0.3.6

fix show info

.gitignore

@@ -4,4 +4,5 @@ build
 dist/
 *.egg-info
 .python-version
-
+.DS_Store
+output/

.travis.yml

@@ -1,15 +1,22 @@
 os:
     - linux
-    - os x
 
 language: python
 python:
     - 2.7
-    - 2.6
+    - 3.6
+    - 3.5
+    - 3.4
 
 install:
     - python setup.py install
 
 script:
+    - echo 268642 > /tmp/test.txt
+    - nhentai --cookie "csrftoken=3c4Mzn4f6NAI1awFqfIh495G3pv5Wade9n63Kx03mkSac8c2QR5vRR4jCwVzb3OR; sessionid=m034e2dyyxgbl9s07hbzgfhvadbap2tk"
     - nhentai --search umaru
-    - nhentai --ids=152503,146134 -t 10 --download --path=/tmp/
+    - nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
+    - nhentai --tag lolicon
+    - nhentai -F
+    - nhentai --file /tmp/test.txt
+    - nhentai --id=152503,146134 --gen-main --output=/tmp/

MANIFEST.in

@@ -1,2 +1,7 @@
 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

README.md

@@ -1,51 +0,0 @@
-nhentai
-=======
-           _   _            _        _
-     _ __ | | | | ___ _ __ | |_ __ _(_)
-    | '_ \| |_| |/ _ \ '_ \| __/ _` | |
-    | | | |  _  |  __/ | | | || (_| | |
-    |_| |_|_| |_|\___|_| |_|\__\__,_|_|
-
-あなたも変態。 いいね?  
-
-由于 [http://nhentai.net](http://nhentai.net) 下载下来的种子速度很慢，而且官方也提供在线观看本子的功能，所以可以利用本脚本下载本子。
-### 安装
-
-    git clone https://github.com/RicterZ/nhentai
-    cd nhentai
-    python setup.py install
-    
-
-### 用法
-+ 下载指定 id 的本子：
-
-
-    nhentai --id=123855 --download
-
-
-+ 下载指定 id 列表的本子：
-
-
-    nhentai --ids=123855,123866 --download
-    
-
-+ 下载某关键词第一页的本子（不推荐）：
-
-
-    nhentai --search="tomori" --page=1 --download
-
-
-`-t, --thread` 指定下载的线程数，最多为 10 线程。  
-`--path` 指定下载文件的输出路径，默认为当前目录。  
-`--timeout` 指定下载图片的超时时间，默认为 30 秒。  
-`--proxy` 指定下载的代理，例如: http://127.0.0.1:8080/
-
-
-![](./images/search.png)  
-![](./images/download.png)  
-
-### License  
-MIT
-
-### あなたも変態
-![](./images/image.jpg)

README.rst

@@ -0,0 +1,187 @@
+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

doujinshi.txt

@@ -0,0 +1,5 @@
+184212
+204944
+222460
+244502
+261909

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.1.3'
+__version__ = '0.3.6'
-__author__ = 'Ricter'
+__author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,72 +1,183 @@
 # coding: utf-8
 from __future__ import print_function
+import os
+import sys
 from optparse import OptionParser
-from logger import logger
 try:
     from itertools import ifilter as filter
 except ImportError:
     pass
 
+import nhentai.constant as constant
+from nhentai import __version__
+from nhentai.utils import urlparse, generate_html, generate_main_html
+from nhentai.logger import logger
 
-import constant
+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('''nHentai: あなたも変態。 いいね?
+    logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
        _   _            _        _
  _ __ | | | | ___ _ __ | |_ __ _(_)
 | '_ \| |_| |/ _ \ '_ \| __/ _` | |
 | | | |  _  |  __/ | | | || (_| | |
 |_| |_|_| |_|\___|_| |_|\__\__,_|_|
-''')
+''' % __version__)
 
