Merge branch 'master' of github.com:RicterZ/nhentai

- call download with `--cbz --rm-origin-dir`, and run command twice.
- user should pass `--regenerate` option to get back origin dir.

.dockerignore

@@ -0,0 +1,10 @@
+.git
+.gitignore
+venv
+*.egg-info
+build
+dist
+images
+LICENSE
+.travis.yml
+.idea

.github/workflows/docker-image.yml

@@ -0,0 +1,27 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [ "master" ]
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    -
+      name: Login to Docker Hub
+      uses: docker/login-action@v2
+      with:
+        username: ${{ secrets.DOCKERHUB_USERNAME }}
+        password: ${{ secrets.DOCKERHUB_TOKEN }}
+    - 
+      name: Build the Docker image
+      uses: docker/build-push-action@v4
+      with:
+        context: .
+        push: true
+        tags: ricterz/nhentai:latest

.gitignore

@@ -7,3 +7,5 @@ dist/
 .DS_Store
 output/
 venv/
+.vscode/
+test-output

.travis.yml

@@ -1,19 +0,0 @@
-os:
-    - linux
-
-language: python
-python:
-    - 3.7
-    - 3.8
-
-install:
-    - python setup.py install
-
-script:
-    - echo 268642 > /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/

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3
+
+WORKDIR /usr/src/nhentai
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+RUN python setup.py install
+
+WORKDIR /output
+ENTRYPOINT ["nhentai"]

MANIFEST.in

@@ -1,4 +1,5 @@
-include README.md
+include README.rst
 include requirements.txt
 include nhentai/viewer/*
 include nhentai/viewer/default/*
+include nhentai/viewer/minimal/*

README.rst

@@ -1,77 +1,108 @@
 nhentai
 =======
 
-.. code-block::
-
-           _   _            _        _
-     _ __ | | | | ___ _ __ | |_ __ _(_)
-    | '_ \| |_| |/ _ \ '_ \| __/ _` | |
-    | | | |  _  |  __/ | | | || (_| | |
-    |_| |_|_| |_|\___|_| |_|\__\__,_|_|
-
-
 あなたも変態。 いいね?
 
 |travis|
 |pypi|
+|version|
 |license|
 
 
-nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
+nhentai is a CLI tool for downloading doujinshi from `nhentai.net <https://nhentai.net>`_
+
+GUI version: `https://github.com/edgar1016/nhentai-GUI <https://github.com/edgar1016/nhentai-GUI>`_
 
 ===================
 Manual Installation
 ===================
+From Github:
+
 .. code-block::
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
     python setup.py install
 
+Build Docker container:
+
+.. code-block::
+
+    git clone https://github.com/RicterZ/nhentai
+    cd nhentai
+    docker build -t nhentai:latest .
+    docker run --rm -it -v ~/Downloads/doujinshi:/output -v ~/.nhentai/:/root/.nhentai nhentai --id 123855
+
 ==================
-Installation (pip)
+Installation
 ==================
-Alternatively, install from PyPI with pip:
+From PyPI with pip:
 
 .. code-block::
 
    pip install nhentai
 
-For a self-contained installation, use `Pipx <https://github.com/pipxproject/pipx/>`_:
+For a self-contained installation, use `pipx <https://github.com/pipxproject/pipx/>`_:
 
 .. code-block::
 
    pipx install nhentai
 
-=====================
-Installation (Gentoo)
-=====================
+Pull from Dockerhub:
+
+.. code-block::
+
+    docker pull ricterz/nhentai
+    docker run --rm -it -v ~/Downloads/doujinshi:/output -v ~/.nhentai/:/root/.nhentai ricterz/nhentai --id 123855
+
+On Gentoo Linux:
+
 .. code-block::
 
     layman -fa glicOne
     sudo emerge net-misc/nhentai
 
+On NixOS:
+
+.. code-block::
+
+    nix-env -iA nixos.nhentai
+    
 =====
 Usage
 =====
-**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--cookie` option to store your cookie.
-
-*The default download folder will be the path where you run the command (CLI path).*
-
-
-Set your nhentai cookie against captcha:
+**⚠️IMPORTANT⚠️**: To bypass the nhentai frequency limit, you should use `--cookie` and `--useragent` options to store your cookie and your user-agent.
 
 .. code-block:: bash
 
+    nhentai --useragent "USER AGENT of YOUR BROWSER"
     nhentai --cookie "YOUR COOKIE FROM nhentai.net"
 
-**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
+**NOTE:**
+
+- The format of the cookie is `"csrftoken=TOKEN; sessionid=ID; cf_clearance=CLOUDFLARE"`
+- `cf_clearance` cookie and useragent must be set if you encounter "blocked by cloudflare captcha" error. Make sure you use the same IP and useragent as when you got it
+
+| To get csrftoken and sessionid, first login to your nhentai account in web browser, then:
+| (Chrome) |ve| |ld| More tools    |ld| Developer tools     |ld| Application |ld| Storage |ld| Cookies |ld| https://nhentai.net
+| (Firefox) |hv| |ld| Web Developer |ld| Web Developer Tools                  |ld| Storage |ld| Cookies |ld| https://nhentai.net
+| 
+
+.. |hv| unicode:: U+2630 .. https://www.compart.com/en/unicode/U+2630
+.. |ve| unicode:: U+22EE .. https://www.compart.com/en/unicode/U+22EE
+.. |ld| unicode:: U+2014 .. https://www.compart.com/en/unicode/U+2014
+
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/usage.png
+    :alt: nhentai
+    :align: center
+
+*The default download folder will be the path where you run the command (%cd% or $PWD).*
 
 Download specified doujinshi:
 
 .. code-block:: bash
 
-    nhentai --id=123855,123866
+    nhentai --id 123855 123866 123877
 
 Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
@@ -112,30 +143,39 @@ Supported doujinshi folder formatter:
 - %t: Doujinshi name
 - %s: Doujinshi subtitle (translated name)
 - %a: Doujinshi authors' name
+- %g: Doujinshi groups name
+- %p: Doujinshi pretty name
+- %ag: Doujinshi authors name or groups name
 
 
 Other options:
 
 .. code-block::
 
