0.4.11

fix bugs

.gitignore

@@ -6,3 +6,4 @@ dist/
 .python-version
 .DS_Store
 output/
+venv/

.travis.yml

@@ -3,19 +3,17 @@ os:
 
 language: python
 python:
-    - 2.7
-    - 3.6
-    - 3.5
-    - 3.4
+    - 3.7
+    - 3.8
 
 install:
     - python setup.py install
 
 script:
     - echo 268642 > /tmp/test.txt
-    - NHENTAI=https://nhentai.net nhentai --cookie '__cfduid=da09f237ceb0f51c75980b0b3fda3ce571558179357; _ga=GA1.2.2000087053.1558179358; _gid=GA1.2.717818542.1558179358; csrftoken=iSxrTFOjrujJqauhAqWvTTI9dl3sfWnxdEFoMuqgmlBrbMin5Gj9wJW4r61cmH1X; sessionid=ewuaayfewbzpiukrarx9d52oxwlz2esd'
-    - NHENTAI=https://nhentai.net nhentai --search umaru
-    - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - NHENTAI=https://nhentai.net nhentai --tag lolicon
-    - NHENTAI=https://nhentai.net nhentai -F
-    - NHENTAI=https://nhentai.net nhentai --file /tmp/test.txt
+    - 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 -F
+    - nhentai --file /tmp/test.txt
+    - nhentai --id=152503,146134 --gen-main --output=/tmp/

MANIFEST.in

@@ -1,5 +1,4 @@
-include README.md
-include requirements.txt
-include nhentai/viewer/index.html
-include nhentai/viewer/styles.css
-include nhentai/viewer/scripts.js
+include README.md
+include requirements.txt
+include nhentai/viewer/*
+include nhentai/viewer/default/*

README.rst

@@ -1,186 +1,209 @@
-nhentai
-=======
-
-.. code-block::
-
-           _   _            _        _
-     _ __ | | | | ___ _ __ | |_ __ _(_)
-    | '_ \| |_| |/ _ \ '_ \| __/ _` | |
-    | | | |  _  |  __/ | | | || (_| | |
-    |_| |_|_| |_|\___|_| |_|\__\__,_|_|
-
-
-あなたも変態。 いいね?
-
-|travis|
-|pypi|
-|license|
-
-
-nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
-
-============
-Installation
-============
-.. code-block::
-
-    git clone https://github.com/RicterZ/nhentai
-    cd nhentai
-    python setup.py install
-    
-=====================
-Installation (Gentoo)
-=====================
-.. code-block::
-
-    layman -fa glicOne
-    sudo emerge net-misc/nhentai
-
-=====
-Usage
-=====
-**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--cookie` option to store your cookie.
-*The default download folder will be the path where you run the command (CLI path).*
-
-
-Set your nhentai cookie against captcha:
-
-.. code-block:: bash
-
-    nhentai --cookie 'YOUR COOKIE FROM nhentai.net'
-
-Download specified doujinshi:
-
-.. code-block:: bash
-
-    nhentai --id=123855,123866
-
-Download doujinshi with ids specified in a file (doujinshi ids split by line):
-
-.. code-block:: bash
-
-    nhentai --file=doujinshi.txt
-
-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 your favorites with delay:
-
-.. code-block:: bash
-
-    nhentai --favorites --download --delay 1
-
-Format output doujinshi folder name:
-
-.. code-block:: bash
-
-    nhentai --id 261100 --format '[%i]%s'
-
-Supported doujinshi folder formatter:
-
-- %i: Doujinshi id
-- %t: Doujinshi name
-- %s: Doujinshi subtitle (translated name)
-- %a: Doujinshi authors' name
-
-
-Other options:
-
-.. code-block::
-
-    Options:
-      # Operation options
-      -h, --help            show this help message and exit
-      -D, --download        download doujinshi (for search results)
-      -S, --show            just show the doujinshi information
-
-      # Doujinshi options
-      --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
-
-      # Download options
-      -o OUTPUT_DIR, --output=OUTPUT_DIR
-                            output dir
-      -t THREADS, --threads=THREADS
-                            thread count for downloading doujinshi
-      -T TIMEOUT, --timeout=TIMEOUT
-                            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
-      -f FILE, --file=FILE  read gallery IDs from file.
-      --format=NAME_FORMAT  format the saved folder name
-
-      # Generating options
-      --html                generate a html viewer at current directory
-      --no-html             don't generate HTML after downloading
-      -C, --cbz             generate Comic Book CBZ File
-      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ
-                            file.
-
-      # nHentai options
-      --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
-
-
-==============
-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:: 
-
-    i.h.loli.club -> i.nhentai.net
-    h.loli.club -> nhentai.net
-
-Set `NHENTAI` env var to your nhentai mirror.
-
-.. code-block:: bash
-
-    NHENTAI=http://h.loli.club nhentai --id 123456
-
-
-.. image:: ./images/search.png?raw=true
-    :alt: nhentai
-    :align: center
-.. image:: ./images/download.png?raw=true
-    :alt: nhentai
-    :align: center
-.. image:: ./images/viewer.png?raw=true
-    :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
-
-.. |pypi| image:: https://img.shields.io/pypi/dm/nhentai.svg
-   :target: https://pypi.org/project/nhentai/
-
-.. |license| image:: https://img.shields.io/github/license/ricterz/nhentai.svg
-   :target: https://github.com/RicterZ/nhentai/blob/master/LICENSE
+nhentai
+=======
+
+.. code-block::
+
+           _   _            _        _
+     _ __ | | | | ___ _ __ | |_ __ _(_)
+    | '_ \| |_| |/ _ \ '_ \| __/ _` | |
+    | | | |  _  |  __/ | | | || (_| | |
+    |_| |_|_| |_|\___|_| |_|\__\__,_|_|
+
+
+あなたも変態。 いいね?
+
+|travis|
+|pypi|
+|license|
+
+
+nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
+
+===================
+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)
+=====================
+.. code-block::
+
+    layman -fa glicOne
+    sudo emerge net-misc/nhentai
+
+=====
+Usage
+=====
+**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--cookie` option to store your cookie.
+
+*The default download folder will be the path where you run the command (CLI path).*
+
+
+Set your nhentai cookie against captcha:
+
+.. code-block:: bash
+
+    nhentai --cookie "YOUR COOKIE FROM nhentai.net"
+
+**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
+
+Download specified doujinshi:
+
+.. code-block:: bash
+
+    nhentai --id=123855,123866
+
+Download doujinshi with ids specified in a file (doujinshi ids split by line):
+
+.. code-block:: bash
+
+    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
+    # 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:
+
+.. code-block:: bash
+
+    nhentai --favorites --download --delay 1
+
+Format output doujinshi folder name:
+
+.. code-block:: bash
+
+    nhentai --id 261100 --format '[%i]%s'
+
+Supported doujinshi folder formatter:
+
+- %i: Doujinshi id
+- %t: Doujinshi name
+- %s: Doujinshi subtitle (translated name)
+- %a: Doujinshi authors' name
+
+
+Other options:
+
+.. code-block::
+
+    Options:
+      # Operation options
+      -h, --help            show this help message and exit
+      -D, --download        download doujinshi (for search results)
+      -S, --show            just show the doujinshi information
+
+      # Doujinshi options
+      --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
+
+      # Download options
+      -o OUTPUT_DIR, --output=OUTPUT_DIR
+                            output dir
+      -t THREADS, --threads=THREADS
+                            thread count for downloading doujinshi
+      -T TIMEOUT, --timeout=TIMEOUT
+                            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
+      -f FILE, --file=FILE  read gallery IDs from file.
+      --format=NAME_FORMAT  format the saved folder name
+
+      # Generating options
+      --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
+      -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
+
+
+==============
+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::
+
+    i.h.loli.club -> i.nhentai.net
+    h.loli.club -> nhentai.net
+
+Set `NHENTAI` env var to your nhentai mirror.
+
+.. code-block:: bash
+
+    NHENTAI=http://h.loli.club nhentai --id 123456
+
+
+.. image:: ./images/search.png?raw=true
+    :alt: nhentai
+    :align: center
+.. image:: ./images/download.png?raw=true
+    :alt: nhentai
+    :align: center
+.. image:: ./images/viewer.png?raw=true
+    :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
+
+.. |pypi| image:: https://img.shields.io/pypi/dm/nhentai.svg
+   :target: https://pypi.org/project/nhentai/
+
+.. |license| image:: https://img.shields.io/github/license/ricterz/nhentai.svg
+   :target: https://github.com/RicterZ/nhentai/blob/master/LICENSE