 
 def cmd_parser():
-    parser = OptionParser()
+    parser = OptionParser('\n  nhentai --search [keyword] --download'
-    parser.add_option('--download', dest='is_download', action='store_true', help='download doujinshi or not')
+                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
-    parser.add_option('--id', type='int', dest='id', action='store', help='doujinshi id of nhentai')
+                          '\n  nhentai --file [filename]'    
-    parser.add_option('--ids', type='str', dest='ids', action='store', help='doujinshi id set, e.g. 1,2,3')
+                          '\n\nEnvironment Variable:\n'
-    parser.add_option('--search', type='string', dest='keyword', action='store', help='keyword searched')
+                          '  NHENTAI                 nhentai mirror url')
+    # operation options
+    parser.add_option('--download', '-D', dest='is_download', action='store_true',
+                      help='download doujinshi (for search results)')
+    parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
+
+    # doujinshi options
+    parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
+    parser.add_option('--search', '-s', type='string', dest='keyword', action='store', help='search doujinshi by keyword')
+    parser.add_option('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
+    parser.add_option('--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 result')
+                      help='page number of search results')
-    parser.add_option('--path', type='string', dest='saved_path', action='store', default='',
+    parser.add_option('--max-page', type='int', dest='max_page', action='store', default=1,
-                      help='path which save the doujinshi')
+                      help='The max page when recursive download tagged doujinshi')
+
+    # download options
+    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='',
+                      help='output dir')
     parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
-                      help='thread count of download doujinshi')
+                      help='thread count for downloading doujinshi')
-    parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
+    parser.add_option('--timeout', '-T', type='int', dest='timeout', action='store', default=30,
-                      help='timeout of download doujinshi')
+                      help='timeout for downloading doujinshi')
-    parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
+    parser.add_option('--delay', '-d', type='int', dest='delay', action='store', default=0,
-                      help='use proxy, example: http://127.0.0.1:1080')
+                      help='slow down between downloading every doujinshi')
-    args, _ = parser.parse_args()
+    parser.add_option('--proxy', '-p', type='string', dest='proxy', action='store', default='',
+                      help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
+    parser.add_option('--file',  '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+    parser.add_option('--format', type='string', dest='name_format', action='store',
+                      help='format the saved folder name', default='[%i][%a][%t]')
 
-    if args.ids:
+    # generate options
-        _ = map(lambda id: id.strip(), args.ids.split(','))
+    parser.add_option('--html', dest='html_viewer', action='store_true',
-        args.ids = set(map(int, filter(lambda id: id.isdigit(), _)))
+                      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('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
+                      help='remove downloaded doujinshi dir when generated CBZ file.')
 
-    if args.is_download and not args.id and not args.ids and not args.keyword:
+    # nhentai options
-        logger.critical('Doujinshi id/ids is required for downloading')
+    parser.add_option('--cookie', type='str', dest='cookie', action='store',
-        parser.print_help()
+                      help='set cookie of nhentai to bypass Google recaptcha')
-        raise SystemExit
+
+    try:
+        sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
+    except (NameError, TypeError):
+        pass
+    except UnicodeDecodeError:
+        exit(0)
+
+    args, _ = parser.parse_args(sys.argv[1:])
+
+    if args.html_viewer:
+        generate_html()
+        exit(0)
+
+    if args.main_viewer and not args.id and not args.keyword and \
+            not args.tag and not args.favorites:
+        generate_main_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.')
+        exit(0)
+
+    if os.path.exists(os.path.join(constant.NHENTAI_HOME, 'proxy')):
+        with open(os.path.join(constant.NHENTAI_HOME, '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(os.path.join(constant.NHENTAI_HOME, 'proxy'), 'w') as f:
+                    f.write(args.proxy)
+        except Exception as e:
+            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
+            exit(1)
+
+        logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
+        exit(0)
+
+    if args.favorites:
+        if not constant.COOKIE:
+            logger.warning('Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.')
+            exit(1)
 
     if args.id:
-        args.ids = (args.id, ) if not args.ids else args.ids
+        _ = map(lambda id_: id_.strip(), args.id.split(','))
+        args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
 
-    if not args.keyword and not args.ids:
+    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(), _)))
+
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and \
+            not args.tag and not args.favorites:
+        logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
-        raise SystemExit
+        exit(1)
+
+    if not args.keyword and not args.id and not args.tag and not args.favorites:
+        parser.print_help()
+        exit(1)
 
     if args.threads <= 0:
         args.threads = 1
-    elif args.threads > 10:
-        logger.critical('Maximum number of used threads is 10')
-        raise SystemExit
 
-    if args.proxy:
+    elif args.threads > 15:
-        import urlparse
+        logger.critical('Maximum number of used threads is 15')
-        proxy_url = urlparse.urlparse(args.proxy)
+        exit(1)
-        if proxy_url.scheme not in ('http', 'https'):
-            logger.error('Invalid protocol \'{}\' of proxy, ignored'.format(proxy_url.scheme))
-        else:
-            constant.PROXY = {proxy_url.scheme: args.proxy}
 
     return args

nhentai/command.py

@@ -1,50 +1,91 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
+from __future__ import unicode_literals, print_function
 import signal
-from cmdline import cmd_parser, banner
+import platform
-from parser import doujinshi_parser, search_parser, print_doujinshi
+import time
-from doujinshi import Doujinshi
+
-from downloader import Downloader
+from nhentai.cmdline import cmd_parser, banner
-from logger import logger
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser, tag_parser, login
+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
 
 
 def main():
     banner()
     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))
+
+    # check your cookie
+    check_cookie()
 
     doujinshi_ids = []
     doujinshi_list = []
 