+    Usage:
+      nhentai --search [keyword] --download
+      NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]
+      nhentai --file [filename]
+
+    Environment Variable:
+      NHENTAI                 nhentai mirror url
+
     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
+      --id                  doujinshi ids set, e.g. 167680 167681 167682
       -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
+      -F, --favorites       list or download your favorites
+      -a ARTIST, --artist=ARTIST
+                            list doujinshi by artist name
+      --page-all            all search results
+      --page=PAGE, --page-range=PAGE
+                            page number of search results. e.g. 1,2-5,14
+      --sorting=SORTING, --sort=SORTING
+                            sorting of doujinshi (recent / popular /
+                            popular-[today|week])
       -o OUTPUT_DIR, --output=OUTPUT_DIR
                             output dir
       -t THREADS, --threads=THREADS
@@ -144,23 +184,35 @@ Other options:
                             timeout for downloading doujinshi
       -d DELAY, --delay=DELAY
                             slow down between downloading every doujinshi
-      -p PROXY, --proxy=PROXY
-                            uses a proxy, for example: http://127.0.0.1:1080
+      --proxy=PROXY         store a proxy, for example: -p "http://127.0.0.1:1080"
       -f FILE, --file=FILE  read gallery IDs from file.
       --format=NAME_FORMAT  format the saved folder name
-
-      # Generating options
+      --dry-run             Dry run, skip file download
       --html                generate a html viewer at current directory
       --no-html             don't generate HTML after downloading
-      --gen-main            generate a main viewer contain all the doujin in the folder
+      --gen-main            generate a main viewer contain all the doujin in the
+                            folder
       -C, --cbz             generate Comic Book CBZ File
-      -P --pdf              generate PDF file
-      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ
-                            or PDF file.
-
-      # nHentai options
-      --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
-
+      -P, --pdf             generate PDF file
+      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ or
+                            PDF file
+      --move-to-folder      remove files in doujinshi dir then move new file to
+                            folder when generated CBZ or PDF file
+      --meta                generate a metadata file in doujinshi format
+      --regenerate          regenerate the cbz or pdf file if exists
+      --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
+      --useragent=USERAGENT, --user-agent=USERAGENT
+                            set useragent to bypass Cloudflare captcha
+      --language=LANGUAGE   set default language to parse doujinshis
+      --clean-language      set DEFAULT as language to parse doujinshis
+      --save-download-history
+                            save downloaded doujinshis, whose will be skipped if
+                            you re-download them
+      --clean-download-history
+                            clean download history
+      --template=VIEWER_TEMPLATE
+                            set viewer template
+      --legacy              use legacy searching method
 
 ==============
 nHentai Mirror
@@ -171,33 +223,28 @@ For example:
 .. code-block::
 
     i.h.loli.club -> i.nhentai.net
+    i3.h.loli.club -> i3.nhentai.net
+    i5.h.loli.club -> i5.nhentai.net
+    i7.h.loli.club -> i7.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
+    NHENTAI=https://h.loli.club nhentai --id 123456
 
 
-.. image:: ./images/search.png?raw=true
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/search.png
     :alt: nhentai
     :align: center
-.. image:: ./images/download.png?raw=true
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/download.png
     :alt: nhentai
     :align: center
-.. image:: ./images/viewer.png?raw=true
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/viewer.png
     :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
@@ -205,5 +252,8 @@ Set `NHENTAI` env var to your nhentai mirror.
 .. |pypi| image:: https://img.shields.io/pypi/dm/nhentai.svg
    :target: https://pypi.org/project/nhentai/
 
+.. |version| image:: https://img.shields.io/pypi/v/nhentai
+   :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

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

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.14'
+__version__ = '0.5.10'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -3,27 +3,18 @@
 import os
 import sys
 import json
+import nhentai.constant as constant
+
+from urllib.parse import urlparse
 from optparse import OptionParser
 
-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, DB
+from nhentai.utils import generate_html, generate_main_html, DB
 from nhentai.logger import logger
 
 
 def banner():
-    logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
-       _   _            _        _
- _ __ | | | | ___ _ __ | |_ __ _(_)
-| '_ \| |_| |/ _ \ '_ \| __/ _` | |
-| | | |  _  |  __/ | | | || (_| | |
-|_| |_|_| |_|\___|_| |_|\__\__,_|_|
-''' % __version__)
+    logger.debug(f'nHentai ver {__version__}: あなたも変態。 いいね?')
 
 
 def load_config():
@@ -46,11 +37,27 @@ def write_config():
         f.write(json.dumps(constant.CONFIG))
 
 
+def callback(option, opt_str, value, parser):
+    if option == '--id':
+        pass
+    value = []
+
+    for arg in parser.rargs:
+        if arg.isdigit():
+            value.append(int(arg))
+        elif arg.startswith('-'):
+            break
+        else:
+            logger.warning(f'Ignore invalid id {arg}')
+
+    setattr(parser.values, option.dest, value)
+
+
 def cmd_parser():
     load_config()
 
     parser = OptionParser('\n  nhentai --search [keyword] --download'
-                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n  NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]'
                           '\n  nhentai --file [filename]'
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
@@ -60,20 +67,23 @@ def cmd_parser():
     parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
 
     # doujinshi options
-    parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
+    parser.add_option('--id', dest='id', action='callback', callback=callback,
+                      help='doujinshi ids set, e.g. 167680 167681 167682')
     parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
                       help='search doujinshi by keyword')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
-                      help='list or download your favorites.')
+                      help='list or download your favorites')
+    parser.add_option('--artist', '-a', action='store', dest='artist',
+                      help='list doujinshi by artist name')
 
     # page options
     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='',
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='1',
                       help='page number of search results. e.g. 1,2-5,14')
-    parser.add_option('--sorting', dest='sorting', action='store', default='recent',
+    parser.add_option('--sorting', '--sort', dest='sorting', action='store', default='popular',
                       help='sorting of doujinshi (recent / popular / popular-[today|week])',
-                      choices=['recent', 'popular', 'popular-today', 'popular-week'])
+                      choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
     parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='./',
@@ -85,10 +95,11 @@ def cmd_parser():
     parser.add_option('--delay', '-d', type='int', dest='delay', action='store', default=0,
                       help='slow down between downloading every doujinshi')
     parser.add_option('--proxy', type='string', dest='proxy', action='store',
-                      help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
+                      help='store a proxy, for example: -p "http://127.0.0.1:1080"')
     parser.add_option('--file', '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
                       help='format the saved folder name', default='[%i][%a][%t]')
+    parser.add_option('--dry-run', action='store_true', dest='dryrun', help='Dry run, skip file download')
 
     # generate options
     parser.add_option('--html', dest='html_viewer', action='store_true',
@@ -102,11 +113,19 @@ def cmd_parser():
     parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
                       help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
-                      help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
+                      help='remove downloaded doujinshi dir when generated CBZ or PDF file')
+    parser.add_option('--move-to-folder', dest='move_to_folder', action='store_true', default=False,
+                      help='remove files in doujinshi dir then move new file to folder when generated CBZ or PDF file')
+    parser.add_option('--meta', dest='generate_metadata', action='store_true',
+                      help='generate a metadata file in doujinshi format')
+    parser.add_option('--regenerate', dest='regenerate', action='store_true', default=False,
+                      help='regenerate the cbz or pdf file if exists')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
-                      help='set cookie of nhentai to bypass Google recaptcha')
+                      help='set cookie of nhentai to bypass Cloudflare captcha')
+    parser.add_option('--useragent', '--user-agent', type='str', dest='useragent', action='store',
+                      help='set useragent to bypass Cloudflare captcha')
     parser.add_option('--language', type='str', dest='language', action='store',
                       help='set default language to parse doujinshis')
     parser.add_option('--clean-language', dest='clean_language', action='store_true', default=False,
@@ -117,67 +136,67 @@ def cmd_parser():
                       help='clean download history')
     parser.add_option('--template', dest='viewer_template', action='store',
                       help='set viewer template', default='')
-
-    try:
-        sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
-    except (NameError, TypeError):
-        pass
-    except UnicodeDecodeError:
-        exit(0)
+    parser.add_option('--legacy', dest='legacy', action='store_true', default=False,
+                      help='use legacy searching method')
 
     args, _ = parser.parse_args(sys.argv[1:])
 
     if args.html_viewer:
-        generate_html()
-        exit(0)
+        generate_html(template=constant.CONFIG['template'])
+        sys.exit(0)
 
     if args.main_viewer and not args.id and not args.keyword and not args.favorites:
         generate_main_html()
-        exit(0)
+        sys.exit(0)
 
     if args.clean_download_history:
         with DB() as db:
             db.clean_all()
 
         logger.info('Download history cleaned.')
-        exit(0)
+        sys.exit(0)
 