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.3.4'
+__version__ = '0.4.11'
 __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:
@@ -10,20 +12,9 @@ except ImportError:
 
 import nhentai.constant as constant
 from nhentai import __version__
-from nhentai.utils import urlparse, generate_html
+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
@@ -48,19 +61,22 @@ def cmd_parser():
 
     # doujinshi options
     parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
-    parser.add_option('--search', '-s', type='string', dest='keyword', action='store', help='search doujinshi by keyword')
-    parser.add_option('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
+    parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
+                      help='search doujinshi by keyword')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
                       help='list or download your favorites.')
 
     # page options
-    parser.add_option('--page', 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-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')
@@ -68,8 +84,8 @@ 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='',
-                      help='uses a proxy, for example: http://127.0.0.1:1080')
+    parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
+                      help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
     parser.add_option('--file',  '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
                       help='format the saved folder name', default='[%i][%a][%t]')
@@ -79,17 +95,32 @@ def cmd_parser():
                       help='generate a html viewer at current directory')
     parser.add_option('--no-html', dest='is_nohtml', action='store_true',
                       help='don\'t generate HTML after downloading')
+    parser.add_option('--gen-main', dest='main_viewer', action='store_true',
+                      help='generate a main viewer contain all the doujin in the folder')
     parser.add_option('--cbz', '-C', dest='is_cbz', action='store_true',
                       help='generate Comic Book CBZ File')
+    parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
+                      help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
-                      help='remove downloaded doujinshi dir when generated CBZ file.')
+                      help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
                       help='set cookie of nhentai to bypass Google recaptcha')
+    parser.add_option('--language', type='str', dest='language', action='store',
+                      help='set default language to parse doujinshis')
+    parser.add_option('--clean-language', dest='clean_language', action='store_true', default=False,
+                      help='set DEFAULT as language to parse doujinshis')
+    parser.add_option('--save-download-history', dest='is_save_download_history', action='store_true',
+                      default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
+    parser.add_option('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
+                      help='clean download history')
+    parser.add_option('--template', dest='viewer_template', action='store',
+                      help='set viewer template', default='')
 
     try:
-        sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
+        sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
+        print()
     except (NameError, TypeError):
         pass
     except UnicodeDecodeError:
@@ -101,57 +132,79 @@ def cmd_parser():
         generate_html()
         exit(0)
 
-    if os.path.exists(os.path.join(constant.NHENTAI_HOME, 'cookie')):
-        with open(os.path.join(constant.NHENTAI_HOME, '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(os.path.join(constant.NHENTAI_HOME, 'cookie'), 'w') as f:
-                f.write(args.cookie)
-        except Exception as e:
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
-
-        logger.info('Cookie saved.')
+    if args.main_viewer and not args.id and not args.keyword and not args.favorites:
+        generate_main_html()
         exit(0)
 
-    '''
-    if args.login:
-        try:
-            _, _ = args.login.split(':', 1)
-        except ValueError:
-            logger.error('Invalid `username:password` pair.')
-            exit(1)
+    if args.clean_download_history:
+        with DB() as db:
+            db.clean_all()
 
-        if not args.is_download:
-            logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
-    '''
+        logger.info('Download history cleaned.')
+        exit(0)
+
+    # --- set config ---
+    if args.cookie is not None:
+        constant.CONFIG['cookie'] = args.cookie
+        logger.info('Cookie saved.')
+        write_config()
+        exit(0)
+
+    if args.language is not None:
+        constant.CONFIG['language'] = args.language
+        logger.info('Default language now set to \'{0}\''.format(args.language))
+        write_config()
+        exit(0)
+        # TODO: search without language
+
+    if args.proxy:
+        proxy_url = urlparse(args.proxy)
+        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https'):
+            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
+            exit(0)
+        else:
+            constant.CONFIG['proxy'] = {
+                'http': args.proxy,
+                'https': args.proxy,
+            }
+            logger.info('Proxy now set to \'{0}\'.'.format(args.proxy))
+            write_config()
+            exit(0)
+
+    if args.viewer_template:
+        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)
 
     if args.id:
-        _ = map(lambda id_: id_.strip(), args.id.split(','))
-        args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
+        _ = [i.strip() for i in args.id.split(',')]
+        args.id = set(int(i) for i in _ if i.isdigit())
 
     if args.file:
         with open(args.file, 'r') as f:
-            _ = map(lambda id: id.strip(), f.readlines())
-            args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
+            _ = [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.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.favorites:
+    if not args.keyword and not args.id and not  args.favorites:
         parser.print_help()
         exit(1)
 
@@ -162,11 +215,4 @@ def cmd_parser():
         logger.critical('Maximum number of used threads is 15')
         exit(1)
 
-    if args.proxy:
-        proxy_url = urlparse(args.proxy)
-        if proxy_url.scheme not in ('http', 'https'):
-            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
-        else:
-            constant.PROXY = {'http': args.proxy, 'https': args.proxy}
-
     return args

nhentai/command.py

@@ -1,66 +1,105 @@
 #!/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, login
+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
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
+    paging, check_cookie, signal_handler, DB
 
 
 def main():
     banner()
-    logger.info('Using mirror: {0}'.format(BASE_URL))
     options = cmd_parser()
+    logger.info('Using mirror: {0}'.format(BASE_URL))
 