-    if options.keyword:
+    if options.favorites:
+        if not options.is_download:
+            logger.warning('You do not specify --download option')
+
+        doujinshis = favorites_parser()
+        print_doujinshi(doujinshis)
+        if options.is_download and doujinshis:
+            doujinshi_ids = map(lambda d: d['id'], doujinshis)
+
+    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)
+
+    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)
-    else:
+
-        doujinshi_ids = options.ids
+    elif not doujinshi_ids:
+        doujinshi_ids = options.id
 
     if doujinshi_ids:
-        for id in doujinshi_ids:
+        for id_ in doujinshi_ids:
-            doujinshi_info = doujinshi_parser(id)
+            if options.delay:
-            doujinshi_list.append(Doujinshi(**doujinshi_info))
+                time.sleep(options.delay)
-    else:
+            doujinshi_info = doujinshi_parser(id_)
-        raise SystemExit
+            doujinshi_list.append(Doujinshi(name_format=options.name_format, **doujinshi_info))
+
+    if not options.is_show:
+        downloader = Downloader(path=options.output_dir,
+                                thread=options.threads, timeout=options.timeout, delay=options.delay)
 
-    if options.is_download:
-        downloader = Downloader(path=options.saved_path,
-                                thread=options.threads, timeout=options.timeout)
         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)
+            elif options.is_cbz:
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+        if options.main_viewer:
+            generate_main_html(options.output_dir)
+        if not platform.system() == 'Windows':
+            logger.log(15, '🍻 All done.')
         else:
-        map(lambda doujinshi: doujinshi.show(), doujinshi_list)
+            logger.log(15, 'All done.')
 
-    logger.log(15, u'🍺 All done.')
+    else:
+        [doujinshi.show() for doujinshi in doujinshi_list]
 
 
 def signal_handler(signal, frame):
-    logger.error('Ctrl-C signal received. Quit.')
+    logger.error('Ctrl-C signal received. Stopping...')
-    raise SystemExit
+    exit(1)
 
 
 signal.signal(signal.SIGINT, signal_handler)

nhentai/constant.py

@@ -1,6 +1,33 @@
-SCHEMA = 'http://'
+# coding: utf-8
-URL = '%snhentai.net' % SCHEMA
+from __future__ import unicode_literals, print_function
-DETAIL_URL = '%s/g' % URL
+import os
-SEARCH_URL = '%s/search/' % URL
+import tempfile
-IMAGE_URL = '%si.nhentai.net/galleries' % SCHEMA
+
+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
+
+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
+FAV_URL = '%s/favorites/' % BASE_URL
+
+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')
+
 PROXY = {}
+
+COOKIE = ''

nhentai/doujinshi.py

@@ -1,8 +1,18 @@
 # coding: utf-8
-from __future__ import print_function
+from __future__ import print_function, unicode_literals
 from tabulate import tabulate
-from constant import DETAIL_URL, IMAGE_URL
+from future.builtins import range
-from logger import logger
+
+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',
+    'g': 'gif',
+}
 
 
 class DoujinshiInfo(dict):
@@ -17,7 +27,7 @@ class DoujinshiInfo(dict):
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='jpg', pages=0, **kwargs):
+    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
         self.id = id
         self.img_id = img_id
@@ -27,8 +37,14 @@ class Doujinshi(object):
         self.url = '%s/%d' % (DETAIL_URL, self.id)
         self.info = DoujinshiInfo(**kwargs)
 
+        name_format = name_format.replace('%i', str(self.id))
+        name_format = name_format.replace('%a', self.info.artists)
+        name_format = name_format.replace('%t', self.name)
+        name_format = name_format.replace('%s', self.info.subtitle)
+        self.filename = format_filename(name_format)
+
     def __repr__(self):
-        return '<Doujinshi: {}>'.format(self.name)
+        return '<Doujinshi: {0}>'.format(self.name)
 
     def show(self):
         table = [
@@ -36,22 +52,33 @@ class Doujinshi(object):
             ["Subtitle", self.info.subtitle],
             ["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],
         ]
-        logger.info(u'Print doujinshi information\n{}'.format(tabulate(table)))
+        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
 
