' % (DETAIL_URL, self.id)
         self.info = DoujinshiInfo(**kwargs)
 
-        name_format = name_format.replace('%i', str(self.id))
-        name_format = name_format.replace('%a', self.info.artists)
-        name_format = name_format.replace('%t', self.name)
-        name_format = name_format.replace('%s', self.info.subtitle)
-        self.filename = format_filename(name_format)
+        name_format = name_format.replace('%i', format_filename(str(self.id)))
+        name_format = name_format.replace('%a', format_filename(self.info.artists))
 
-    def __repr__(self):
-        return '<Doujinshi: {0}>'.format(self.name)
+        name_format = name_format.replace('%t', format_filename(self.name))
+        name_format = name_format.replace('%p', format_filename(self.pretty_name))
+        name_format = name_format.replace('%s', format_filename(self.info.subtitle))
+        self.filename = format_filename(name_format, 255, True)
 
-    def show(self):
-        table = [
+        self.table = [
             ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
@@ -57,26 +57,25 @@ class Doujinshi(object):
             ["URL", self.url],
             ["Pages", self.pages],
         ]
-        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
 
-    def download(self):
+    def __repr__(self):
+        return '<Doujinshi: {0}>'.format(self.name)
+
+    def show(self):
+
+        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(self.table)))
+
+    def download(self, regenerate_cbz=False):
         logger.info('Starting to download doujinshi: %s' % 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]))
 
-            self.downloader.download(download_queue, self.filename)
-
-            '''
-            for i in range(len(self.ext)):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i+1, EXT_MAP[self.ext[i]]))
-            '''
-
+            self.downloader.download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
         else:
             logger.critical('Downloader has not been loaded')
 

nhentai/downloader.py

@@ -14,6 +14,7 @@ try:
 except ImportError:
     from urlparse import urlparse
 
+from nhentai import constant
 from nhentai.logger import logger
 from nhentai.parser import request
 from nhentai.utils import Singleton
@@ -34,7 +35,7 @@ class Downloader(Singleton):
         self.timeout = timeout
         self.delay = delay
 
-    def download_(self, url, folder='', filename='', retried=0):
+    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))
@@ -51,7 +52,7 @@ class Downloader(Singleton):
                 i = 0
                 while i < 10:
                     try:
-                        response = request('get', url, stream=True, timeout=self.timeout)
+                        response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
                         if response.status_code != 200:
                             raise NHentaiImageNotExistException
 
@@ -77,7 +78,8 @@ 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)
+                return 0, self.download_(url=url, folder=folder, filename=filename,
+                                         retried=retried+1, proxy=proxy)
             else:
                 return 0, None
 
@@ -111,24 +113,29 @@ class Downloader(Singleton):
         else:
             logger.log(15, '{0} downloaded successfully'.format(data))
 
-    def download(self, queue, folder=''):
+    def download(self, queue, folder='', regenerate_cbz=False):
         if not isinstance(folder, text):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
+        if os.path.exists(folder + '.cbz'):
+            if not regenerate_cbz:
+                logger.warning('CBZ file \'{}.cbz\' exists, ignored download request'.format(folder))
+                return
+
         if not os.path.exists(folder):
-            logger.warn('Path \'{0}\' does not exist, creating.'.format(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)))
 
         else:
-            logger.warn('Path \'{0}\' already exist.'.format(folder))
+            logger.warning('Path \'{0}\' already exist.'.format(folder))
 
-        queue = [(self, url, folder) for url in queue]
+        queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
 
         pool = multiprocessing.Pool(self.size, init_worker)
         [pool.apply_async(download_wrapper, args=item) for item in queue]
@@ -137,9 +144,9 @@ class Downloader(Singleton):
         pool.join()
 
