0.4.17 releases, for #246

Pull/221

.gitignore

@@ -6,3 +6,5 @@ dist/
 .python-version
 .DS_Store
 output/
+venv/
+.vscode/

.travis.yml

@@ -3,18 +3,17 @@ os:
 
 language: python
 python:
-    - 2.7
     - 3.7
+    - 3.8
 
 install:
     - python setup.py install
 
 script:
     - echo 268642 > /tmp/test.txt
-    - nhentai --cookie "csrftoken=xIh7s9d4NB8qSLN7eJZG9064zsV84aHEYFoAU49Ib9anqmoT0pZRw6TIdayLzQuT; sessionid=un101zfgpglsyffdnsm72le4euuisp7t"
+    - nhentai --cookie "_ga=GA1.2.1651446371.1545407218; __cfduid=d0ed34dfb81167d2a51a1d6392c1768a81601380350; csrftoken=KRN0GR1ft86m3HTefpQA99pp6R1Bo7hUs5QxNGOAIuwB5g4EcJj04fwMB8QKgLaB; sessionid=7hzoowox78c90wi5ud5ibphm4axcck7c"
     - nhentai --search umaru
     - nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - nhentai --tag lolicon --sorting popular
     - nhentai -F
     - nhentai --file /tmp/test.txt
     - nhentai --id=152503,146134 --gen-main --output=/tmp/

MANIFEST.in

@@ -1,8 +1,5 @@
 include README.md
 include requirements.txt
-include nhentai/viewer/index.html
-include nhentai/viewer/styles.css
-include nhentai/viewer/scripts.js
-include nhentai/viewer/main.html
-include nhentai/viewer/main.css
-include nhentai/viewer/main.js
+include nhentai/viewer/*
+include nhentai/viewer/default/*
+include nhentai/viewer/minimal/*

README.rst

@@ -19,15 +19,30 @@ nhentai
 
 nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
 
-============
-Installation
-============
+===================
+Manual Installation
+===================
 .. code-block::
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
     python setup.py install
-    
+
+==================
+Installation (pip)
+==================
+Alternatively, install from PyPI with pip:
+
+.. code-block::
+
+           pip install nhentai
+
+For a self-contained installation, use `Pipx <https://github.com/pipxproject/pipx/>`_:
+
+.. code-block::
+
+           pipx install nhentai
+
 =====================
 Installation (Gentoo)
 =====================
@@ -35,7 +50,14 @@ Installation (Gentoo)
 
     layman -fa glicOne
     sudo emerge net-misc/nhentai
+    
+=====================
+Installation (NixOs)
+=====================
+.. code-block::
 
+    nix-env -iA nixos.nhentai
+    
 =====
 Usage
 =====
@@ -50,6 +72,20 @@ Set your nhentai cookie against captcha:
 
     nhentai --cookie "YOUR COOKIE FROM nhentai.net"
 
+**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
+
 Download specified doujinshi:
 
 .. code-block:: bash
@@ -62,53 +98,20 @@ Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
     nhentai --file=doujinshi.txt
 
+Set search default language
+
+.. code-block:: bash
+
+    nhentai --language=english
+
 Search a keyword and download the first page:
 
 .. code-block:: bash
 
     nhentai --search="tomori" --page=1 --download
-
-Download by tag name:
-
-.. code-block:: bash
-
-    nhentai --tag lolicon --download --page=2
-
-Download by language:
-
-.. code-block:: bash
-
-    nhentai --language english --download --page=2
-
-Download by artist name:
-
-.. code-block:: bash
-
-    nhentai --artist henreader --download
-
-Download by character name:
-
-.. code-block:: bash
-
-    nhentai --character "kuro von einsbern" --download
-
-Download by parody name:
-
-.. code-block:: bash
-
-    nhentai --parody "the idolmaster" --download
-
-Download by group name:
-
-.. code-block:: bash
-
-    nhentai --group clesta --download
-
-Download using multiple tags (--tag, --character, --paordy and --group supported):
-
-.. code-block:: bash
-
-    nhentai --tag "lolicon, teasing" --artist "tamano kedama, atte nanakusa"
+    # you also can download by tags and multiple keywords
+    nhentai --search="tag:lolicon, artist:henreader, tag:full color"
+    nhentai --search="lolicon, henreader, full color"
 
 Download your favorites with delay:
 
@@ -128,6 +131,7 @@ Supported doujinshi folder formatter:
 - %t: Doujinshi name
 - %s: Doujinshi subtitle (translated name)
 - %a: Doujinshi authors' name
+- %p: Doujinshi pretty name
 
 
 Other options:
@@ -170,8 +174,9 @@ Other options:
       --no-html             don't generate HTML after downloading
       --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
-                            file.
+                            or PDF file.
 