     def download(self):
-        logger.info('Start download doujinshi: %s' % self.name)
+        logger.info('Starting to download doujinshi: %s' % self.name)
         if self.downloader:
             download_queue = []
-            for i in xrange(1, self.pages + 1):
+
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext))
+            if len(self.ext) != self.pages:
-            self.downloader.download(download_queue, self.id)
+                logger.warning('Page count and ext count do not equal')
+
+            for i in range(1, min(self.pages, len(self.ext)) + 1):
+                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))
+
+            self.downloader.download(download_queue, self.filename)
+
+            '''
+            for i in range(len(self.ext)):
+                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i+1, EXT_MAP[self.ext[i]]))
+            '''
+
         else:
-            logger.critical('Downloader has not be loaded')
+            logger.critical('Downloader has not been loaded')
 
 
 if __name__ == '__main__':

nhentai/downloader.py

@@ -1,73 +1,123 @@
-# coding: utf-8
+# coding: utf-
+from __future__ import unicode_literals, print_function
+from future.builtins import str as text
 import os
 import requests
 import threadpool
-from urlparse import urlparse
+import time
-from logger import logger
+
-from parser import request
+try:
+    from urllib.parse import urlparse
+except ImportError:
+    from urlparse import urlparse
+
+from nhentai.logger import logger
+from nhentai.parser import request
+from nhentai.utils import Singleton
 
 
-class Downloader(object):
+requests.packages.urllib3.disable_warnings()
-    _instance = None
 
-    def __new__(cls, *args, **kwargs):
-        if not cls._instance:
-            cls._instance = super(Downloader, cls).__new__(cls, *args, **kwargs)
-        return cls._instance
 
-    def __init__(self, path='', thread=1, timeout=30):
+class NhentaiImageNotExistException(Exception):
-        if not isinstance(thread, (int, )) or thread < 1 or thread > 10:
+    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')
         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=False):
+    def _download(self, url, folder='', filename='', retried=0):
-        logger.info('Start downloading: {} ...'.format(url))
+        if self.delay:
+            time.sleep(self.delay)
+        logger.info('Starting to download {0} ...'.format(url))
         filename = filename if filename else os.path.basename(urlparse(url).path)
+        base_filename, extension = os.path.splitext(filename)
+        try:
+            if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
+                logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
+                                                                                extension)))
+                return 1, url
+
+            response = None
+            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
+                i = 0
+                while i < 10:
                     try:
-            with open(os.path.join(folder, filename), "wb") as f:
                         response = request('get', url, stream=True, timeout=self.timeout)
+                        if response.status_code != 200:
+                            raise NhentaiImageNotExistException
+
+                    except NhentaiImageNotExistException as e:
+                        raise e
+
+                    except Exception as e:
+                        i += 1
+                        if not i < 10:
+                            logger.critical(str(e))
+                            return 0, None
+                        continue
+
+                    break
+
                 length = response.headers.get('content-length')
                 if length is None:
                     f.write(response.content)
                 else:
                     for chunk in response.iter_content(2048):
                         f.write(chunk)
-        except requests.HTTPError as e:
+
-            if not retried:
+        except (requests.HTTPError, requests.Timeout) as e:
-                logger.error('Error: {}, retrying'.format(str(e)))
+            if retried < 3:
-                return self._download(url=url, folder=folder, filename=filename, retried=True)
+                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
+                return 0, self._download(url=url, folder=folder, filename=filename, retried=retried+1)
             else:
-                return None
+                return 0, None
+
+        except NhentaiImageNotExistException as e:
+            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            return -1, url
+
         except Exception as e:
             logger.critical(str(e))
-            return None
+            return 0, None
-        return url
+
+        return 1, url
 
     def _download_callback(self, request, result):
-        if not result:
+        result, data = result
-            logger.critical('Too many errors occurred, quit.')
+        if result == 0:
-            raise SystemExit
+            logger.warning('fatal errors occurred, ignored')
-        logger.log(15, '{} download successfully'.format(result))
+            # exit(1)
+        elif result == -1:
+            logger.warning('url {} return status code 404'.format(data))
+        else:
+            logger.log(15, '{0} downloaded successfully'.format(data))
 
     def download(self, queue, folder=''):
-        if not isinstance(folder, (str, unicode)):
+        if not isinstance(folder, text):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
         if not os.path.exists(folder):
-            logger.warn('Path \'{}\' not exist.'.format(folder))
+            logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
-                logger.critical('Error: {}'.format(str(e)))
+                logger.critical('{0}'.format(str(e)))
-                raise SystemExit
+                exit(1)
         else:
-            logger.warn('Path \'{}\' already exist.'.format(folder))
+            logger.warn('Path \'{0}\' already exist.'.format(folder))
 
         queue = [([url], {'folder': folder}) for url in queue]
 

nhentai/logger.py

@@ -1,13 +1,24 @@
-import logging
 #
 # 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 os
 import re
+import platform
 import sys
 