+    # CONFIG['proxy'] will be changed after cmd_parser()
+    if constant.CONFIG['proxy']['http']:
+        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']['http']))
+
+    if not constant.CONFIG['template']:
+        constant.CONFIG['template'] = 'default'
+
+    logger.info('Using viewer template "{}"'.format(constant.CONFIG['template']))
+
+    # check your cookie
+    check_cookie()
+
+    doujinshis = []
     doujinshi_ids = []
     doujinshi_list = []
 
+    page_list = paging(options.page)
+
     if options.favorites:
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshi_ids = favorites_parser()
-
-    elif options.tag:
-        doujinshis = tag_parser(options.tag, max_page=options.max_page)
-        print_doujinshi(doujinshis)
-        if options.is_download and doujinshis:
-            doujinshi_ids = map(lambda d: d['id'], doujinshis)
+        doujinshis = favorites_parser(page=page_list)
 
     elif options.keyword:
-        doujinshis = search_parser(options.keyword, options.page)
-        print_doujinshi(doujinshis)
-        if options.is_download:
-            doujinshi_ids = map(lambda d: d['id'], doujinshis)
+        if constant.CONFIG['language']:
+            logger.info('Using default language: {0}'.format(constant.CONFIG['language']))
+            options.keyword += ' language:{}'.format(constant.CONFIG['language'])
+        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=page_list,
+                                   is_page_all=options.page_all)
 
     elif not doujinshi_ids:
         doujinshi_ids = options.id
 
+    print_doujinshi(doujinshis)
+    if options.is_download and doujinshis:
+        doujinshi_ids = [i['id'] for i in doujinshis]
+
+        if options.is_save_download_history:
+            with DB() as db:
+                data = map(int, db.get_all())
+
+            doujinshi_ids = list(set(doujinshi_ids) - set(data))
+
     if doujinshi_ids:
-        for id_ in doujinshi_ids:
+        for i, id_ in enumerate(doujinshi_ids):
             if options.delay:
                 time.sleep(options.delay)
+
             doujinshi_info = doujinshi_parser(id_)
-            doujinshi_list.append(Doujinshi(name_format=options.name_format, **doujinshi_info))
+
+            if doujinshi_info:
+                doujinshi_list.append(Doujinshi(name_format=options.name_format, **doujinshi_info))
+
+            if (i + 1) % 10 == 0:
+                logger.info('Progress: %d / %d' % (i + 1, len(doujinshi_ids)))
 
     if not options.is_show:
-        downloader = Downloader(path=options.output_dir,
-                                thread=options.threads, timeout=options.timeout, delay=options.delay)
+        downloader = Downloader(path=options.output_dir, size=options.threads,
+                                timeout=options.timeout, delay=options.delay)
 
         for doujinshi in doujinshi_list:
+
             doujinshi.downloader = downloader
             doujinshi.download()
-            if not options.is_nohtml and not options.is_cbz:
-                generate_html(options.output_dir, doujinshi)
+            if options.is_save_download_history:
+                with DB() as db:
+                    db.add_one(doujinshi.id)
+
+            if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
+                generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
             elif options.is_cbz:
                 generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+            elif options.is_pdf:
+                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
+
+        if options.main_viewer:
+            generate_main_html(options.output_dir)
 
         if not platform.system() == 'Windows':
             logger.log(15, '🍻 All done.')
@@ -71,12 +110,12 @@ def main():
         [doujinshi.show() for doujinshi in doujinshi_list]
 
 
-def signal_handler(signal, frame):
-    logger.error('Ctrl-C signal received. Stopping...')
-    exit(1)
-
-
 signal.signal(signal.SIGINT, signal_handler)
 
+
 if __name__ == '__main__':
+    if sys.version_info < (3, 0, 0):
+        logger.error('nhentai now only support Python 3.x')
+        exit(1)
+
     main()

nhentai/constant.py

@@ -1,18 +1,22 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+
 import os
 import tempfile
-from nhentai.utils import urlparse
+
+try:
+    from urlparse import urlparse
+except ImportError:
+    from urllib.parse import urlparse
+
 
 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
 TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
 LOGIN_URL = '%s/login/' % BASE_URL
 CHALLENGE_URL = '%s/challenge' % BASE_URL
@@ -22,7 +26,13 @@ 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_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
+NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
-PROXY = {}
 
-COOKIE = ''
+CONFIG = {
+    'proxy': {'http': '', 'https': ''},
+    'cookie': '',
+    'language': '',
+    'template': '',
+}

nhentai/doujinshi.py

@@ -1,7 +1,6 @@
 # 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
@@ -41,18 +40,19 @@ class Doujinshi(object):
         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 = name_format
+        self.filename = format_filename(name_format)
 
     def __repr__(self):
         return '<Doujinshi: {0}>'.format(self.name)
 
     def show(self):
         table = [
+            ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
-            ["Characters", self.info.character],
+            ["Characters", self.info.characters],
             ["Authors", self.info.artists],
-            ["Language", self.info.language],
+            ["Languages", self.info.languages],
             ["Tags", self.info.tags],
             ["URL", self.url],
             ["Pages", self.pages],

nhentai/downloader.py

@@ -1,9 +1,12 @@
 # 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
 
 try:
@@ -15,27 +18,23 @@ from nhentai.logger import logger
 from nhentai.parser import request
 from nhentai.utils import Singleton
 
-
 requests.packages.urllib3.disable_warnings()
+semaphore = multiprocessing.Semaphore(1)
 
 
-class NhentaiImageNotExistException(Exception):
+class NHentaiImageNotExistException(Exception):
     pass
 
 
 class Downloader(Singleton):
 
-    def __init__(self, path='', thread=1, timeout=30, delay=0):
-        if not isinstance(thread, (int, )) or thread < 1 or thread > 15:
-            raise ValueError('Invalid threads count')
+    def __init__(self, path='', size=5, timeout=30, delay=0):
+        self.size = size
         self.path = str(path)
-        self.thread_count = thread
-        self.threads = []
-        self.thread_pool = None
         self.timeout = timeout
         self.delay = delay
 
-    def _download(self, url, folder='', filename='', retried=0):
+    def download_(self, url, folder='', filename='', retried=0):
         if self.delay:
             time.sleep(self.delay)
         logger.info('Starting to download {0} ...'.format(url))
@@ -54,9 +53,9 @@ class Downloader(Singleton):
                     try:
                         response = request('get', url, stream=True, timeout=self.timeout)
                         if response.status_code != 200:
-                            raise NhentaiImageNotExistException
+                            raise NHentaiImageNotExistException
 
-                    except NhentaiImageNotExistException as e:
+                    except NHentaiImageNotExistException as e:
                         raise e
 
                     except Exception as e:
@@ -78,27 +77,37 @@ 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)
             else:
                 return 0, None
 
-        except NhentaiImageNotExistException as e:
+        except NHentaiImageNotExistException as e:
             os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
             return -1, url
 
         except Exception as e:
+            import traceback
+            traceback.print_stack()
             logger.critical(str(e))
             return 0, None
 