 
-def download_wrapper(obj, url, folder=''):
+def download_wrapper(obj, url, folder='', proxy=None):
     if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download_(obj, url=url, folder=folder)
+        return Downloader.download_(obj, url=url, folder=folder, proxy=proxy)
     else:
         return -3, None
 

nhentai/logger.py

@@ -173,7 +173,7 @@ logger.setLevel(logging.DEBUG)
 if __name__ == '__main__':
     logger.log(15, 'nhentai')
     logger.info('info')
-    logger.warn('warn')
+    logger.warning('warning')
     logger.debug('debug')
     logger.error('error')
     logger.critical('critical')

nhentai/parser.py

@@ -126,20 +126,23 @@ def doujinshi_parser(id_):
             return doujinshi_parser(str(id_))
 
     except Exception as e:
-        logger.warn('Error: {}, ignored'.format(str(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/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+                       doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
@@ -174,13 +177,15 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def old_search_parser(keyword, sorting='date', page=1):
+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.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
+    response = request('get', url=constant.LEGACY_SEARCH_URL,
+                       params={'q': keyword, 'page': page, 'sort': sorting}).content
 
     result = _get_title_and_id(response)
     if not result:
-        logger.warn('Not found anything of keyword {}'.format(keyword))
+        logger.warning('Not found anything of keyword {}'.format(keyword))
 
     return result
 
@@ -197,6 +202,7 @@ def print_doujinshi(doujinshi_list):
 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:
         page = [1]
 
@@ -206,6 +212,7 @@ def search_parser(keyword, sorting, page, is_page_all=False):
         page = range(1, init_response['num_pages']+1)
 
     total = '/{0}'.format(page[-1]) if is_page_all else ''
+    not_exists_persist = False
     for p in page:
         i = 0
 
@@ -217,20 +224,23 @@ def search_parser(keyword, sorting, page, is_page_all=False):
                 response = request('get', url.replace('%2B', '+')).json()
             except Exception as e:
                 logger.critical(str(e))
-
+                response = None
             break
 
-        if 'result' not in response:
-            logger.warn('No result in response in page {}'.format(p))
+        if response is None or 'result' not in response:
+            logger.warning('No result in response in page {}'.format(p))
+            if not_exists_persist is True:
                 break
+            continue
 
         for row in response['result']:
             title = row['title']['english']
             title = title[:85] + '..' if len(title) > 85 else title
             result.append({'id': row['id'], 'title': title})
 
+        not_exists_persist = False
         if not result:
-            logger.warn('No results for keywords {}'.format(keyword))
+            logger.warning('No results for keywords {}'.format(keyword))
 
     return result
 

nhentai/serializer.py

@@ -2,6 +2,7 @@
 import json
 import os
 from xml.sax.saxutils import escape
+from nhentai.constant import LANGUAGEISO
 
 
 def serialize_json(doujinshi, dir):
@@ -26,12 +27,12 @@ def serialize_json(doujinshi, dir):
     metadata['Pages'] = doujinshi.pages
 
     with open(os.path.join(dir, 'metadata.json'), 'w') as f:
-        json.dump(metadata, f, separators=','':')
+        json.dump(metadata, f, separators=(',', ':'))
 
 
-def serialize_comicxml(doujinshi, dir):
+def serialize_comic_xml(doujinshi, dir):
     from iso8601 import parse_date
-    with open(os.path.join(dir, 'ComicInfo.xml'), 'w') as f:
+    with open(os.path.join(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')
@@ -45,7 +46,8 @@ def serialize_comicxml(doujinshi, dir):
         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
         xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
 
-        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and 'full color' in doujinshi.info.tags else 'Yes')
+        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and
+                             'full color' in doujinshi.info.tags else 'Yes')
 
         if doujinshi.info.date:
             dt = parse_date(doujinshi.info.date)
@@ -59,13 +61,14 @@ def serialize_comicxml(doujinshi, dir):
         if doujinshi.info.tags:
             xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
         if doujinshi.info.artists:
-            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in doujinshi.info.artists.split(',')]))
-        # if doujinshi.info.groups:
-        #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
+            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in
+                                                          doujinshi.info.artists.split(',')]))
+
         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, 'Language', i) for i in languages if i != 'translated']
+            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGEISO[i]) for i in languages
+                if (i != 'translated' and i in LANGUAGEISO)]
 
         f.write('</ComicInfo>')
 