 
+if platform.system() == 'Windows':
+    import ctypes
+    import ctypes.wintypes
+
+    # Reference: https://gist.github.com/vsajip/758430
+    #            https://github.com/ipython/ipython/issues/4252
+    #            https://msdn.microsoft.com/en-us/library/windows/desktop/ms686047%28v=vs.85%29.aspx
+    ctypes.windll.kernel32.SetConsoleTextAttribute.argtypes = [ctypes.wintypes.HANDLE, ctypes.wintypes.WORD]
+    ctypes.windll.kernel32.SetConsoleTextAttribute.restype = ctypes.wintypes.BOOL
+
+
 class ColorizingStreamHandler(logging.StreamHandler):
     # color names to indices
     color_map = {
@@ -22,17 +33,8 @@ class ColorizingStreamHandler(logging.StreamHandler):
     }
 
     # levels to (background, foreground, bold/intense)
-    if os.name == 'nt':
     level_map = {
-            logging.DEBUG: (None, 'white', False),
+        logging.DEBUG: (None, 'blue', False),
-            logging.INFO: (None, 'green', False),
-            logging.WARNING: (None, 'yellow', False),
-            logging.ERROR: (None, 'red', False),
-            logging.CRITICAL: ('red', 'white', False)
-        }
-    else:
-        level_map = {
-            logging.DEBUG: (None, 'white', False),
         logging.INFO: (None, 'green', False),
         logging.WARNING: (None, 'yellow', False),
         logging.ERROR: (None, 'red', False),
@@ -47,7 +49,29 @@ class ColorizingStreamHandler(logging.StreamHandler):
         isatty = getattr(self.stream, 'isatty', None)
         return isatty and isatty() and not self.disable_coloring
 
-    if os.name != 'nt':
+    def emit(self, record):
+        try:
+            message = self.format(record)
+            stream = self.stream
+
+            if not self.is_tty:
+                if message and message[0] == "\r":
+                    message = message[1:]
+                stream.write(message)
+            else:
+                self.output_colorized(message)
+            stream.write(getattr(self, 'terminator', '\n'))
+
+            self.flush()
+        except (KeyboardInterrupt, SystemExit):
+            raise
+        except IOError:
+            pass
+        except:
+            self.handleError(record)
+
+
+    if not platform.system() == 'Windows':
         def output_colorized(self, message):
             self.stream.write(message)
     else:
@@ -65,8 +89,6 @@ class ColorizingStreamHandler(logging.StreamHandler):
         }
 
         def output_colorized(self, message):
-            import ctypes
-
             parts = self.ansi_esc.split(message)
             write = self.stream.write
             h = None
@@ -82,6 +104,9 @@ class ColorizingStreamHandler(logging.StreamHandler):
                 text = parts.pop(0)
 
                 if text:
+                    if sys.version_info < (3, 0, 0):
+                        write(text.encode('utf-8'))
+                    else:
                         write(text)
 
                 if parts:
@@ -135,6 +160,7 @@ class ColorizingStreamHandler(logging.StreamHandler):
         message = logging.StreamHandler.format(self, record)
         return self.colorize(message, record)
 
+
 logging.addLevelName(15, "INFO")
 logger = logging.getLogger('nhentai')
 LOGGER_HANDLER = ColorizingStreamHandler(sys.stdout)

nhentai/parser.py

@@ -1,38 +1,130 @@
 # coding: utf-8
-from __future__ import print_function
+from __future__ import unicode_literals, print_function
-import sys
+
+import os
 import re
+import threadpool
 import requests
+import time
 from bs4 import BeautifulSoup
-import constant
-from logger import logger
 from tabulate import tabulate
 
+import nhentai.constant as constant
+from nhentai.utils import request
+from nhentai.logger import logger
 
-def request(method, url, **kwargs):
-    if not hasattr(requests, method):
-        raise AttributeError('\'requests\' object has no attribute \'{}\''.format(method))
 