+        except KeyboardInterrupt:
+            return -3, None
+
         return 1, url
 
-    def _download_callback(self, request, result):
+    def _download_callback(self, result):
         result, data = result
         if result == 0:
             logger.warning('fatal errors occurred, ignored')
             # exit(1)
         elif result == -1:
             logger.warning('url {} return status code 404'.format(data))
+        elif result == -2:
+            logger.warning('Ctrl-C pressed, exiting sub processes ...')
+        elif result == -3:
+            # workers wont be run, just pass
+            pass
         else:
             logger.log(15, '{0} downloaded successfully'.format(data))
 
@@ -115,14 +124,32 @@ class Downloader(Singleton):
                 os.makedirs(folder)
             except EnvironmentError as e:
                 logger.critical('{0}'.format(str(e)))
-                exit(1)
+
         else:
             logger.warn('Path \'{0}\' already exist.'.format(folder))
 
-        queue = [([url], {'folder': folder}) for url in queue]
+        queue = [(self, url, folder) for url in queue]
 
-        self.thread_pool = threadpool.ThreadPool(self.thread_count)
-        requests_ = threadpool.makeRequests(self._download, queue, self._download_callback)
-        [self.thread_pool.putRequest(req) for req in requests_]
+        pool = multiprocessing.Pool(self.size, init_worker)
+        [pool.apply_async(download_wrapper, args=item) for item in queue]
 
-        self.thread_pool.wait()
+        pool.close()
+        pool.join()
+
+
+def download_wrapper(obj, url, folder=''):
+    if sys.platform == 'darwin' or semaphore.get_value():
+        return Downloader.download_(obj, url=url, folder=folder)
+    else:
+        return -3, None
+
+
+def init_worker():
+    signal.signal(signal.SIGINT, subprocess_signal)
+
+
+def subprocess_signal(signal, frame):
+    if semaphore.acquire(timeout=1):
+        logger.warning('Ctrl-C pressed, exiting sub processes ...')
+
+    raise KeyboardInterrupt

nhentai/parser.py

@@ -1,34 +1,16 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import os
 import re
-import threadpool
-import requests
 import time
 from bs4 import BeautifulSoup
 from tabulate import tabulate
 
 import nhentai.constant as constant
+from nhentai.utils import request
 from nhentai.logger import logger
 
 
-session = requests.Session()
-session.headers.update({
-    'Referer': constant.LOGIN_URL,
-    'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
-})
-
-
-def request(method, url, **kwargs):
-    global session
-    if not hasattr(session, method):
-        raise AttributeError('\'requests.Session\' object has no attribute \'{0}\''.format(method))
-
-    session.headers.update({'Cookie': constant.COOKIE})
-    return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
-
-
 def _get_csrf_token(content):
     html = BeautifulSoup(content, 'html.parser')
     csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
@@ -66,7 +48,22 @@ def login(username, password):
         exit(2)
 
 
-def favorites_parser():
+def _get_title_and_id(response):
+    result = []
+    html = BeautifulSoup(response, 'html.parser')
+    doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
+    for doujinshi in doujinshi_search_result:
+        doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
+        title = doujinshi_container.text.strip()
+        title = title if len(title) < 85 else title[:82] + '...'
+        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
+        result.append({'id': id_, 'title': title})
+
+    return result
+
+
+def favorites_parser(page=None):
+    result = []
     html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
     count = html.find('span', attrs={'class': 'count'})
     if not count:
@@ -79,30 +76,31 @@ def favorites_parser():
         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
 
-    ret = []
-    doujinshi_id = re.compile('data-id="([\d]+)"')
+        page_range_list = range(1, pages + 1)
 
-    for page in range(1, pages + 1):
+    for page in page_range_list:
         try:
             logger.info('Getting doujinshi ids of page %d' % page)
-            resp = request('get', constant.FAV_URL + '?page=%d' % page).text
-            ids = doujinshi_id.findall(resp)
-            ret.extend(ids)
+            resp = request('get', constant.FAV_URL + '?page=%d' % page).content
 
+            result.extend(_get_title_and_id(resp))
         except Exception as e:
             logger.error('Error: %s, continue', str(e))
 
-    return ret
+    return result
 
 
 def doujinshi_parser(id_):
@@ -119,14 +117,17 @@ 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.critical(str(e))
-        raise SystemExit
+        logger.warn('Error: {}, ignored'.format(str(e)))
+        return None
 
     html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
@@ -138,7 +139,7 @@ def doujinshi_parser(id_):
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
@@ -152,51 +153,88 @@ 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
     information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
-    needed_fields = ['Characters', 'Artists', 'Language', 'Tags']
+    needed_fields = ['Characters', 'Artists', 'Languages', 'Tags', 'Parodies', 'Groups', 'Categories']
     for field in information_fields:
         field_name = field.contents[0].strip().strip(':')
         if field_name in needed_fields:
-            data = [sub_field.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)
 
+    time_field = doujinshi_info.find('time')
+    if time_field.has_attr('datetime'):
+        doujinshi['date'] = time_field['datetime']
     return doujinshi
 
 
-def search_parser(keyword, page):
+def old_search_parser(keyword, sorting='date', page=1):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
-    result = []
-    try:
-        response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page}).content
-    except requests.ConnectionError as e:
-        logger.critical(e)
-        logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
-        raise SystemExit
+    response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
 
-    html = BeautifulSoup(response, 'html.parser')
-    doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
-    for doujinshi in doujinshi_search_result:
-        doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
-        title = doujinshi_container.text.strip()
-        title = title if len(title) < 85 else title[:82] + '...'
-        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
-        result.append({'id': id_, 'title': title})
+    result = _get_title_and_id(response)
     if not result:
         logger.warn('Not found anything of keyword {}'.format(keyword))
 
     return result
 
 
+def print_doujinshi(doujinshi_list):
+    if not doujinshi_list:
+        return
+    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
+    headers = ['id', 'doujinshi']
+    logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
+                tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+
+
+def search_parser(keyword, sorting, page, is_page_all=False):
+    # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
+    result = []
+    if not page:
+        page = [1]
+
+    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)
+
+    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.warn('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.warn('No results for keywords {}'.format(keyword))
+
+    return result
+
+
 def __api_suspended_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
         raise Exception('Doujinshi id({0}) is not valid'.format(id_))
@@ -221,11 +259,11 @@ def __api_suspended_doujinshi_parser(id_):
     doujinshi['name'] = response['title']['english']
     doujinshi['subtitle'] = response['title']['japanese']
     doujinshi['img_id'] = response['media_id']
-    doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))
+    doujinshi['ext'] = ''.join([i['t'] for i in response['images']['pages']])
     doujinshi['pages'] = len(response['images']['pages'])
 