       # nHentai options
       --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
@@ -183,7 +188,7 @@ nHentai Mirror
 If you want to use a mirror, you should set up a reverse proxy of `nhentai.net` and `i.nhentai.net`.
 For example:
 
-.. code-block:: 
+.. code-block::
 
     i.h.loli.club -> i.nhentai.net
     h.loli.club -> nhentai.net

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.3.8'
+__version__ = '0.4.17'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,8 +1,10 @@
 # coding: utf-8
-from __future__ import print_function
+
 import os
 import sys
+import json
 from optparse import OptionParser
+
 try:
     from itertools import ifilter as filter
 except ImportError:
@@ -13,17 +15,6 @@ from nhentai import __version__
 from nhentai.utils import urlparse, generate_html, generate_main_html, DB
 from nhentai.logger import logger
 
-try:
-    if sys.version_info < (3, 0, 0):
-        import codecs
-        import locale
-        sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
-        sys.stderr = codecs.getwriter(locale.getpreferredencoding())(sys.stderr)
-
-except NameError:
-    # python3
-    pass
-
 
 def banner():
     logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
@@ -35,10 +26,32 @@ def banner():
 ''' % __version__)
 
 
+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.update(json.load(f))
+    except json.JSONDecodeError:
+        logger.error('Failed to load config file.')
+        write_config()
+
+
+def write_config():
+    if not os.path.exists(constant.NHENTAI_HOME):
+        os.mkdir(constant.NHENTAI_HOME)
+
+    with open(constant.NHENTAI_CONFIG_FILE, 'w') as f:
+        f.write(json.dumps(constant.CONFIG))
+
+
 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  nhentai --file [filename]'
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
     # operation options
@@ -50,29 +63,20 @@ def cmd_parser():
     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'])
+    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='',
+    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')
@@ -80,11 +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', '-p', 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('--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',
@@ -95,20 +100,31 @@ def cmd_parser():
                       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 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')
 
     # 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', 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,
+                      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')
+    parser.add_option('--template', dest='viewer_template', action='store',
+                      help='set viewer template', default='')
 
     try:
         sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
-        print()
     except (NameError, TypeError):
         pass
     except UnicodeDecodeError:
@@ -117,12 +133,10 @@ 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.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:
+    if args.main_viewer and not args.id and not args.keyword and not args.favorites:
         generate_main_html()
         exit(0)
 
@@ -133,50 +147,54 @@ def cmd_parser():
         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)
-
+    # --- set config ---
+    if args.cookie is not None:
+        constant.CONFIG['cookie'] = args.cookie
+        write_config()
         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))
+    elif args.useragent is not None:
+        constant.CONFIG['useragent'] = args.useragent
+        write_config()
+        logger.info('Useragent 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', 'socks5', 'socks5h', 'socks4', 'socks4a'):
+            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)
+
+    if args.viewer_template is not None:
+        if not args.viewer_template:
+            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))
+            exit(1)
+        else:
+            constant.CONFIG['template'] = args.viewer_template
+            write_config()
+
+    # --- end set config ---
 
     if args.favorites:
-        if not constant.COOKIE:
+        if not constant.CONFIG['cookie']:
             logger.warning('Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.')
             exit(1)
 
@@ -189,15 +207,12 @@ def cmd_parser():
             _ = [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:
+    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.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:
+    if not args.keyword and not args.id and not args.favorites:
         parser.print_help()
         exit(1)
 
@@ -208,4 +223,8 @@ 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

@@ -1,79 +1,75 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+
+import sys
 import signal
 import platform
 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, tag_parser
+from nhentai.parser import doujinshi_parser, 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, check_cookie, signal_handler, DB
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
+    paging, check_cookie, signal_handler, DB
 
 
 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))
 
-    from nhentai.constant import PROXY
-    # constant.PROXY will be changed after cmd_parser()
-    if PROXY != {}:
-        logger.info('Using proxy: {0}'.format(PROXY))
+    # 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()
 