-    return requests.__dict__[method](url, proxies=constant.PROXY, **kwargs)
+def _get_csrf_token(content):
+    html = BeautifulSoup(content, 'html.parser')
+    csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
+    if not csrf_token_elem:
+        raise Exception('Cannot find csrf token to login')
+    return csrf_token_elem.attrs['value']
+
+
+def login(username, password):
+    logger.warning('This feature is deprecated, please use --cookie to set your cookie.')
+    csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
+    if os.getenv('DEBUG'):
+        logger.info('Getting CSRF token ...')
+
+    if os.getenv('DEBUG'):
+        logger.info('CSRF token is {}'.format(csrf_token))
+
+    login_dict = {
+        'csrfmiddlewaretoken': csrf_token,
+        'username_or_email': username,
+        'password': password,
+    }
+    resp = request('post', url=constant.LOGIN_URL, data=login_dict)
+
+    if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+        csrf_token = _get_csrf_token(resp.text)
+        resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
+
+    if 'Invalid username/email or password' in resp.text:
+        logger.error('Login failed, please check your username and password')
+        exit(1)
+
+    if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+        logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
+        exit(2)
+
+
+def _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():
+    result = []
+    html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
+    count = html.find('span', attrs={'class': 'count'})
+    if not count:
+        logger.error("Can't get your number of favorited doujins. Did the login failed?")
+        return []
+
+    count = int(count.text.strip('(').strip(')').replace(',', ''))
+    if count == 0:
+        logger.warning('No favorites found')
+        return []
+    pages = int(count / 25)
+
+    if pages:
+        pages += 1 if count % (25 * pages) else 0
+    else:
+        pages = 1
+
+    logger.info('You have %d favorites in %d pages.' % (count, pages))
+
+    if os.getenv('DEBUG'):
+        pages = 1
+
+    for page in range(1, pages + 1):
+        try:
+            logger.info('Getting doujinshi ids of page %d' % page)
+            resp = request('get', constant.FAV_URL + '?page=%d' % page).content
+
+            result.extend(_get_title_and_id(resp))
+        except Exception as e:
+            logger.error('Error: %s, continue', str(e))
+
+    return result
 
 
 def doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({}) is not valid'.format(id_))
+        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
 
     id_ = int(id_)
-    logger.log(15, 'Fetching doujinshi information of id {}'.format(id_))
+    logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{}/{}/'.format(constant.DETAIL_URL, id_)
+    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
 
     try:
-        response = request('get', url).content
+        response = request('get', url)
+        if response.status_code in (200, ):
+            response = response.content
+        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))
-        sys.exit()
+        raise SystemExit
 
-    html = BeautifulSoup(response)
+    html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
@@ -42,12 +134,19 @@ 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)$', doujinshi_cover.a.img['src'])
+    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
+
+    ext = []
+    for i in html.find_all('div', attrs={'class': 'thumb-container'}):
+        _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
+        ext.append(ext_name)
+
     if not img_id:
         logger.critical('Tried yo get image id failed')
-        sys.exit()
+        exit(1)
+
     doujinshi['img_id'] = img_id.group(1)
-    doujinshi['ext'] = img_id.group(2)
+    doujinshi['ext'] = ext
 
     pages = 0
     for _ in doujinshi_info.find_all('div', class_=''):
@@ -59,7 +158,7 @@ def doujinshi_parser(id_):
 
     # 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']
     for field in information_fields:
         field_name = field.contents[0].strip().strip(':')
         if field_name in needed_fields:
@@ -71,8 +170,7 @@ def doujinshi_parser(id_):
 
 
 def search_parser(keyword, page):
-    logger.debug('Searching doujinshis of keyword {}'.format(keyword))
+    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:
@@ -80,24 +178,141 @@ def search_parser(keyword, page):
         logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
         raise SystemExit
 
-    html = BeautifulSoup(response)
+    result = _get_title_and_id(response)
-    doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
+    if not result:
-    for doujinshi in doujinshi_search_result:
+        logger.warn('Not found anything of keyword {}'.format(keyword))
-        doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
+
-        title = doujinshi_container.text.strip()
-        title = (title[:85] + '..') if len(title) > 85 else title
-        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
-        result.append({'id': id_, 'title': title})
     return result
 