     # gain information of the doujinshi
-    needed_fields = ['character', 'artist', 'language', 'tag']
+    needed_fields = ['character', 'artist', 'language', 'tag', 'parody', 'group', 'category']
     for tag in response['tags']:
         tag_type = tag['type']
         if tag_type in needed_fields:
@@ -244,94 +282,5 @@ def __api_suspended_doujinshi_parser(id_):
     return doujinshi
 
 
-def __api_suspended_search_parser(keyword, 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}).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 print_doujinshi(doujinshi_list):
-    if not doujinshi_list:
-        return
-    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
-    headers = ['id', 'doujinshi']
-    logger.info('Search Result\n' +
-                tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
-
-
-def __api_suspended_tag_parser(tag_id, 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': 'popular', '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': 'popular', '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))
-
-    return result
-
-
-def tag_parser(tag_name, max_page=1):
-    result = []
-    tag_name = tag_name.lower()
-    tag_name = tag_name.replace(' ', '-')
-
-    for p in range(1, max_page + 1):
-        logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
-        response = request('get', url='%s/%s?page=%d' % (constant.TAG_URL, tag_name, p)).content
-
-        html = BeautifulSoup(response, 'html.parser')
-        doujinshi_items = html.find_all('div', attrs={'class': 'gallery'})
-        if not doujinshi_items:
-            logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
-            return
-
-        for i in doujinshi_items:
-            doujinshi_id = i.a.attrs['href'].strip('/g')
-            doujinshi_title = i.a.text.strip()
-            doujinshi_title = doujinshi_title if len(doujinshi_title) < 85 else doujinshi_title[:82] + '...'
-            result.append({'title': doujinshi_title, 'id': doujinshi_id})
-
-    if not result:
-        logger.warn('No results for tag \'{}\''.format(tag_name))
-
-    return result
-
-
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/serializer.py

@@ -0,0 +1,126 @@
+# coding: utf-8
+import json
+import os
+from xml.sax.saxutils import escape
+
+
+def serialize_json(doujinshi, dir):
+    metadata = {'title': doujinshi.name,
+                'subtitle': doujinshi.info.subtitle}
+    if doujinshi.info.date:
+        metadata['upload_date'] = doujinshi.info.date
+    if doujinshi.info.parodies:
+        metadata['parody'] = [i.strip() for i in doujinshi.info.parodies.split(',')]
+    if doujinshi.info.characters:
+        metadata['character'] = [i.strip() for i in doujinshi.info.characters.split(',')]
+    if doujinshi.info.tags:
+        metadata['tag'] = [i.strip() for i in doujinshi.info.tags.split(',')]
+    if doujinshi.info.artists:
+        metadata['artist'] = [i.strip() for i in doujinshi.info.artists.split(',')]
+    if doujinshi.info.groups:
+        metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
+    if doujinshi.info.languages:
+        metadata['language'] = [i.strip() for i in doujinshi.info.languages.split(',')]
+    metadata['category'] = doujinshi.info.categories
+    metadata['URL'] = doujinshi.url
+    metadata['Pages'] = doujinshi.pages
+
+    with open(os.path.join(dir, 'metadata.json'), 'w') as f:
+        json.dump(metadata, f, separators=','':')
+
+
+def serialize_comicxml(doujinshi, dir):
+    from iso8601 import parse_date
+    with open(os.path.join(dir, 'ComicInfo.xml'), 'w') 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.groups:
+        #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.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']
+
+        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():
+    lst = []
+    output_dir = "./"
+    os.chdir(output_dir)
+    doujinshi_dirs = next(os.walk('.'))[1]
+    for folder in doujinshi_dirs:
+        files = os.listdir(folder)
+        if 'metadata.json' not in files:
+            continue
+        data_folder = output_dir + folder + '/' + 'metadata.json'
+        json_file = open(data_folder, 'r')
+        json_dict = json.load(json_file)
+        json_dict['Folder'] = folder
+        lst.append(json_dict)
+    return lst
+
+
+def serialize_unique(lst):
+    dictionary = {}
+    parody = []
+    character = []
+    tag = []
+    artist = []
+    group = []
+    for dic in lst:
+        if 'parody' in dic:
+            parody.extend([i for i in dic['parody']])
+        if 'character' in dic:
+            character.extend([i for i in dic['character']])
+        if 'tag' in dic:
+            tag.extend([i for i in dic['tag']])
+        if 'artist' in dic:
+            artist.extend([i for i in dic['artist']])
+        if 'group' in dic:
+            group.extend([i for i in dic['group']])
+    dictionary['parody'] = list(set(parody))
+    dictionary['character'] = list(set(character))
+    dictionary['tag'] = list(set(tag))
+    dictionary['artist'] = list(set(artist))
+    dictionary['group'] = list(set(group))
+    return dictionary
+
+
+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=','':')
+        f.write('var data = ' + indexed_json)
+        f.write(';\nvar tags = ' + unique_json)

nhentai/utils.py

@@ -1,12 +1,35 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import sys
+import re
 import os
-import string
 import zipfile
 import shutil
+import requests
+import sqlite3
+
+from nhentai import constant
 from nhentai.logger import logger
+from nhentai.serializer import serialize_json, serialize_comicxml, 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.CONFIG['cookie']
+    })
+    return getattr(session, method)(url, proxies=constant.CONFIG['proxy'], verify=False, **kwargs)
+
+
+def check_cookie():
+    response = request('get', constant.BASE_URL).text
+    username = re.findall('"/users/\d+/(.*?)"', response)
+    if not username:
+        logger.error('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
+    else:
+        logger.info('Login successfully! Your username: {}'.format(username[0]))
 
 
 class _Singleton(type):
@@ -39,7 +62,7 @@ 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:
@@ -56,19 +79,19 @@ def generate_html(output_dir='.', doujinshi_obj=None):
 
         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:
-        title = doujinshi_obj.name
+        serialize_json(doujinshi_obj, doujinshi_dir)
+        name = doujinshi_obj.name
         if sys.version_info < (3, 0):
-            title = title.encode('utf-8')
+            name = doujinshi_obj.name.encode('utf-8')
     else:
-        title = 'nHentai HTML Viewer'
+        name = {'title': 'nHentai HTML Viewer'}
 