     # --- set config ---
     if args.cookie is not None:
         constant.CONFIG['cookie'] = args.cookie
+        write_config()
         logger.info('Cookie saved.')
+        sys.exit(0)
+    elif args.useragent is not None:
+        constant.CONFIG['useragent'] = args.useragent
         write_config()
-        exit(0)
-
-    if args.language is not None:
+        logger.info('User-Agent saved.')
+        sys.exit(0)
+    elif 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)
+        logger.info(f'Default language now set to "{args.language}"')
+        sys.exit(0)
         # TODO: search without language
 
     if args.proxy is not None:
         proxy_url = urlparse(args.proxy)
-        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https'):
-            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
-            exit(0)
+        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h',
+                                                             'socks4', 'socks4a'):
+            logger.error(f'Invalid protocol "{proxy_url.scheme}" of proxy, ignored')
+            sys.exit(0)
         else:
             constant.CONFIG['proxy'] = {
                 'http': args.proxy,
                 'https': args.proxy,
             }
-            logger.info('Proxy now set to \'{0}\'.'.format(args.proxy))
+            logger.info(f'Proxy now set to "{args.proxy}"')
             write_config()
-            exit(0)
+            sys.exit(0)
 
     if args.viewer_template is not None:
         if not args.viewer_template:
             args.viewer_template = 'default'
 
         if not os.path.exists(os.path.join(os.path.dirname(__file__),
-                                           'viewer/{}/index.html'.format(args.viewer_template))):
-            logger.error('Template \'{}\' does not exists'.format(args.viewer_template))
-            exit(1)
+                                           f'viewer/{args.viewer_template}/index.html')):
+            logger.error(f'Template "{args.viewer_template}" does not exists')
+            sys.exit(1)
         else:
             constant.CONFIG['template'] = args.viewer_template
             write_config()
@@ -187,31 +206,31 @@ def cmd_parser():
     if args.favorites:
         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:
-        _ = [i.strip() for i in args.id.split(',')]
-        args.id = set(int(i) for i in _ if i.isdigit())
+            sys.exit(1)
 
     if args.file:
         with open(args.file, 'r') as f:
             _ = [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.favorites:
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites and not args.artist:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
-        exit(1)
+        sys.exit(1)
 
-    if not args.keyword and not args.id and not  args.favorites:
+    if not args.keyword and not args.id and not args.favorites and not args.artist:
         parser.print_help()
-        exit(1)
+        sys.exit(1)
 
     if args.threads <= 0:
         args.threads = 1
 
     elif args.threads > 15:
         logger.critical('Maximum number of used threads is 15')
-        exit(1)
+        sys.exit(1)
+
+    if args.dryrun and (args.is_cbz or args.is_pdf):
+        logger.critical('Cannot generate PDF or CBZ during dry-run')
+        sys.exit(1)
 
     return args

nhentai/command.py

@@ -1,20 +1,20 @@
-#!/usr/bin/env python2.7
 # coding: utf-8
-
+import os
+import shutil
 import sys
 import signal
 import platform
-import time
+import urllib3.exceptions
 
 from nhentai import constant
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser
+from nhentai.parser import doujinshi_parser, search_parser, legacy_search_parser, print_doujinshi, favorites_parser
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
-    paging, check_cookie, signal_handler, DB
+from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata_file, \
+    paging, check_cookie, signal_handler, DB, move_to_folder
 
 
 def main():
@@ -22,26 +22,25 @@ def main():
 
     if sys.version_info < (3, 0, 0):
         logger.error('nhentai now only support Python 3.x')
-        exit(1)
+        sys.exit(1)
 
     options = cmd_parser()
-    logger.info('Using mirror: {0}'.format(BASE_URL))
+    logger.info(f'Using mirror: {BASE_URL}')
 
     # CONFIG['proxy'] will be changed after cmd_parser()
     if constant.CONFIG['proxy']['http']:
-        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']['http']))
+        logger.info(f'Using proxy: {constant.CONFIG["proxy"]["http"]}')
 
     if not constant.CONFIG['template']:
         constant.CONFIG['template'] = 'default'
 
-    logger.info('Using viewer template "{}"'.format(constant.CONFIG['template']))
+    logger.info(f'Using viewer template "{constant.CONFIG["template"]}"')
 
     # check your cookie
     check_cookie()
 
     doujinshis = []
     doujinshi_ids = []
-    doujinshi_list = []
 
     page_list = paging(options.page)
 
@@ -49,15 +48,21 @@ def main():
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshis = favorites_parser(page=page_list)
+        doujinshis = favorites_parser() if options.page_all else favorites_parser(page=page_list)
 
     elif options.keyword:
         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,
+            logger.info(f'Using default language: {constant.CONFIG["language"]}')
+            options.keyword += f' language:{constant.CONFIG["language"]}'
+
+        _search_parser = legacy_search_parser if options.legacy else search_parser
+        doujinshis = _search_parser(options.keyword, sorting=options.sorting, page=page_list,
                                     is_page_all=options.page_all)
 
+    elif options.artist:
+        doujinshis = legacy_search_parser(options.artist, sorting=options.sorting, page=page_list,
+                                          is_page_all=options.page_all, type_='ARTIST')
+
     elif not doujinshi_ids:
         doujinshi_ids = options.id
 
@@ -69,54 +74,76 @@ def main():
         with DB() as db:
             data = map(int, db.get_all())
 
-            doujinshi_ids = list(set(doujinshi_ids) - set(data))
-
-    if doujinshi_ids:
-        for i, id_ in enumerate(doujinshi_ids):
-            if options.delay:
-                time.sleep(options.delay)
-
-            doujinshi_info = doujinshi_parser(id_)
-
-            if doujinshi_info:
-                doujinshi_list.append(Doujinshi(name_format=options.name_format, **doujinshi_info))
-
-            if (i + 1) % 10 == 0:
-                logger.info('Progress: %d / %d' % (i + 1, len(doujinshi_ids)))
+        doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
 
     if not options.is_show:
         downloader = Downloader(path=options.output_dir, size=options.threads,
                                 timeout=options.timeout, delay=options.delay)
 
-        for doujinshi in doujinshi_list:
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
 