@@ -120,7 +123,7 @@ def serialize_unique(lst):
 def set_js_database():
     with open('data.js', 'w') as f:
         indexed_json = merge_json()
-        unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
-        indexed_json = json.dumps(indexed_json, separators=','':')
+        unique_json = json.dumps(serialize_unique(indexed_json), separators=(',', ':'))
+        indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)

nhentai/utils.py

@@ -10,24 +10,35 @@ import sqlite3
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
+from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
+
+
+MAX_FIELD_LENGTH = 100
 
 
 def request(method, url, **kwargs):
     session = requests.Session()
     session.headers.update({
         'Referer': constant.LOGIN_URL,
-        'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+        'User-Agent': constant.CONFIG['useragent'],
         'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.CONFIG['proxy'], verify=False, **kwargs)
+
+    if not kwargs.get('proxies', None):
+        kwargs['proxies'] = constant.CONFIG['proxy']
+
+    return getattr(session, method)(url, verify=False, **kwargs)
 
 
 def check_cookie():
-    response = request('get', constant.BASE_URL).text
-    username = re.findall('"/users/\d+/(.*?)"', response)
+    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.error('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
+        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]))
 
@@ -70,6 +81,13 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     else:
         doujinshi_dir = '.'
 
+    if not os.path.exists(doujinshi_dir):
+        logger.warning('Path \'{0}\' does not exist, creating.'.format(doujinshi_dir))
+        try:
+            os.makedirs(doujinshi_dir)
+        except EnvironmentError as e:
+            logger.critical('{0}'.format(str(e)))
+
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
@@ -166,11 +184,11 @@ def generate_main_html(output_dir='./'):
         logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=False):
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True):
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
         if write_comic_info:
-            serialize_comicxml(doujinshi_obj, doujinshi_dir)
+            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
         cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
     else:
         cbz_filename = './doujinshi.cbz'
@@ -194,8 +212,6 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
 def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     try:
         import img2pdf
-    except ImportError:
-        logger.error("Please install img2pdf package by using pip.")
 
         """Write images to a PDF file using img2pdf."""
         if doujinshi_obj is not None:
@@ -223,6 +239,9 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
 
         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 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
@@ -231,7 +250,7 @@ def unicode_truncate(s, length, encoding='utf-8'):
     return encoded.decode(encoding, 'ignore')
 
 
-def format_filename(s):
+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.
     but most doujinshi's names include Japanese 2-byte characters and these was rejected.
@@ -239,16 +258,20 @@ def format_filename(s):
     if filename include forbidden characters (\'/:,;*?"<>|) ,it replace space character(' '). 
     """
     # maybe you can use `--format` to select a suitable filename
+
+    if not _truncate_only:
         ban_chars = '\\\'/:,;*?"<>|\t'
         filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
         filename = ' '.join(filename.split())
-    print(repr(filename))
 
         while filename.endswith('.'):
             filename = filename[:-1]
+    else:
+        filename = s
 
-    if len(filename) > 100:
-        filename = filename[:100] + u'…'
+    # limit `length` chars
+    if len(filename) >= length:
+        filename = filename[:length - 1] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
@@ -280,6 +303,34 @@ def paging(page_string):
     return page_list
 
 
+def generate_metadata_file(output_dir, table, doujinshi_obj=None):
+    logger.info('Writing Metadata Info')
+
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    else:
+        doujinshi_dir = '.'
+
+    logger.info(doujinshi_dir)
+
+    f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
+
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'CIRCLE', 'SCANLATOR',
+              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
+              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR',
+                      'LANGUAGE', 'TAGS', 'URL', 'PAGES']
+
+    for i in range(len(fields)):
+        f.write('{}: '.format(fields[i]))
+        if fields[i] in special_fields:
+            f.write(str(table[special_fields.index(fields[i])][1]))
+        f.write('\n')
+
+    f.close()
+
+
 class DB(object):
     conn = None
     cur = None

nhentai/viewer/minimal/index.html

@@ -0,0 +1,25 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=yes, viewport-fit=cover" />
+    <title>{TITLE}</title>
+    <style>
+{STYLES}
+    </style>
+</head>
+<body>
+
+<nav id="list" hidden=true>
+{IMAGES}</nav>
+
+<div id="image-container">
+    <div id="dest"></div>
+    <span id="page-num"></span>
+</div>
+
+<script>
+{SCRIPTS}
+</script>
+</body>
+</html>