-    data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
+    data = html.format(TITLE=name, IMAGES=image_html, SCRIPTS=js, STYLES=css)
     try:
         if sys.version_info < (3, 0):
             with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
@@ -77,15 +100,78 @@ 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_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+def generate_main_html(output_dir='./'):
+    """
+    Generate a main html to show all the contain doujinshi.
+    With a link to their `index.html`.
+    Default output folder will be the CLI path.
+    """
+
+    image_html = ''
+
+    main = readfile('viewer/main.html')
+    css = readfile('viewer/main.css')
+    js = readfile('viewer/main.js')
+
+    element = '\n\
+            <div class="gallery-favorite">\n\
+                <div class="gallery">\n\
+                    <a href="./{FOLDER}/index.html" class="cover" style="padding:0 0 141.6% 0"><img\n\
+                            src="./{FOLDER}/{IMAGE}" />\n\
+                        <div class="caption">{TITLE}</div>\n\
+                    </a>\n\
+                </div>\n\
+            </div>\n'
+
+    os.chdir(output_dir)
+    doujinshi_dirs = next(os.walk('.'))[1]
+
+    for folder in doujinshi_dirs:
+        files = os.listdir(folder)
+        files.sort()
+
+        if 'index.html' in files:
+            logger.info('Add doujinshi \'{}\''.format(folder))
+        else:
+            continue
+
+        image = files[0]  # 001.jpg or 001.png
+        if folder is not None:
+            title = folder.replace('_', ' ')
+        else:
+            title = 'nHentai HTML Viewer'
+
+        image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
+    if image_html == '':
+        logger.warning('No index.html found, --gen-main paused.')
+        return
+    try:
+        data = main.format(STYLES=css, SCRIPTS=js, PICTURE=image_html)
+        if sys.version_info < (3, 0):
+            with open('./main.html', 'w') as f:
+                f.write(data)
+        else:
+            with open('./main.html', 'wb') as f:
+                f.write(data.encode('utf-8'))
+        shutil.copy(os.path.dirname(__file__)+'/viewer/logo.png', './')
+        set_js_database()
+        logger.log(
+            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
+    except Exception as e:
+        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):
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '%s.cbz' % doujinshi_obj.id)
+        if write_comic_info:
+            serialize_comicxml(doujinshi_obj, doujinshi_dir)
+        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
     else:
         cbz_filename = './doujinshi.cbz'
         doujinshi_dir = '.'
@@ -102,26 +188,120 @@ 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
+    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:
+        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))
+
+
+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())
+    print(repr(filename))
 
-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)
-    filename = filename.replace(' ', '_')  # I don't like spaces in filenames.
     if len(filename) > 100:
-        filename = filename[:100] + '...]'
+        filename = filename[:100] + u'…'
 
     # Remove [] from filename
-    filename = filename.replace('[]', '')
+    filename = filename.replace('[]', '').strip()
     return filename
+
+
+def signal_handler(signal, frame):
+    logger.error('Ctrl-C signal received. Stopping...')
+    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
+
+
+class DB(object):
+    conn = None
+    cur = None
+
+    def __enter__(self):
+        self.conn = sqlite3.connect(constant.NHENTAI_HISTORY)
+        self.cur = self.conn.cursor()
+        self.cur.execute('CREATE TABLE IF NOT EXISTS download_history (id text)')
+        self.conn.commit()
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.conn.close()
+
+    def clean_all(self):
+        self.cur.execute('DELETE FROM download_history WHERE 1')
+        self.conn.commit()
+
+    def add_one(self, data):
+        self.cur.execute('INSERT INTO download_history VALUES (?)', [data])
+        self.conn.commit()
+
+    def get_all(self):
+        data = self.cur.execute('SELECT id FROM download_history')
+        return [i[0] for i in data]

nhentai/viewer/default/index.html

@@ -2,6 +2,7 @@
 <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}

nhentai/viewer/default/scripts.js

@@ -1,78 +1,85 @@
-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}")`;
-
-    document.getElementById('page-num')
-        .innerText = [
-                (pageNum + 1).toLocaleString(),
-                pages.length.toLocaleString()
-            ].join('\u200a/\u200a');
-}
-
-changePage(0);
-
-document.getElementById('list').onclick = event => {
-    if (pages.includes(event.target)) {
-        changePage(pages.indexOf(event.target));
-    }
-};
-
-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 'a':
-            changePage(currentPage - 1);
-            break;
-
-        // Next Image
-        case ' ':
-        case 'esc': // future close page function
-        case 'enter':
-        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
-            changePage(currentPage - 1);
-            break;
-        case 39: //right
-            changePage(currentPage + 1);
-            break;
-        case 40: //down
-            changePage(currentPage + 1);
-            break;
-    }
+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('list').onclick = event => {
+    if (pages.includes(event.target)) {
+        changePage(pages.indexOf(event.target));
+    }
+};
+
+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/default/styles.css

@@ -1,69 +1,70 @@
-*, *::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: 100%;
-    overflow: auto;
-    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: 100vh;
-    background: #222;
-    color: #fff;
-    text-align: center;
-    cursor: pointer;
-    -webkit-user-select: none;
-    user-select: none;
-    position: relative;
-}
-
-#image-container #dest {
-    height: 100%;
-    width: 100%;
-    background-size: contain;
-    background-repeat: no-repeat;
-    background-position: center;
-}
-
-#image-container #page-num {
-    position: absolute;
-    font-size: 18pt;
-    left: 10px;
-    bottom: 5px;
-    font-weight: bold;
-    opacity: 0.75;
-    text-shadow: /* Duplicate the same shadow to make it very strong */
-        0 0 2px #222,
-        0 0 2px #222,
-        0 0 2px #222;
+  
+*, *::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: 2000px;
+    background: #222;
+    color: #fff;
+    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;
+}
+
+#image-container #page-num {
+    position: static;
+    font-size: 14pt;
+    left: 10px;
+    bottom: 5px;
+    font-weight: bold;
+    opacity: 0.75;
+    text-shadow: /* Duplicate the same shadow to make it very strong */
+        0 0 2px #222,
+        0 0 2px #222,
+        0 0 2px #222;
 }