-    index = 0
     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(options.page_range)
-
-    elif options.tag:
-        doujinshis = tag_parser(options.tag, sorting=options.sorting, max_page=options.max_page)
-
-    elif options.artist:
-        index = 1
-
-    elif options.character:
-        index = 2
-
-    elif options.parody:
-        index = 3
-
-    elif options.group:
-        index = 4
-
-    elif options.language:
-        index = 5
+        doujinshis = favorites_parser(page=page_list)
 
     elif options.keyword:
-        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
+        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
 
-    if index:
-        doujinshis = tag_parser(options.language, max_page=options.max_page, index=index)
-
     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 = set(db.get_all())
+    if options.is_save_download_history:
+        with DB() as db:
+            data = map(int, db.get_all())
 
-            doujinshi_ids = list(set(doujinshi_ids) - data)
+        doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
 
     if doujinshi_ids:
         for i, id_ in enumerate(doujinshi_ids):
@@ -93,17 +89,24 @@ def main():
                                 timeout=options.timeout, delay=options.delay)
 
         for doujinshi in doujinshi_list:
+            if not options.dryrun:
+                doujinshi.downloader = downloader
+                doujinshi.download()
+
+            if options.generate_metadata:
+                table = doujinshi.table
+                generate_metadata_file(options.output_dir, table, doujinshi)
 
-            doujinshi.downloader = downloader
-            doujinshi.download()
             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:
-                generate_html(options.output_dir, doujinshi)
+            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)
@@ -119,6 +122,5 @@ def main():
 
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/constant.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+
 import os
 import tempfile
 
@@ -12,17 +12,10 @@ except ImportError:
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
 __api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
-__api_suspended_SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
 DETAIL_URL = '%s/g' % BASE_URL
-SEARCH_URL = '%s/search/' % BASE_URL
+SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
-TAG_URL = ['%s/tag' % BASE_URL,
-           '%s/artist' % BASE_URL,
-           '%s/character' % BASE_URL,
-           '%s/parody' % BASE_URL,
-           '%s/group' % BASE_URL,
-           '%s/language' % BASE_URL]
 
 TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
 LOGIN_URL = '%s/login/' % BASE_URL
@@ -33,10 +26,20 @@ u = urlparse(BASE_URL)
 IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
 
 NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
-NHENTAI_PROXY = os.path.join(NHENTAI_HOME, 'proxy')
-NHENTAI_COOKIE = os.path.join(NHENTAI_HOME, 'cookie')
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
+NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
-PROXY = {}
+CONFIG = {
+    'proxy': {'http': '', 'https': ''},
+    'cookie': '',
+    'language': '',
+    'template': '',
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
+}
 
-COOKIE = ''
+LANGUAGEISO ={
+    'english' : 'en',
+    'chinese' : 'zh',
+    'japanese' : 'ja',
+    'translated' : 'translated'
+}

nhentai/doujinshi.py

@@ -1,13 +1,11 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
+
 from tabulate import tabulate
-from future.builtins import range
 
 from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
 from nhentai.utils import format_filename
 
-
 EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
@@ -27,8 +25,10 @@ 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
@@ -40,14 +40,12 @@ class Doujinshi(object):
         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('%p', self.pretty_name)
         name_format = name_format.replace('%s', self.info.subtitle)
         self.filename = format_filename(name_format)
 
-    def __repr__(self):
-        return '<Doujinshi: {0}>'.format(self.name)
-
-    def show(self):
-        table = [
+        self.table = [
+            ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
             ["Characters", self.info.characters],
@@ -57,26 +55,25 @@ 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 __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):
         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]))
+                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]]))
-            '''
-
         else:
             logger.critical('Downloader has not been loaded')
 

nhentai/downloader.py

@@ -1,27 +1,26 @@
 # coding: utf-
-from __future__ import unicode_literals, print_function
 
 import multiprocessing
 import signal
 
 from future.builtins import str as text
+import sys
 import os
 import requests
-import threadpool
 import time
-import multiprocessing as mp
 
 try:
     from urllib.parse import urlparse
 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, signal_handler
+from nhentai.utils import Singleton
 
 requests.packages.urllib3.disable_warnings()
-semaphore = mp.Semaphore()
+semaphore = multiprocessing.Semaphore(1)
 
 
 class NHentaiImageNotExistException(Exception):
@@ -36,7 +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))
@@ -53,7 +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
 