nhentai/viewer/minimal/scripts.js

@@ -0,0 +1,79 @@
+const pages = Array.from(document.querySelectorAll('img.image-item'));
+let currentPage = 0;
+
+function changePage(pageNum) {
+    const previous = pages[currentPage];
+    const current = pages[pageNum];
+
+    if (current == null) {
+        return;
+    }
+    
+    previous.classList.remove('current');
+    current.classList.add('current');
+
+    currentPage = pageNum;
+
+    const display = document.getElementById('dest');
+    display.style.backgroundImage = `url("${current.src}")`;
+
+    scroll(0,0)
+
+    document.getElementById('page-num')
+        .innerText = [
+                (pageNum + 1).toLocaleString(),
+                pages.length.toLocaleString()
+            ].join('\u200a/\u200a');
+}
+
+changePage(0);
+
+document.getElementById('image-container').onclick = event => {
+    const width = document.getElementById('image-container').clientWidth;
+    const clickPos = event.clientX / width;
+
+    if (clickPos < 0.5) {
+        changePage(currentPage - 1);
+    } else {
+        changePage(currentPage + 1);
+    }
+};
+
+document.onkeypress = event => {
+    switch (event.key.toLowerCase()) {
+        // Previous Image
+        case 'w':
+	   scrollBy(0, -40);
+	   break;
+        case 'a':
+            changePage(currentPage - 1);
+            break;
+        // Return to previous page
+        case 'q':
+            window.history.go(-1);
+            break;
+        // Next Image
+        case ' ':
+        case 's':
+	    scrollBy(0, 40);
+            break;
+        case 'd':
+            changePage(currentPage + 1);
+            break;
+    }// remove arrow cause it won't work
+};
+
+document.onkeydown = event =>{
+    switch (event.keyCode) {
+        case 37: //left
+            changePage(currentPage - 1);
+            break;
+        case 38: //up
+            break;
+        case 39: //right
+            changePage(currentPage + 1);
+            break;
+        case 40: //down
+            break;
+    }
+};

nhentai/viewer/minimal/styles.css

@@ -0,0 +1,75 @@
+  
+*, *::after, *::before {
+    box-sizing: border-box;
+}
+
+img {
+    vertical-align: middle;
+}
+
+html, body {
+    display: flex;
+    background-color: #e8e6e6;
+    height: 100%;
+    width: 100%;
+    padding: 0;
+    margin: 0;
+    font-family: sans-serif;
+}
+
+#list {
+    height: 2000px;
+    overflow: scroll;
+    width: 260px;
+    text-align: center;
+}
+
+#list img {
+    width: 200px;
+    padding: 10px;
+    border-radius: 10px;
+    margin: 15px 0;
+    cursor: pointer;
+}
+
+#list img.current {
+    background: #0003;
+}
+
+#image-container {
+    flex: auto;
+    height: 100%;
+    background: rgb(0, 0, 0);
+    color: rgb(100, 100, 100);
+    text-align: center;
+    cursor: pointer;
+    -webkit-user-select: none;
+    user-select: none;
+    position: relative;
+}
+
+#image-container #dest {
+    height: 2000px;
+    width: 100%;
+    background-size: contain;
+    background-repeat: no-repeat;
+    background-position: top;
+    margin-left: auto;
+    margin-right: auto;
+    max-width: 100%;
+    max-height: 100vh;
+    margin: auto;
+}
+
+#image-container #page-num {
+    position: static;
+    font-size: 9pt;
+    left: 10px;
+    bottom: 5px;
+    font-weight: bold;
+    opacity: 0.9;
+    text-shadow: /* Duplicate the same shadow to make it very strong */
+        0 0 2px #222,
+        0 0 2px #222,
+        0 0 2px #222;
+}

requirements.txt

@@ -1,7 +1,6 @@
 requests>=2.5.0
-soupsieve<2.0
+soupsieve
 BeautifulSoup4>=4.0.0
-threadpool>=1.2.7
 tabulate>=0.7.5
 future>=0.15.2
 iso8601 >= 0.1