+            if not options.dryrun:
                 doujinshi.downloader = downloader
+
+                if doujinshi.check_if_need_download(options):
                     doujinshi.download()
+                else:
+                    logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {doujinshi.name}')
+                    continue
+
+            if options.generate_metadata:
+                generate_metadata_file(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:
+            if not options.is_nohtml:
                 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.is_cbz:
+                generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
+
+            if options.is_pdf:
+                generate_doc('pdf', options.output_dir, doujinshi, options.regenerate)
+
+            if options.move_to_folder:
+                if options.is_cbz:
+                    move_to_folder(options.output_dir, doujinshi, 'cbz')
+                if options.is_pdf:
+                    move_to_folder(options.output_dir, doujinshi, 'pdf')
+
+            if options.rm_origin_dir:
+                if options.move_to_folder:
+                    logger.critical('You specified both --move-to-folder and --rm-origin-dir options, '
+                                    'you will not get anything :(')
+                shutil.rmtree(os.path.join(options.output_dir, doujinshi.filename), ignore_errors=True)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)
 
         if not platform.system() == 'Windows':
-            logger.log(15, '🍻 All done.')
+            logger.log(16, '🍻 All done.')
         else:
-            logger.log(15, 'All done.')
+            logger.log(16, 'All done.')
 
     else:
-        [doujinshi.show() for doujinshi in doujinshi_list]
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
+            doujinshi.show()
 
 
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/constant.py

@@ -1,38 +1,66 @@
 # coding: utf-8
-
 import os
 import tempfile
 
-try:
-    from urlparse import urlparse
-except ImportError:
-    from urllib.parse import urlparse
+from urllib.parse import urlparse
+from platform import system
 
 
+def get_nhentai_home() -> str:
+    home = os.getenv('HOME', tempfile.gettempdir())
+
+    if system() == 'Linux':
+        xdgdat = os.getenv('XDG_DATA_HOME')
+        if xdgdat and os.path.exists(os.path.join(xdgdat, 'nhentai')):
+            return os.path.join(xdgdat, 'nhentai')
+        if home and os.path.exists(os.path.join(home, '.nhentai')):
+            return os.path.join(home, '.nhentai')
+        if xdgdat:
+            return os.path.join(xdgdat, 'nhentai')
+
+    # Use old default path in other systems
+    return os.path.join(home, '.nhentai')
+
+
+DEBUG = os.getenv('DEBUG', False)
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-__api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
+DETAIL_URL = f'{BASE_URL}/g'
+LEGACY_SEARCH_URL = f'{BASE_URL}/search/'
+SEARCH_URL = f'{BASE_URL}/api/galleries/search'
+ARTIST_URL = f'{BASE_URL}/artist/'
 
-DETAIL_URL = '%s/g' % BASE_URL
-SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+TAG_API_URL = f'{BASE_URL}/api/galleries/tagged'
+LOGIN_URL = f'{BASE_URL}/login/'
+CHALLENGE_URL = f'{BASE_URL}/challenge'
+FAV_URL = f'{BASE_URL}/favorites/'
 
 
-TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
-LOGIN_URL = '%s/login/' % BASE_URL
-CHALLENGE_URL = '%s/challenge' % BASE_URL
-FAV_URL = '%s/favorites/' % BASE_URL
+IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
+IMAGE_URL_MIRRORS = [
+    f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}',
+]
 
-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_HOME = get_nhentai_home()
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
 NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
+__api_suspended_DETAIL_URL = f'{BASE_URL}/api/gallery'
 
 CONFIG = {
     'proxy': {'http': '', 'https': ''},
     'cookie': '',
     'language': '',
     'template': '',
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+    'max_filename': 85
+}
+
+LANGUAGE_ISO = {
+    'english': 'en',
+    'chinese': 'zh',
+    'japanese': 'ja',
+    'translated': 'translated'
 }

nhentai/doujinshi.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+import os
 
 from tabulate import tabulate
 
@@ -20,65 +21,99 @@ class DoujinshiInfo(dict):
 
     def __getattr__(self, item):
         try:
-            return dict.__getitem__(self, item)
+            ret = dict.__getitem__(self, item)
+            return ret if ret else 'Unknown'
         except KeyError:
-            return ''
+            return 'Unknown'
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
+    def __init__(self, name=None, pretty_name=None, id=None, img_id=None,
+                 ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
+        self.pretty_name = pretty_name
         self.id = id
         self.img_id = img_id
         self.ext = ext
         self.pages = pages
         self.downloader = None
-        self.url = '%s/%d' % (DETAIL_URL, self.id)
+        self.url = f'{DETAIL_URL}/{self.id}'
         self.info = DoujinshiInfo(**kwargs)
 
-        name_format = name_format.replace('%i', 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)
+        ag_value = self.info.groups if self.info.artists == 'Unknown' else self.info.artists
+        name_format = name_format.replace('%ag', format_filename(ag_value))
+
+        name_format = name_format.replace('%i', format_filename(str(self.id)))
+        name_format = name_format.replace('%a', format_filename(self.info.artists))
+        name_format = name_format.replace('%g', format_filename(self.info.groups))
+
+        name_format = name_format.replace('%t', format_filename(self.name))
+        name_format = name_format.replace('%p', format_filename(self.pretty_name))
+        name_format = name_format.replace('%s', format_filename(self.info.subtitle))
+        self.filename = format_filename(name_format, 255, True)
+
+        self.table = [
+            ['Parodies', self.info.parodies],
+            ['Doujinshi', self.name],
+            ['Subtitle', self.info.subtitle],
+            ['Date', self.info.date],
+            ['Characters', self.info.characters],
+            ['Authors', self.info.artists],
+            ['Groups', self.info.groups],
+            ['Languages', self.info.languages],
+            ['Tags', self.info.tags],
+            ['URL', self.url],
+            ['Pages', self.pages],
+        ]
 
     def __repr__(self):
-        return '<Doujinshi: {0}>'.format(self.name)
+        return f'<Doujinshi: {self.name}>'
 
     def show(self):
-        table = [
-            ["Parodies", self.info.parodies],
-            ["Doujinshi", self.name],
-            ["Subtitle", self.info.subtitle],
-            ["Characters", self.info.characters],
-            ["Authors", self.info.artists],
-            ["Languages", self.info.languages],
-            ["Tags", self.info.tags],
-            ["URL", self.url],
-            ["Pages", self.pages],
-        ]
-        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
+        logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
+
+    def check_if_need_download(self, options):
+        base_path = os.path.join(self.downloader.path, self.filename)
+
+        # regenerate, re-download
+        if options.regenerate:
+            return True
+
+        # pdf or cbz file exists, skip re-download
+        # doujinshi directory may not exist b/c of --rm-origin-dir option set.
+        # user should pass --regenerate option to get back origin dir.
+        ret_pdf = ret_cbz = None
+        if options.is_pdf:
+            ret_pdf = os.path.exists(f'{base_path}.pdf') or os.path.exists(f'{base_path}/{self.filename}.pdf')
+
+        if options.is_cbz:
+            ret_cbz = os.path.exists(f'{base_path}.cbz') or os.path.exists(f'{base_path}/{self.filename}.cbz')
+
+        ret = list(filter(lambda s: s is not None, [ret_cbz, ret_pdf]))
+        if ret and all(ret):
+            return False
+
+        # doujinshi directory doesn't exist, re-download
+        if not (os.path.exists(base_path) and os.path.isdir(base_path)):
+            return True
+
+        # fallback
+        return True
 
     def download(self):
-        logger.info('Starting to download doujinshi: %s' % self.name)
+        logger.info(f'Starting to download doujinshi: {self.name}')
         if self.downloader:
             download_queue = []
-
             if len(self.ext) != self.pages:
                 logger.warning('Page count and ext count do not equal')
 
             for i in range(1, min(self.pages, len(self.ext)) + 1):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))
-
-            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]]))
-            '''
+                download_queue.append(f'{IMAGE_URL}/{self.img_id}/{i}.{self.ext[i-1]}')
 