nhentai/viewer/main.css

@@ -0,0 +1,332 @@
+/*! normalize.css v5.0.0 | MIT License | github.com/necolas/normalize.css */
+/* Original from https://static.nhentai.net/css/main_style.9bb9b703e601.css */
+a {
+    background-color: transparent;
+    -webkit-text-decoration-skip: objects
+}
+
+img {
+    border-style: none
+}
+
+html {
+    box-sizing: border-box
+}
+
+*,:after,:before {
+    box-sizing: inherit
+}
+
+body,html {
+    font-family: 'Noto Sans',sans-serif;
+    font-size: 14px;
+    line-height: 1.42857143;
+    height: 100%;
+    margin: 0;
+    text-align: center;
+    color: #34495e;
+    background-color: #fff;
+    -webkit-font-smoothing: antialiased;
+    -moz-osx-font-smoothing: grayscale
+}
+
+a {
+    text-decoration: none;
+    color: #34495e
+}
+
+blockquote {
+    border: 0
+}
+
+.container {
+    display: block;
+    clear: both;
+    margin-left: 15rem;
+    margin-right: 0.5rem;
+    margin-bottom: 5px;
+    margin-top: 5px;
+    padding: 4px;
+    border-radius: 9px;
+    background-color: #ecf0f1;
+    width: 100% - 15rem;
+    max-width: 1500px
+}
+
+.gallery,.gallery-favorite,.thumb-container {
+    display: inline-block;
+    vertical-align: top
+}
+
+.gallery img,.gallery-favorite img,.thumb-container img {
+    display: block;
+    max-width: 100%;
+    height: auto
+}
+
+@media screen and (min-width: 980px) {
+    .gallery,.gallery-favorite,.thumb-container {
+        width:19%;
+        margin: 3px;
+    }
+}
+
+@media screen and (max-width: 979px) {
+    .gallery,.gallery-favorite,.thumb-container {
+        width:24%;
+        margin: 2px
+    }
+}
+
+@media screen and (max-width: 772px) {
+    .gallery,.gallery-favorite,.thumb-container {
+        width:32%;
+        margin: 1.5px
+    }
+}
+
+@media screen and (max-width: 500px) {
+    .gallery,.gallery-favorite,.thumb-container {
+        width:49%;
+        margin: .5px
+    }
+}
+
+.gallery a,.gallery-favorite a {
+    display: block
+}
+
+.gallery a img,.gallery-favorite a img {
+    position: absolute
+}
+
+.caption {
+    line-height: 15px;
+    left: 0;
+    right: 0;
+    top: 100%;
+    position: absolute;
+    z-index: 10;
+    overflow: hidden;
+    width: 100%;
+    max-height: 34px;
+    padding: 3px;
+    background-color: #fff;
+    font-weight: 700;
+    display: block;
+    text-align: center;
+    text-decoration: none;
+    color: #34495e
+}
+
+.gallery {
+    position: relative;
+    margin-bottom: 3em
+}
+
+.gallery:hover .caption {
+    max-height: 100%;
+    box-shadow: 0 10px 20px rgba(100,100,100,.5)
+}
+
+.gallery-favorite .gallery {
+    width: 100%
+}
+
+.sidenav {
+  height: 100%;
+  width: 15rem;
+  position: fixed;
+  z-index: 1;
+  top: 0;
+  left: 0;
+  background-color: #0d0d0d;
+  overflow: hidden;
+
+  padding-top: 20px;
+  -webkit-touch-callout: none; /* iOS Safari */
+  -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 */
+  user-select: none;
+}
+
+.sidenav a {
+  background-color: #eee;
+  padding: 5px 0px 5px 15px;
+  text-decoration: none;
+  font-size: 15px;
+  color: #0d0d0d;
+  display: block;
+  text-align: left;
+}
+.sidenav img {
+	width:100%;
+	padding: 0px 5px 0px 5px;
+
+}
+
+.sidenav h1 {
+    font-size: 1.5em;
+	margin: 0px 0px 10px;
+}
+
+.sidenav a:hover {
+  color: white;
+  background-color: #EC2754;
+}
+
+.accordion {
+  font-weight: bold;
+  background-color: #eee;
+  color: #444;
+  padding: 10px 0px 5px 8px;
+  width: 100%;
+  border: none;
+  text-align: left;
+  outline: none;
+  font-size: 15px;
+  transition: 0.4s;
+  cursor:pointer;
+}
+
+.accordion:hover {
+  background-color: #ddd;
+}
+
+.accordion.active{
+  background-color:#ddd;
+}
+
+.nav-btn {
+  font-weight: bold;
+  background-color: #eee;
+  color: #444;
+  padding: 8px 8px 5px 9px;
+  width: 100%;
+  border: none;
+  text-align: left;
+  outline: none;
+  font-size: 15px;
+}
+
+.hidden {
+  display:none;
+}
+
+.nav-btn a{
+  font-weight: normal;
+  padding-right: 10px;
+  border-radius: 15px;
+  cursor: crosshair
+}
+
+.options {
+  display:block;
+  padding: 0px 0px 0px 0px;
+  background-color: #eee;
+  max-height: 0;
+  overflow: hidden;
+  transition: max-height 0.2s ease-out;
+  cursor:pointer;
+}
+
+.search{
+  background-color: #eee;
+  padding-right:40px;
+  white-space: nowrap;
+  padding-top: 5px;
+  height:43px;
+
+}
+
+.search input{
+  border-top-right-radius:10px;
+  padding-top:0;
+  padding-bottom:0;
+  font-size:1em;
+  width:100%;
+  height:38px;
+  vertical-align:top;
+}
+
+.btn{
+  border-top-left-radius:10px;
+  color:#fff;
+  font-size:100%;
+  padding: 8px;
+  width:38px;
+  background-color:#ed2553;
+}
+
+#tags{
+    text-align:left;
+    display: flex;
+	width:15rem;
+    justify-content: start;
+	margin: 2px 2px 2px 0px;
+	flex-wrap: wrap;
+}
+
+.btn-2{
+  font-weight:700;
+  padding-right:0.5rem;
+  padding-left:0.5rem;
+  color:#fff;
+  border:0;
+  font-size:100%;
+  height:1.25rem;
+  outline: 0;
+  border-radius: 0.3rem;
+  cursor: pointer;
+  margin:0.15rem;
+  transition: all 1s linear;
+}
+
+.btn-2#parody{
+  background-color: red;
+}
+
+.btn-2#character{
+  background-color: blue;
+}
+
+.btn-2#tag{
+  background-color: green;
+}
+
+.btn-2#artist{
+  background-color: fuchsia;
+}
+
+.btn-2#group{
+  background-color: teal;
+}
+
+.btn-2.hover{
+  filter: saturate(20%)
+}
+
+input,input:focus{
+  border:none;
+  outline:0;
+}
+
+html.theme-black,html.theme-black body {
+    color: #d9d9d9;
+    background-color: #0d0d0d
+}
+
+html.theme-black #thumbnail-container,html.theme-black .container {
+    background-color: #1f1f1f
+}
+
+html.theme-black .gallery:hover .caption {
+    box-shadow: 0 10px 20px rgba(0,0,0,.5)
+}
+
+html.theme-black .caption {
+    background-color: #404040;
+    color: #d9d9d9
+}

nhentai/viewer/main.html

@@ -0,0 +1,51 @@
+<!doctype html>
+<html lang="en" class=" theme-black">
+
+<head>
+    <meta charset="utf-8" />
+    <meta name="theme-color" content="#1f1f1f" />
+    <meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=yes, viewport-fit=cover" />
+    <title>nHentai Viewer</title>
+    <script type="text/javascript" src="data.js"></script>
+        <!-- <link rel="stylesheet" href="./main.css"> -->
+<style>
+{STYLES}
+</style>
+</head>
+
+<body>
+    <div id="content">
+        <nav class="sidenav">
+			<img src="logo.png">
+			<h1>nHentai Viewer</h1>
+                        <button class="accordion">Language</button>
+            <div class="options" id="language">
+                    <a>English</a>
+                    <a>Japanese</a>
+                    <a>Chinese</a>
+            </div>
+			<button class="accordion">Category</button>
+            <div class="options" id ="category">
+                    <a>Doujinshi</a>
+                    <a>Manga</a>
+            </div>
+			<button class="nav-btn hidden">Filters</button>
+			<div class="search">
+				<input autocomplete="off" type="search" id="tagfilter" name="q" value="" autocapitalize="none" required="">
+				<svg class="btn" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="white" d="M505 442.7L405.3 343c-4.5-4.5-10.6-7-17-7H372c27.6-35.3 44-79.7 44-128C416 93.1 322.9 0 208 0S0 93.1 0 208s93.1 208 208 208c48.3 0 92.7-16.4 128-44v16.3c0 6.4 2.5 12.5 7 17l99.7 99.7c9.4 9.4 24.6 9.4 33.9 0l28.3-28.3c9.4-9.4 9.4-24.6.1-34zM208 336c-70.7 0-128-57.2-128-128 0-70.7 57.2-128 128-128 70.7 0 128 57.2 128 128 0 70.7-57.2 128-128 128z"/></svg>
+			<div id="tags">
+			</div>
+		</nav>
+        <div class="container" id="favcontainer">
+
+            {PICTURE}
+
+        </div> <!-- container -->
+
+    </div>
+<script>
+    {SCRIPTS}
+</script>
+</body>
+
+</html>