@@ -79,7 +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
 
@@ -121,29 +121,27 @@ class Downloader(Singleton):
             folder = os.path.join(self.path, folder)
 
         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)
-
-        for item in queue:
-            pool.apply_async(download_wrapper, args=item, callback=self._download_callback)
+        [pool.apply_async(download_wrapper, args=item) for item in queue]
 
         pool.close()
         pool.join()
 
 
-def download_wrapper(obj, url, folder=''):
-    if semaphore.get_value():
-        return Downloader.download_(obj, url=url, folder=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, proxy=proxy)
     else:
         return -3, None
 

nhentai/logger.py

@@ -1,7 +1,6 @@
 #
 # Copyright (C) 2010-2012 Vinay Sajip. All rights reserved. Licensed under the new BSD license.
 #
-from __future__ import print_function, unicode_literals
 import logging
 import re
 import platform
@@ -174,7 +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

@@ -1,7 +1,5 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
-import sys
 import os
 import re
 import time
@@ -64,7 +62,7 @@ def _get_title_and_id(response):
     return result
 
 
-def favorites_parser(page_range=''):
+def favorites_parser(page=None):
     result = []
     html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
     count = html.find('span', attrs={'class': 'count'})
@@ -78,20 +76,20 @@ def favorites_parser(page_range=''):
         return []
     pages = int(count / 25)
 
-    if pages:
-        pages += 1 if count % (25 * pages) else 0
+    if page:
+        page_range_list = page
     else:
-        pages = 1
+        if pages:
+            pages += 1 if count % (25 * pages) else 0
+        else:
+            pages = 1
 
-    logger.info('You have %d favorites in %d pages.' % (count, pages))
+        logger.info('You have %d favorites in %d pages.' % (count, pages))
 
-    if os.getenv('DEBUG'):
-        pages = 1
+        if os.getenv('DEBUG'):
+            pages = 1
 
-    page_range_list = range(1, pages + 1)
-    if page_range:
-        logger.info('page range is {0}'.format(page_range))
-        page_range_list = page_range_parser(page_range, pages)
+        page_range_list = range(1, pages + 1)
 
     for page in page_range_list:
         try:
@@ -105,32 +103,6 @@ def favorites_parser(page_range=''):
     return result
 
 
-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 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_))
@@ -145,26 +117,32 @@ def doujinshi_parser(id_):
         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.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'}):
@@ -178,12 +156,9 @@ def doujinshi_parser(id_):
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
 
-    pages = 0
-    for _ in doujinshi_info.find_all('div', class_=''):
-        pages = re.search('([\d]+) pages', _.text)
-        if pages:
-            pages = pages.group(1)
-            break
+    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
@@ -192,7 +167,7 @@ def doujinshi_parser(id_):
     for field in information_fields:
         field_name = field.contents[0].strip().strip(':')
         if field_name in needed_fields:
-            data = [sub_field.contents[0].strip() for sub_field in
+            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)
 
@@ -202,13 +177,13 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def search_parser(keyword, sorting='date', page=1):
+def old_search_parser(keyword, sorting='date', page=1):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     response = request('get', url=constant.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
 
@@ -218,96 +193,47 @@ def print_doujinshi(doujinshi_list):
         return
     doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
-    logger.info('Search Result\n' +
+    logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def tag_parser(tag_name, sorting='date', max_page=1, index=0):
+def search_parser(keyword, sorting, page, is_page_all=False):
+    # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     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 = ''
+    if not page:
+        page = [1]
 
-    for p in range(1, max_page + 1):
-        if sys.version_info >= (3, 0, 0):
-            unicode_ = str
-        else:
-            unicode_ = unicode
+    if is_page_all:
+        url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
+        init_response = request('get', url.replace('%2B', '+')).json()
+        page = range(1, init_response['num_pages']+1)
 
-        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)
+    total = '/{0}'.format(page[-1]) if is_page_all else ''
+    for p in page:
+        i = 0
+
+        logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
+        while i < 3:
+            try:
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+                                                                      'page': p, 'sort': sorting}).url
+                response = request('get', url.replace('%2B', '+')).json()
+            except Exception as e:
+                logger.critical(str(e))
+
+            break
+
+        if 'result' not in response:
+            logger.warning('No result in response in page {}'.format(p))
+            break
+
+        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})
 