+            return self.downloader.start_download(download_queue, self.filename)
         else:
             logger.critical('Downloader has not been loaded')
+            return False
 
 
 if __name__ == '__main__':
@@ -88,4 +123,4 @@ if __name__ == '__main__':
     try:
         test.download()
     except Exception as e:
-        print('Exception: %s' % str(e))
+        print(f'Exception: {e}')

nhentai/downloader.py

@@ -3,22 +3,20 @@
 import multiprocessing
 import signal
 
-from future.builtins import str as text
 import sys
 import os
 import requests
 import time
+import urllib3.exceptions
 
-try:
-    from urllib.parse import urlparse
-except ImportError:
-    from urlparse import urlparse
-
+from urllib.parse import urlparse
+from nhentai import constant
 from nhentai.logger import logger
 from nhentai.parser import request
 from nhentai.utils import Singleton
 
-requests.packages.urllib3.disable_warnings()
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 semaphore = multiprocessing.Semaphore(1)
 
 
@@ -26,6 +24,21 @@ class NHentaiImageNotExistException(Exception):
     pass
 
 
+def download_callback(result):
+    result, data = result
+    if result == 0:
+        logger.warning('fatal errors occurred, ignored')
+    elif result == -1:
+        logger.warning(f'url {data} return status code 404')
+    elif result == -2:
+        logger.warning('Ctrl-C pressed, exiting sub processes ...')
+    elif result == -3:
+        # workers won't be run, just pass
+        pass
+    else:
+        logger.log(16, f'{data} downloaded successfully')
+
+
 class Downloader(Singleton):
 
     def __init__(self, path='', size=5, timeout=30, delay=0):
@@ -34,29 +47,34 @@ class Downloader(Singleton):
         self.timeout = timeout
         self.delay = delay
 
-    def download_(self, url, folder='', filename='', retried=0):
+    def download(self, url, folder='', filename='', retried=0, proxy=None):
         if self.delay:
             time.sleep(self.delay)
-        logger.info('Starting to download {0} ...'.format(url))
+        logger.info(f'Starting to download {url} ...')
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
+
+        save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
         try:
-            if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
-                logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
-                                                                                extension)))
+            if os.path.exists(save_file_path):
+                logger.warning(f'Skipped download: {save_file_path} already exists')
                 return 1, url
 
             response = None
-            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
+            with open(save_file_path, "wb") as f:
                 i = 0
                 while i < 10:
                     try:
-                        response = request('get', url, stream=True, timeout=self.timeout)
+                        response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
                         if response.status_code != 200:
-                            raise NHentaiImageNotExistException
-
-                    except NHentaiImageNotExistException as e:
-                        raise e
+                            path = urlparse(url).path
+                            for mirror in constant.IMAGE_URL_MIRRORS:
+                                print(f'{mirror}{path}')
+                                mirror_url = f'{mirror}{path}'
+                                response = request('get', mirror_url, stream=True,
+                                                   timeout=self.timeout, proxies=proxy)
+                                if response.status_code == 200:
+                                    break
 
                     except Exception as e:
                         i += 1
@@ -76,13 +94,14 @@ class Downloader(Singleton):
 
         except (requests.HTTPError, requests.Timeout) as e:
             if retried < 3:
-                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
-                return 0, self.download_(url=url, folder=folder, filename=filename, retried=retried+1)
+                logger.warning(f'Warning: {e}, retrying({retried}) ...')
+                return 0, self.download(url=url, folder=folder, filename=filename,
+                                        retried=retried+1, proxy=proxy)
             else:
                 return 0, None
 
         except NHentaiImageNotExistException as e:
-            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            os.remove(save_file_path)
             return -1, url
 
         except Exception as e:
@@ -96,39 +115,24 @@ class Downloader(Singleton):
 
         return 1, url
 
-    def _download_callback(self, result):
-        result, data = result
-        if result == 0:
-            logger.warning('fatal errors occurred, ignored')
-            # exit(1)
-        elif result == -1:
-            logger.warning('url {} return status code 404'.format(data))
-        elif result == -2:
-            logger.warning('Ctrl-C pressed, exiting sub processes ...')
-        elif result == -3:
-            # workers wont be run, just pass
-            pass
-        else:
-            logger.log(15, '{0} downloaded successfully'.format(data))
-
-    def download(self, queue, folder=''):
-        if not isinstance(folder, text):
+    def start_download(self, queue, folder='') -> bool:
+        if not isinstance(folder, (str, )):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
+        logger.info(f'Doujinshi will be saved at "{folder}"')
         if not os.path.exists(folder):
-            logger.warning('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
-                logger.critical('{0}'.format(str(e)))
+                logger.critical(str(e))
 
-        else:
-            logger.warning('Path \'{0}\' already exist.'.format(folder))
-
-        queue = [(self, url, folder) for url in queue]
+        if os.getenv('DEBUG', None) == 'NODOWNLOAD':
+            # Assuming we want to continue with rest of process.
+            return True
+        queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
 
         pool = multiprocessing.Pool(self.size, init_worker)
         [pool.apply_async(download_wrapper, args=item) for item in queue]
@@ -136,10 +140,12 @@ class Downloader(Singleton):
         pool.close()
         pool.join()
 
+        return True
 
-def download_wrapper(obj, url, folder=''):
+
+def download_wrapper(obj, url, folder='', proxy=None):
     if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download_(obj, url=url, folder=folder)
+        return Downloader.download(obj, url=url, folder=folder, proxy=proxy)
     else:
         return -3, None
 
@@ -148,7 +154,7 @@ def init_worker():
     signal.signal(signal.SIGINT, subprocess_signal)
 
 
-def subprocess_signal(signal, frame):
+def subprocess_signal(sig, frame):
     if semaphore.acquire(timeout=1):
         logger.warning('Ctrl-C pressed, exiting sub processes ...')
 

nhentai/logger.py

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

nhentai/parser.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-
+import sys
 import os
 import re
 import time
@@ -26,7 +26,7 @@ def login(username, password):
         logger.info('Getting CSRF token ...')
 
     if os.getenv('DEBUG'):
-        logger.info('CSRF token is {}'.format(csrf_token))
+        logger.info(f'CSRF token is {csrf_token}')
 
     login_dict = {
         'csrfmiddlewaretoken': csrf_token,
@@ -41,11 +41,11 @@ def login(username, password):
 
     if 'Invalid username/email or password' in resp.text:
         logger.error('Login failed, please check your username and password')
-        exit(1)
+        sys.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)
+        sys.exit(2)
 
 
 def _get_title_and_id(response):
@@ -56,7 +56,7 @@ def _get_title_and_id(response):
         doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
         title = doujinshi_container.text.strip()
         title = title if len(title) < 85 else title[:82] + '...'
-        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
+        id_ = re.search('/g/([0-9]+)/', doujinshi.a['href']).group(1)
         result.append({'id': id_, 'title': title})
 
     return result
@@ -67,7 +67,7 @@ def favorites_parser(page=None):
     html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
     count = html.find('span', attrs={'class': 'count'})
     if not count:
-        logger.error("Can't get your number of favorited doujins. Did the login failed?")
+        logger.error("Can't get your number of favorite doujinshis. Did the login failed?")
         return []
 
     count = int(count.text.strip('(').strip(')').replace(',', ''))
@@ -84,7 +84,7 @@ def favorites_parser(page=None):
         else:
             pages = 1
 