nhentai/viewer/main.js

@@ -0,0 +1,177 @@
+    //------------------------------------navbar script------------------------------------
+var menu = document.getElementsByClassName("accordion");
+for (var i = 0; i < menu.length; i++) {
+  menu[i].addEventListener("click", function() {
+    var panel = this.nextElementSibling;
+    if (panel.style.maxHeight) {
+	  this.classList.toggle("active");
+      panel.style.maxHeight = null;
+    } else {
+      panel.style.maxHeight = panel.scrollHeight + "px";
+	  this.classList.toggle("active");
+    }
+  });
+}
+var language = document.getElementById("language").children;
+for (var i = 0; i < language.length; i++){
+	language[i].addEventListener("click", function() {
+		toggler = document.getElementById("language")
+		toggler.style.maxHeight = null;
+		document.getElementsByClassName("accordion")[0].classList.toggle("active");
+		filter_maker(this.innerText, "language");
+});
+}
+var category = document.getElementById("category").children;
+for (var i = 0; i < category.length; i++){
+	category[i].addEventListener("click", function() {
+		document.getElementById("category").style.maxHeight = null;
+		document.getElementsByClassName("accordion")[1].classList.toggle("active");
+		filter_maker(this.innerText, "category");
+});
+}
+//-----------------------------------------------------------------------------------
+//----------------------------------Tags Script--------------------------------------
+tag_maker(tags);
+
+var tag = document.getElementsByClassName("btn-2");
+for (var i = 0; i < tag.length; i++){
+	tag[i].addEventListener("click", function() {
+	filter_maker(this.innerText, this.id);
+});
+}
+
+var input = document.getElementById("tagfilter");
+input.addEventListener("input", function() {
+	var tags = document.querySelectorAll(".btn-2");
+	if (this.value.length > 0) {
+        for (var i = 0; i < tags.length; i++) {
+            var tag = tags[i];
+            var nome = tag.innerText;
+            var exp = new RegExp(this.value, "i");;
+            if (exp.test(nome)) {
+                tag.classList.remove("hidden");
+		    }
+			else {
+				tag.classList.add("hidden");
+            }
+        }
+    } else {
+        for (var i = 0; i < tags.length; i++) {
+            var tag = tags[i];
+				tag.classList.add('hidden');
+        }
+    }
+});
+input.addEventListener('keypress', function (e) {
+	enter_search(e, this.value);
+});
+//-----------------------------------------------------------------------------------
+//------------------------------------Functions--------------------------------------
+function enter_search(e, input){
+	var count = 0;
+	var key = e.which || e.keyCode;
+	if (key === 13 && input.length > 0) {
+	  var all_tags = document.getElementById("tags").children;
+	  for(i = 0; i < all_tags.length; i++){
+		if (!all_tags[i].classList.contains("hidden")){
+			count++;
+			var tag_name = all_tags[i].innerText;
+			var tag_id   = all_tags[i].id;
+			if (count>1){break}
+		}
+	  }
+	  if (count == 1){
+		filter_maker(tag_name, tag_id);
+	  }
+	}
+}
+function filter_maker(text, class_value){
+    var check = filter_checker(text);
+	var nav_btn = document.getElementsByClassName("nav-btn")[0];
+	if (nav_btn.classList.contains("hidden")){
+	  nav_btn.classList.toggle("hidden");
+	}
+	if (check == true){
+		var node = document.createElement("a");
+		var textnode = document.createTextNode(text);
+		node.appendChild(textnode);
+		node.classList.add(class_value);
+		nav_btn.appendChild(node);
+		filter_searcher();
+	}
+}
+
+function filter_searcher(){
+	var verifier = null;
+	var tags_filter = [];
+	var doujinshi_id = [];
+	var filter_tag = document.getElementsByClassName("nav-btn")[0].children;
+	filter_tag[filter_tag.length-1].addEventListener("click", function() {
+		this.remove();
+		try{
+			filter_searcher();
+		}
+		catch{
+			var gallery = document.getElementsByClassName("gallery-favorite");
+			for (var i = 0; i < gallery.length; i++){
+				gallery[i].classList.remove("hidden");
+			}
+		}
+	});
+	for (var i=0; i < filter_tag.length; i++){
+		var fclass = filter_tag[i].className;
+		var fname = filter_tag[i].innerText.toLowerCase();
+		tags_filter.push([fclass, fname])
+	}
+	for (var i=0; i < data.length; i++){
+		for (var j=0; j < tags_filter.length; j++){
+			try{
+				if(data[i][tags_filter[j][0]].includes(tags_filter[j][1])){
+					verifier = true;
+				}
+				else{
+					verifier = false;
+					break
+				}
+			}
+			catch{
+				verifier = false;
+					break
+			}
+		}
+		if (verifier){doujinshi_id.push(data[i].Folder);}
+	}
+	var gallery = document.getElementsByClassName("gallery-favorite");
+	for (var i = 0; i < gallery.length; i++){
+		gtext = gallery	[i].children[0].children[0].children[1].innerText;
+		if(doujinshi_id.includes(gtext)){
+			gallery[i].classList.remove("hidden");
+		}
+		else{
+		gallery[i].classList.add("hidden");
+		}
+	}
+}
+
+function filter_checker(text){
+    var filter_tags = document.getElementsByClassName("nav-btn")[0].children;
+	if (filter_tags == null){return true;}
+	for (var i=0; i < filter_tags.length; i++){
+		if (filter_tags[i].innerText == text){return false;}
+	}
+	return true;
+}
+
+function tag_maker(data){
+	for (i in data){
+		for (j in data[i]){
+			var node = document.createElement("button");
+			var textnode = document.createTextNode(data[i][j]);
+			node.appendChild(textnode);
+			node.classList.add("btn-2");
+			node.setAttribute('id', i);
+			node.classList.add("hidden");
+			document.getElementById("tags").appendChild(node);
+		}
+	}
+}

requirements.txt

@@ -1,5 +1,7 @@
 requests>=2.5.0
+soupsieve<2.0
 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',