         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 __api_suspended_search_parser(keyword, sorting, page):
-    logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
-    result = []
-    i = 0
-    while i < 5:
-        try:
-            response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).json()
-        except Exception as e:
-            i += 1
-            if not i < 5:
-                logger.critical(str(e))
-                logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
-                exit(1)
-            continue
-        break
-
-    if 'result' not in response:
-        raise Exception('No result in response')
-
-    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})
-
-    if not result:
-        logger.warn('No results for keywords {}'.format(keyword))
-
-    return result
-
-
-def __api_suspended_tag_parser(tag_id, sorting, max_page=1):
-    logger.info('Searching for doujinshi with tag id {0}'.format(tag_id))
-    result = []
-    response = request('get', url=constant.TAG_API_URL, params={'sort': sorting, 'tag_id': tag_id}).json()
-    page = max_page if max_page <= response['num_pages'] else int(response['num_pages'])
-
-    for i in range(1, page + 1):
-        logger.info('Getting page {} ...'.format(i))
-
-        if page != 1:
-            response = request('get', url=constant.TAG_API_URL,
-                               params={'sort': sorting, 'tag_id': tag_id}).json()
-    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})
-
-    if not result:
-        logger.warn('No results for tag id {}'.format(tag_id))
+            logger.warning('No results for keywords {}'.format(keyword))
 
     return result
 

nhentai/serializer.py

@@ -1,9 +1,11 @@
 # coding: utf-8
 import json
 import os
+from xml.sax.saxutils import escape
+from nhentai.constant import LANGUAGEISO
 
 
-def serialize(doujinshi, dir):
+def serialize_json(doujinshi, dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
     if doujinshi.info.date:
@@ -25,7 +27,54 @@ def serialize(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_comic_xml(doujinshi, dir):
+    from iso8601 import parse_date
+    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')
+
+        xml_write_simple_tag(f, 'Manga', 'Yes')
+
+        xml_write_simple_tag(f, 'Title', doujinshi.name)
+        xml_write_simple_tag(f, 'Summary', doujinshi.info.subtitle)
+        xml_write_simple_tag(f, 'PageCount', doujinshi.pages)
+        xml_write_simple_tag(f, 'URL', doujinshi.url)
+        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')
+
+        if doujinshi.info.date:
+            dt = parse_date(doujinshi.info.date)
+            xml_write_simple_tag(f, 'Year', dt.year)
+            xml_write_simple_tag(f, 'Month', dt.month)
+            xml_write_simple_tag(f, 'Day', dt.day)
+        if doujinshi.info.parodies:
+            xml_write_simple_tag(f, 'Series', doujinshi.info.parodies)
+        if doujinshi.info.characters:
+            xml_write_simple_tag(f, 'Characters', doujinshi.info.characters)
+        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.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)]
+
+        f.write('</ComicInfo>')
+
+
+def xml_write_simple_tag(f, name, val, indent=1):
+    f.write('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
 
 
 def merge_json():
@@ -74,7 +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

@@ -1,10 +1,8 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import sys
 import re
 import os
-import string
 import zipfile
 import shutil
 import requests
@@ -12,24 +10,32 @@ import sqlite3
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize, set_js_database
+from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
 
 
 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)',
-        'Cookie': constant.COOKIE
+        'User-Agent': constant.CONFIG['useragent'],
+        'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.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]))
 
@@ -64,7 +70,7 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None):
+def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     image_html = ''
 
     if doujinshi_obj is not None:
@@ -72,6 +78,13 @@ def generate_html(output_dir='.', doujinshi_obj=None):
     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()
 
@@ -79,14 +92,14 @@ def generate_html(output_dir='.', doujinshi_obj=None):
         if not os.path.splitext(image)[1] in ('.jpg', '.png'):
             continue
 
-        image_html += '<img src="{0}" class="image-item"/>\n'\
+        image_html += '<img src="{0}" class="image-item"/>\n' \
             .format(image)
-    html = readfile('viewer/index.html')
-    css = readfile('viewer/styles.css')
-    js = readfile('viewer/scripts.js')
+    html = readfile('viewer/{}/index.html'.format(template))
+    css = readfile('viewer/{}/styles.css'.format(template))
+    js = readfile('viewer/{}/scripts.js'.format(template))
 