-        logger.info('You have %d favorites in %d pages.' % (count, pages))
+        logger.info(f'You have {count} favorites in {pages} pages.')
 
         if os.getenv('DEBUG'):
             pages = 1
@@ -93,53 +93,63 @@ def favorites_parser(page=None):
 
     for page in page_range_list:
         try:
-            logger.info('Getting doujinshi ids of page %d' % page)
-            resp = request('get', constant.FAV_URL + '?page=%d' % page).content
+            logger.info(f'Getting doujinshi ids of page {page}')
+            resp = request('get', f'{constant.FAV_URL}?page={page}').content
 
             result.extend(_get_title_and_id(resp))
         except Exception as e:
-            logger.error('Error: %s, continue', str(e))
+            logger.error(f'Error: {e}, continue')
 
     return result
 
 
-def doujinshi_parser(id_):
+def doujinshi_parser(id_, counter=0):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
+        raise Exception(f'Doujinshi id({id_}) is not valid')
 
     id_ = int(id_)
-    logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
+    logger.info(f'Fetching doujinshi information of id {id_}')
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
+    url = f'{constant.DETAIL_URL}/{id_}/'
 
     try:
         response = request('get', url)
         if response.status_code in (200, ):
             response = response.content
         elif response.status_code in (404,):
-            logger.error("Doujinshi with id {0} cannot be found".format(id_))
+            logger.error(f'Doujinshi with id {id_} cannot be found')
             return []
         else:
-            logger.debug('Slow down and retry ({}) ...'.format(id_))
-            time.sleep(1)
-            return doujinshi_parser(str(id_))
+            counter += 1
 
-    except Exception as e:
-        logger.warning('Error: {}, ignored'.format(str(e)))
+            if counter == 10:
+                logger.critical(f'Failed to fetch doujinshi information of id {id_}')
                 return None
 
+            logger.debug(f'Slow down and retry ({id_}) ...')
+            time.sleep(1)
+            return doujinshi_parser(str(id_), counter)
+
+    except Exception as e:
+        logger.warning(f'Error: {e}, ignored')
+        return None
+
+    # print(response)
     html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
+    pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
     subtitle = doujinshi_info.find('h2')
 
     doujinshi['name'] = title
+    doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+                       doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
@@ -148,11 +158,12 @@ def doujinshi_parser(id_):
 
     if not img_id:
         logger.critical('Tried yo get image id failed')
-        exit(1)
+        sys.exit(1)
 
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
 
+    pages = 0
     for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
         if re.search('Pages:', _.text):
             pages = _.find('span', class_='name').string
@@ -174,76 +185,15 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def old_search_parser(keyword, sorting='date', page=1):
-    logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
-    response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
-
-    result = _get_title_and_id(response)
-    if not result:
-        logger.warning('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.warning('No result in response in page {}'.format(p))
-            break
-
-        for row in response['result']:
-            title = row['title']['english']
-            title = title[:85] + '..' if len(title) > 85 else title
-            result.append({'id': row['id'], 'title': title})
-
-        if not result:
-            logger.warning('No results for keywords {}'.format(keyword))
-
-    return result
-
-
-def __api_suspended_doujinshi_parser(id_):
+def legacy_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
+        raise Exception(f'Doujinshi id({id_}) is not valid')
 
     id_ = int(id_)
-    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
+    logger.info(f'Fetching information of doujinshi id {id_}')
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    url = f'{constant.DETAIL_URL}/{id_}'
     i = 0
     while 5 > i:
         try:
@@ -252,7 +202,7 @@ def __api_suspended_doujinshi_parser(id_):
             i += 1
             if not i < 5:
                 logger.critical(str(e))
-                exit(1)
+                sys.exit(1)
             continue
         break
 
@@ -282,5 +232,112 @@ def __api_suspended_doujinshi_parser(id_):
     return doujinshi
 
 
+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(f'Search Result || Found {doujinshi_list.__len__()} doujinshis')
+    print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+
+
+def legacy_search_parser(keyword, sorting, page, is_page_all=False, type_='SEARCH'):
+    logger.info(f'Searching doujinshis of keyword {keyword}')
+    result = []
+
+    if type_ not in ('SEARCH', 'ARTIST', ):
+        raise ValueError('Invalid type')
+
+    if is_page_all:
+        if type_ == 'SEARCH':
+            response = request('get', url=constant.LEGACY_SEARCH_URL,
+                               params={'q': keyword, 'page': 1, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': 1}).content
+
+        html = BeautifulSoup(response, 'lxml')
+        pagination = html.find(attrs={'class': 'pagination'})
+        last_page = pagination.find(attrs={'class': 'last'})
+        last_page = re.findall('page=([0-9]+)', last_page.attrs['href'])[0]
+        logger.info(f'Getting doujinshi ids of {last_page} pages')
+        pages = range(1, int(last_page))
+    else:
+        pages = page
+
+    for p in pages:
+        logger.info(f'Fetching page {p} ...')
+        if type_ == 'SEARCH':
+            response = request('get', url=constant.LEGACY_SEARCH_URL,
+                               params={'q': keyword, 'page': p, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': p}).content
+
+        if response is None:
+            logger.warning(f'No result in response in page {p}')
+            continue
+        result.extend(_get_title_and_id(response))
+
+    if not result:
+        logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
+def search_parser(keyword, sorting, page, is_page_all=False):
+    result = []
+    response = None
+    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 = f'/{page[-1]}' if is_page_all else ''
+    not_exists_persist = False
+    for p in page:
+        i = 0
+
+        logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
+        while i < 3:
+            try:
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+                                                                      'page': p, 'sort': sorting}).url
+
+                if constant.DEBUG:
+                    logger.debug(f'Request URL: {url}')
+
+                response = request('get', url.replace('%2B', '+')).json()
+            except Exception as e:
+                logger.critical(str(e))
+                response = None
+            break
+
+        if constant.DEBUG:
+            logger.debug(f'Response: {response}')
+
+        if response is None or 'result' not in response:
+            logger.warning(f'No result in response in page {p}')
+            if not_exists_persist is True:
+                break
+            continue
+
+        for row in response['result']:
+            title = row['title']['english']
+            title = title[:constant.CONFIG['max_filename']] + '..' if \
+                len(title) > constant.CONFIG['max_filename'] else title
+
+            result.append({'id': row['id'], 'title': title})
+
+        not_exists_persist = False
+        if not result:
+            logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/serializer.py

@@ -2,9 +2,10 @@
 import json
 import os
 from xml.sax.saxutils import escape
+from nhentai.constant import LANGUAGE_ISO
 