 
 def print_doujinshi(doujinshi_list):
     if not doujinshi_list:
         return
-    doujinshi_list = [i.values() for i in doujinshi_list]
+    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 tag_parser(tag_name, max_page=1):
+    result = []
+    tag_name = tag_name.lower()
+    tag_name = tag_name.replace(' ', '-')
+
+    for p in range(1, max_page + 1):
+        logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
+        response = request('get', url='%s/%s/?page=%d' % (constant.TAG_URL, tag_name, p)).content
+
+        result += _get_title_and_id(response)
+        if not result:
+            logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
+            return
+
+    if not result:
+        logger.warn('No results for tag \'{}\''.format(tag_name))
+
+    return result
+
+
+def __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 __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 __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_))
+
+    id_ = int(id_)
+    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
+    doujinshi = dict()
+    doujinshi['id'] = id_
+    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    i = 0
+    while 5 > i:
+        try:
+            response = request('get', url).json()
+        except Exception as e:
+            i += 1
+            if not i < 5:
+                logger.critical(str(e))
+                exit(1)
+            continue
+        break
+
+    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['pages'] = len(response['images']['pages'])
+
+    # gain information of the doujinshi
+    needed_fields = ['character', 'artist', 'language', 'tag']
+    for tag in response['tags']:
+        tag_type = tag['type']
+        if tag_type in needed_fields:
+            if tag_type == 'tag':
+                if tag_type not in doujinshi:
+                    doujinshi[tag_type] = {}
+
+                tag['name'] = tag['name'].replace(' ', '-')
+                tag['name'] = tag['name'].lower()
+                doujinshi[tag_type][tag['name']] = tag['id']
+            elif tag_type not in doujinshi:
+                doujinshi[tag_type] = tag['name']
+            else:
+                doujinshi[tag_type] += ', ' + tag['name']
+
+    return doujinshi
+
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/utils.py

@@ -0,0 +1,209 @@
+# coding: utf-8
+from __future__ import unicode_literals, print_function
+
+import sys
+import re
+import os
+import string
+import zipfile
+import shutil
+import requests
+
+from nhentai import constant
+from nhentai.logger import logger
+
+
+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
+    })
+    return getattr(session, method)(url, proxies=constant.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):
+    """ A metaclass that creates a Singleton base class when called. """
+    _instances = {}
+
+    def __call__(cls, *args, **kwargs):
+        if cls not in cls._instances:
+            cls._instances[cls] = super(_Singleton, cls).__call__(*args, **kwargs)
+        return cls._instances[cls]
+
+
+class Singleton(_Singleton(str('SingletonMeta'), (object,), {})):
+    pass
+
+
+def urlparse(url):
+    try:
+        from urlparse import urlparse
+    except ImportError:
+        from urllib.parse import urlparse
+
+    return urlparse(url)
+
+
+def readfile(path):
+    loc = os.path.dirname(__file__)
+
+    with open(os.path.join(loc, path), 'r') as file:
+        return file.read()
+
+
+def generate_html(output_dir='.', doujinshi_obj=None):
+    image_html = ''
+
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    else:
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    for image in file_list:
+        if not os.path.splitext(image)[1] in ('.jpg', '.png'):
+            continue
+
+        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')
+
+    if doujinshi_obj is not None:
+        title = doujinshi_obj.name
+        if sys.version_info < (3, 0):
+            title = title.encode('utf-8')
+    else:
+        title = 'nHentai HTML Viewer'
+
+    data = html.format(TITLE=title, 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:
+                f.write(data)
+        else:
+            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')))
+    except Exception as e:
+        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
+
+
+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.
+    """
+
+    count = 0
+    image_html = ''
+    main = readfile('viewer/main.html')
+    css = readfile('viewer/main.css')
+    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:
+            count += 1
+            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('None index.html found, --gen-main paused.')
+        return
+    try:
+        data = main.format(STYLES=css, COUNT=count, 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'))
+        logger.log(
+            15, 'Main Viewer has been write to \'{0}main.html\''.format(output_dir))
+    except Exception as e:
+        logger.warning('Writen Main Viewer failed ({})'.format(str(e)))
+
+
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=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, '..'), '{}.cbz'.format(doujinshi_obj.filename))
+    else:
+        cbz_filename = './doujinshi.cbz'
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
+    with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
+        for image in file_list:
+            image_path = os.path.join(doujinshi_dir, image)
+            cbz_pf.write(image_path, image)
+
+    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))
+
+
+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.
+
+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.
+
+"""
+    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] + '...]'
+
+    # Remove [] from filename
+    filename = filename.replace('[]', '')
+    return filename

nhentai/viewer/index.html

@@ -0,0 +1,24 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="UTF-8">
+    <title>{TITLE}</title>
+    <style>
+{STYLES}
+    </style>
+</head>
+<body>
+
+<nav id="list">
+{IMAGES}</nav>
+
+<div id="image-container">
+    <span id="page-num"></span>
+    <div id="dest"></div>
+</div>
+
+<script>
+{SCRIPTS}
+</script>
+</body>
+</html>