     if doujinshi_obj is not None:
-        serialize(doujinshi_obj, doujinshi_dir)
+        serialize_json(doujinshi_obj, doujinshi_dir)
         name = doujinshi_obj.name
         if sys.version_info < (3, 0):
             name = doujinshi_obj.name.encode('utf-8')
@@ -102,9 +115,9 @@ def generate_html(output_dir='.', doujinshi_obj=None):
             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 write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(15, 'HTML Viewer has been written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
     except Exception as e:
-        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
+        logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
 
 
 def generate_main_html(output_dir='./'):
@@ -150,7 +163,7 @@ def generate_main_html(output_dir='./'):
 
         image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
     if image_html == '':
-        logger.warning('None index.html found, --gen-main paused.')
+        logger.warning('No index.html found, --gen-main paused.')
         return
     try:
         data = main.format(STYLES=css, SCRIPTS=js, PICTURE=image_html)
@@ -160,17 +173,19 @@ def generate_main_html(output_dir='./'):
         else:
             with open('./main.html', 'wb') as f:
                 f.write(data.encode('utf-8'))
-        shutil.copy(os.path.dirname(__file__)+'/viewer/logo.png', './')
+        shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
         set_js_database()
         logger.log(
-            15, 'Main Viewer has been write to \'{0}main.html\''.format(output_dir))
+            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
     except Exception as e:
-        logger.warning('Writen Main Viewer failed ({})'.format(str(e)))
+        logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=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_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'
@@ -188,24 +203,67 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
-    logger.log(15, 'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir))
+    logger.log(15, 'Comic Book CBZ file has been written to \'{0}\''.format(doujinshi_dir))
+
+
+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 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):
-    """Take a string and return a valid filename constructed from the string.
-Uses a whitelist approach: any characters not present in valid_chars are
-removed. Also spaces are replaced with underscores.
+    """
+    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.
+    so it is using blacklist approach now.
+    if filename include forbidden characters (\'/:,;*?"<>|) ,it replace space character(' '). 
+    """
+    # maybe you can use `--format` to select a suitable filename
+    ban_chars = '\\\'/:,;*?"<>|\t'
+    filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
+    filename = ' '.join(filename.split())
 
-Note: this method may produce invalid filenames such as ``, `.` or `..`
-When I use this method I prepend a date string like '2009_01_15_19_46_32_'
-and append a file extension like '.txt', so I avoid the potential of using
-an invalid filename.
+    while filename.endswith('.'):
+        filename = filename[:-1]
 
-"""
-    valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
-    filename = ''.join(c for c in s if c in valid_chars)
     if len(filename) > 100:
-        filename = filename[:100] + '...]'
+        filename = filename[:100] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
@@ -217,6 +275,54 @@ def signal_handler(signal, frame):
     exit(1)
 
 
+def paging(page_string):
+    # 1,3-5,14 -> [1, 3, 4, 5, 14]
+    if not page_string:
+        return []
+
+    page_list = []
+    for i in page_string.split(','):
+        if '-' in i:
+            start, end = i.split('-')
+            if not (start.isdigit() and end.isdigit()):
+                raise Exception('Invalid page number')
+            page_list.extend(list(range(int(start), int(end) + 1)))
+        else:
+            if not i.isdigit():
+                raise Exception('Invalid page number')
+            page_list.append(int(i))
+
+    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/main.css

@@ -148,7 +148,7 @@ blockquote {
   -webkit-user-select: none; /* Safari */
   -khtml-user-select: none; /* Konqueror HTML */
   -moz-user-select: none; /* Old versions of Firefox */
-  ms-user-select: none; /* Internet Explorer/Edge */
+  -ms-user-select: none; /* Internet Explorer/Edge */
   user-select: none;
 }
 
@@ -157,7 +157,7 @@ blockquote {
   padding: 5px 0px 5px 15px;
   text-decoration: none;
   font-size: 15px;
-  color: #0d0d0d9;
+  color: #0d0d0d;
   display: block;
   text-align: left;
 }
@@ -329,4 +329,4 @@ html.theme-black .gallery:hover .caption {
 html.theme-black .caption {
     background-color: #404040;
     color: #d9d9d9
-}
+}

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

@@ -1,6 +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

setup.py

@@ -23,7 +23,7 @@ setup(
 
     author=__author__,
     author_email=__email__,
-    keywords='nhentai, doujinshi',
+    keywords=['nhentai', 'doujinshi', 'downloader'],
     description='nhentai.net doujinshis downloader',
     long_description=long_description(),
     url='https://github.com/RicterZ/nhentai',