 
-def serialize_json(doujinshi, dir):
+def serialize_json(doujinshi, output_dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
     if doujinshi.info.date:
@@ -21,17 +22,17 @@ def serialize_json(doujinshi, dir):
         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['category'] = [i.strip() for i in doujinshi.info.categories.split(',')]
     metadata['URL'] = doujinshi.url
     metadata['Pages'] = doujinshi.pages
 
-    with open(os.path.join(dir, 'metadata.json'), 'w') as f:
-        json.dump(metadata, f, separators=','':')
+    with open(os.path.join(output_dir, 'metadata.json'), 'w') as f:
+        json.dump(metadata, f, separators=(',', ':'))
 
 
-def serialize_comicxml(doujinshi, dir):
+def serialize_comic_xml(doujinshi, output_dir):
     from iso8601 import parse_date
-    with open(os.path.join(dir, 'ComicInfo.xml'), 'w') as f:
+    with open(os.path.join(output_dir, 'ComicInfo.xml'), 'w', encoding="utf-8") as f:
         f.write('<?xml version="1.0" encoding="utf-8"?>\n')
         f.write('<ComicInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" '
                 'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">\n')
@@ -45,7 +46,8 @@ def serialize_comicxml(doujinshi, dir):
         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
         xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
 
-        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and 'full color' in doujinshi.info.tags else 'Yes')
+        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and
+                             'full color' in doujinshi.info.tags else 'Yes')
 
         if doujinshi.info.date:
             dt = parse_date(doujinshi.info.date)
@@ -59,19 +61,20 @@ def serialize_comicxml(doujinshi, dir):
         if doujinshi.info.tags:
             xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
         if doujinshi.info.artists:
-            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in doujinshi.info.artists.split(',')]))
-        # if doujinshi.info.groups:
-        #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
+            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in
+                                                          doujinshi.info.artists.split(',')]))
+
         if doujinshi.info.languages:
             languages = [i.strip() for i in doujinshi.info.languages.split(',')]
             xml_write_simple_tag(f, 'Translated', 'Yes' if 'translated' in languages else 'No')
-            [xml_write_simple_tag(f, 'Language', i) for i in languages if i != 'translated']
+            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGE_ISO[i]) for i in languages
+             if (i != 'translated' and i in LANGUAGE_ISO)]
 
         f.write('</ComicInfo>')
 
 
 def xml_write_simple_tag(f, name, val, indent=1):
-    f.write('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
+    f.write(f'{" "*indent}<{name}>{escape(str(val))}</{name}>\n')
 
 
 def merge_json():
@@ -120,7 +123,7 @@ def serialize_unique(lst):
 def set_js_database():
     with open('data.js', 'w') as f:
         indexed_json = merge_json()
-        unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
-        indexed_json = json.dumps(indexed_json, separators=','':')
+        unique_json = json.dumps(serialize_unique(indexed_json), separators=(',', ':'))
+        indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)

nhentai/utils.py

@@ -5,31 +5,45 @@ import re
 import os
 import zipfile
 import shutil
+
 import requests
 import sqlite3
+import urllib.parse
+from typing import Optional, Tuple
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
+from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
+
+MAX_FIELD_LENGTH = 100
 
 
 def request(method, url, **kwargs):
     session = requests.Session()
     session.headers.update({
         'Referer': constant.LOGIN_URL,
-        'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+        'User-Agent': constant.CONFIG['useragent'],
         'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.CONFIG['proxy'], verify=False, **kwargs)
+
+    if not kwargs.get('proxies', None):
+        kwargs['proxies'] = constant.CONFIG['proxy']
+
+    return getattr(session, method)(url, verify=False, **kwargs)
 
 
 def check_cookie():
-    response = request('get', constant.BASE_URL).text
-    username = re.findall('"/users/\d+/(.*?)"', response)
+    response = request('get', constant.BASE_URL)
+    if response.status_code == 403 and 'Just a moment...' in response.text:
+        logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
+        sys.exit(1)
+
+    username = re.findall('"/users/[0-9]+/(.*?)"', response.text)
     if not username:
-        logger.error('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
+        logger.warning(
+            'Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
     else:
-        logger.info('Login successfully! Your username: {}'.format(username[0]))
+        logger.log(16, f'Login successfully! Your username: {username[0]}')
 
 
 class _Singleton(type):
@@ -46,15 +60,6 @@ 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__)
 
@@ -62,13 +67,38 @@ def readfile(path):
         return file.read()
 
 
+def parse_doujinshi_obj(
+        output_dir: str,
+        doujinshi_obj=None,
+        file_type: str = ''
+) -> Tuple[str, str]:
+
+    filename = f'./doujinshi.{file_type}'
+    doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    if doujinshi_obj is not None:
+        _filename = f'{doujinshi_obj.filename}.{file_type}'
+
+        if file_type == 'cbz':
+            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+
+        if file_type == 'pdf':
+            _filename = _filename.replace('/', '-')
+
+        filename = os.path.join(output_dir, _filename)
+
+    return doujinshi_dir, filename
+
+
 def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '.html')
     image_html = ''
 
-    if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    else:
-        doujinshi_dir = '.'
+    if not os.path.exists(doujinshi_dir):
+        logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
+        try:
+            os.makedirs(doujinshi_dir)
+        except EnvironmentError as e:
+            logger.critical(e)
 
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
@@ -76,38 +106,52 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     for image in file_list:
         if not os.path.splitext(image)[1] in ('.jpg', '.png'):
             continue
+        image_html += f'<img src="{image}" class="image-item"/>\n'
 
-        image_html += '<img src="{0}" class="image-item"/>\n'\
-            .format(image)
-    html = readfile('viewer/{}/index.html'.format(template))
-    css = readfile('viewer/{}/styles.css'.format(template))
-    js = readfile('viewer/{}/scripts.js'.format(template))
+    html = readfile(f'viewer/{template}/index.html')
+    css = readfile(f'viewer/{template}/styles.css')
+    js = readfile(f'viewer/{template}/scripts.js')
 
     if doujinshi_obj is not None:
         serialize_json(doujinshi_obj, doujinshi_dir)
         name = doujinshi_obj.name
-        if sys.version_info < (3, 0):
-            name = doujinshi_obj.name.encode('utf-8')
     else:
         name = {'title': 'nHentai HTML Viewer'}
 
     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:
-                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 written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(16, f'HTML Viewer has been written to "{os.path.join(doujinshi_dir, "index.html")}"')
     except Exception as e:
-        logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing HTML Viewer failed ({e})')
+
+
+def move_to_folder(output_dir='.', doujinshi_obj=None, file_type=None):
+    if not file_type:
+        raise RuntimeError('no file_type specified')
+
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
+
+    for fn in os.listdir(doujinshi_dir):
+        file_path = os.path.join(doujinshi_dir, fn)
+        _, ext = os.path.splitext(file_path)
+        if ext in ['.pdf', '.cbz']:
+            continue
+
+        if os.path.isfile(file_path):
+            try:
+                os.remove(file_path)
+            except Exception as e:
+                print(f"Error deleting file: {e}")
+
+    shutil.move(filename, os.path.join(doujinshi_dir, os.path.basename(filename)))
 
 
 def generate_main_html(output_dir='./'):
     """
-    Generate a main html to show all the contain doujinshi.
+    Generate a main html to show all the contains doujinshi.
     With a link to their `index.html`.
     Default output folder will be the CLI path.
     """
@@ -136,7 +180,7 @@ def generate_main_html(output_dir='./'):
         files.sort()
 
         if 'index.html' in files:
-            logger.info('Add doujinshi \'{}\''.format(folder))
+            logger.info(f'Add doujinshi "{folder}"')
         else:
             continue
 