nhentai/viewer/main.css

@@ -0,0 +1,255 @@
+/*! normalize.css v5.0.0 | MIT License | github.com/necolas/normalize.css */
+/* Original from https://static.nhentai.net/css/main_style.9bb9b703e601.css */
+html {
+    font-family: sans-serif;
+    line-height: 1.15;
+    -ms-text-size-adjust: 100%;
+    -webkit-text-size-adjust: 100%
+}
+
+body {
+    margin: 0
+}
+
+h1 {
+    font-size: 2em;
+    margin: .67em 0
+}
+
+a {
+    background-color: transparent;
+    -webkit-text-decoration-skip: objects
+}
+
+a:active,a:hover {
+    outline-width: 0
+}
+
+abbr[title] {
+    border-bottom: none;
+    text-decoration: underline;
+    text-decoration: underline dotted
+}
+
+b,strong {
+    font-weight: inherit
+}
+
+b,strong {
+    font-weight: bolder
+}
+
+code,kbd,samp {
+    font-family: monospace,monospace;
+    font-size: 1em
+}
+
+small {
+    font-size: 80%
+}
+
+sub,sup {
+    font-size: 75%;
+    line-height: 0;
+    position: relative;
+    vertical-align: baseline
+}
+
+sub {
+    bottom: -.25em
+}
+
+sup {
+    top: -.5em
+}
+
+img {
+    border-style: none
+}
+
+label {
+    display: block;
+    font-weight: 700;
+    text-align: justify;
+    white-space: nowrap
+}
+
+html {
+    box-sizing: border-box
+}
+
+*,:after,:before {
+    box-sizing: inherit
+}
+
+h1,h2,h3,h4,h5,h6 {
+    font-weight: 700
+}
+
+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
+}
+
+a:hover {
+    text-decoration: none;
+    color: #ed2553
+}
+
+a.count {
+    color: #999
+}
+
+a.bold {
+    font-weight: 700
+}
+
+code {
+    color: #ed2553;
+    border: 1px solid #fbd3dd;
+    background-color: #fef0f3
+}
+
+blockquote {
+    border: 0
+}
+
+.container {
+    display: block;
+    clear: both;
+    margin-left: auto;
+    margin-right: auto;
+    margin-bottom: 10px;
+    margin-top: 10px;
+    padding: 10px;
+    border-radius: 9px;
+    background-color: #ecf0f1;
+    width: 100%;
+    max-width: 1200px
+}
+
+.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;
+        margin-bottom: 8px
+    }
+}
+
+@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%
+}
+
+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 #thumbnail-container .lazyload,html.theme-black .lazyload {
+    background-color: #262626
+}
+
+html.theme-black #thumbnail-container .lazyload-loading,html.theme-black .lazyload-loading {
+    background-color: #2e2e2e
+}
+
+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
+}
+
+html.theme-black code {
+    color: #ed2553;
+    border: none;
+    background-color: #292929
+}

nhentai/viewer/main.html

@@ -0,0 +1,30 @@
+<!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 &raquo; Viewer</title>
+        <!-- <link rel="stylesheet" href="./main.css"> -->
+<style>
+{STYLES}
+</style>
+</head>
+
+<body>
+    <div id="content">
+
+        <h1>Main Folder({COUNT})</h1>
+
+        <div class="container" id="favcontainer">
+
+            {PICTURE}
+
+        </div> <!-- container -->
+
+    </div>
+
+</body>
+
+</html>

nhentai/viewer/scripts.js

@@ -0,0 +1,81 @@
+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 'w':
+        case 'a':
+            changePage(currentPage - 1);
+            break;
+        // Return to previous page
+        case 'q':
+            window.history.go(-1);
+            break;
+        // Next Image
+        case ' ':
+        case 's':
+        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;
+    }
+};

nhentai/viewer/styles.css

@@ -0,0 +1,69 @@
+*, *::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;
+}

requirements.txt

@@ -2,3 +2,4 @@ requests>=2.5.0
 BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
+future>=0.15.2

setup.cfg

@@ -0,0 +1,3 @@
+[metadata]
+description-file = README.md
+

setup.py

@@ -1,9 +1,21 @@
+# coding: utf-8
+from __future__ import print_function, unicode_literals
+import sys
+import codecs
 from setuptools import setup, find_packages
 from nhentai import __version__, __author__, __email__
 
+
 with open('requirements.txt') as f:
     requirements = [l for l in f.read().splitlines() if l]
 
+
+def long_description():
+    with codecs.open('README.rst', 'rb') as readme:
+        if not sys.version_info < (3, 0, 0):
+            return readme.read().decode('utf-8')
+
+
 setup(
     name='nhentai',
     version=__version__,
@@ -13,7 +25,9 @@ setup(
     author_email=__email__,
     keywords='nhentai, doujinshi',
     description='nhentai.net doujinshis downloader',
+    long_description=long_description(),
     url='https://github.com/RicterZ/nhentai',
+    download_url='https://github.com/RicterZ/nhentai/tarball/master',
     include_package_data=True,
     zip_safe=False,