@@ -146,92 +190,63 @@ def generate_main_html(output_dir='./'):
         else:
             title = 'nHentai HTML Viewer'
 
-        image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
+        image_html += element.format(FOLDER=urllib.parse.quote(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', './')
+        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))
+        output_dir = output_dir[:-1] if output_dir.endswith('/') else output_dir
+        logger.log(16, f'Main Viewer has been written to "{output_dir}/main.html"')
     except Exception as e:
-        logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing Main Viewer failed ({e})')
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=False):
-    if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-        if write_comic_info:
-            serialize_comicxml(doujinshi_obj, doujinshi_dir)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
-    else:
-        cbz_filename = './doujinshi.cbz'
-        doujinshi_dir = '.'
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
 
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
+
+    if os.path.exists(f'{doujinshi_dir}.{file_type}') and not regenerate:
+        logger.info(f'Skipped {file_type} file generation: {doujinshi_dir}.{file_type} already exists')
+        return
+
+    if file_type == 'cbz':
         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:
+        logger.info(f'Writing CBZ file to path: {filename}')
+        with zipfile.ZipFile(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 written to \'{0}\''.format(doujinshi_dir))
-
-
-def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+        logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
+    elif file_type == 'pdf':
         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 = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif'))]
             file_list.sort()
 
-    logger.info('Writing PDF file to path: {}'.format(pdf_filename))
-    with open(pdf_filename, 'wb') as pdf_f:
+            logger.info(f'Writing PDF file to path: {filename}')
+            with open(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))
+                pdf_f.write(img2pdf.convert(full_path_list, rotation=img2pdf.Rotation.ifvalid))
 
-    if rm_origin_dir:
-        shutil.rmtree(doujinshi_dir, ignore_errors=True)
+            logger.log(16, f'PDF file has been written to "{filename}"')
 
-    logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
+        except ImportError:
+            logger.error("Please install img2pdf package by using pip.")
 
 
-def unicode_truncate(s, length, encoding='utf-8'):
-    """https://stackoverflow.com/questions/1809531/truncating-unicode-so-it-fits-a-maximum-size-when-encoded-for-wire-transfer
-    """
-    encoded = s.encode(encoding)[:length]
-    return encoded.decode(encoding, 'ignore')
-
-
-def format_filename(s):
+def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
     """
     It used to be a whitelist approach allowed only alphabet and a part of symbols.
     but most doujinshi's names include Japanese 2-byte characters and these was rejected.
@@ -239,16 +254,20 @@ def format_filename(s):
     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()
+
+    if not _truncate_only:
+        ban_chars = '\\\'/:,;*?"<>|\t\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b'
+        filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
         filename = ' '.join(filename.split())
-    print(repr(filename))
 
         while filename.endswith('.'):
             filename = filename[:-1]
+    else:
+        filename = s
 
-    if len(filename) > 100:
-        filename = filename[:100] + u'…'
+    # limit `length` chars
+    if len(filename) >= length:
+        filename = filename[:length - 1] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
@@ -257,7 +276,7 @@ def format_filename(s):
 
 def signal_handler(signal, frame):
     logger.error('Ctrl-C signal received. Stopping...')
-    exit(1)
+    sys.exit(1)
 
 
 def paging(page_string):
@@ -271,7 +290,7 @@ def paging(page_string):
             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)))
+            page_list.extend(list(range(int(start), int(end) + 1)))
         else:
             if not i.isdigit():
                 raise Exception('Invalid page number')
@@ -280,6 +299,29 @@ def paging(page_string):
     return page_list
 
 
+def generate_metadata_file(output_dir, doujinshi_obj):
+
+    info_txt_path = os.path.join(output_dir, doujinshi_obj.filename, 'info.txt')
+
+    f = open(info_txt_path, 'w', encoding='utf-8')
+
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
+              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
+              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
+                      'LANGUAGE', 'TAGS', 'URL', 'PAGES']
+
+    for i in range(len(fields)):
+        f.write(f'{fields[i]}: ')
+        if fields[i] in special_fields:
+            f.write(str(doujinshi_obj.table[special_fields.index(fields[i])][1]))
+        f.write('\n')
+
+    f.close()
+    logger.log(16, f'Metadata Info has been written to "{info_txt_path}"')
+
+
 class DB(object):
     conn = None
     cur = None

nhentai/viewer/main.js

@@ -139,7 +139,7 @@ function filter_searcher(){
 					break
 			}
 		}
-		if (verifier){doujinshi_id.push(data[i].Folder);}
+		if (verifier){doujinshi_id.push(data[i].Folder.replace("_", " "));}
 	}
 	var gallery = document.getElementsByClassName("gallery-favorite");
 	for (var i = 0; i < gallery.length; i++){

nhentai/viewer/minimal/index.html

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

nhentai/viewer/minimal/scripts.js

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

nhentai/viewer/minimal/styles.css

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

poetry.lock

@@ -0,0 +1,216 @@
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.11.2"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.6.0"
+files = [
+    {file = "beautifulsoup4-4.11.2-py3-none-any.whl", hash = "sha256:0e79446b10b3ecb499c1556f7e228a53e64a2bfcebd455f370d8927cb5b59e39"},
+    {file = "beautifulsoup4-4.11.2.tar.gz", hash = "sha256:bc4bdda6717de5a2987436fb8d72f45dc90dd856bdfd512a1314ce90349a0106"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "certifi"
+version = "2024.7.4"
+description = "Python package for providing Mozilla's CA Bundle."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"},
+    {file = "certifi-2024.7.4.tar.gz", hash = "sha256:5a1e7645bc0ec61a09e26c36f6106dd4cf40c6db3a1fb6352b0244e7fb057c7b"},
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.0.1"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+optional = false
+python-versions = "*"
+files = [
+    {file = "charset-normalizer-3.0.1.tar.gz", hash = "sha256:ebea339af930f8ca5d7a699b921106c6e29c617fe9606fa7baa043c1cdae326f"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:88600c72ef7587fe1708fd242b385b6ed4b8904976d5da0893e31df8b3480cb6"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c75ffc45f25324e68ab238cb4b5c0a38cd1c3d7f1fb1f72b5541de469e2247db"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db72b07027db150f468fbada4d85b3b2729a3db39178abf5c543b784c1254539"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62595ab75873d50d57323a91dd03e6966eb79c41fa834b7a1661ed043b2d404d"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ff6f3db31555657f3163b15a6b7c6938d08df7adbfc9dd13d9d19edad678f1e8"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:772b87914ff1152b92a197ef4ea40efe27a378606c39446ded52c8f80f79702e"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70990b9c51340e4044cfc394a81f614f3f90d41397104d226f21e66de668730d"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:292d5e8ba896bbfd6334b096e34bffb56161c81408d6d036a7dfa6929cff8783"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:2edb64ee7bf1ed524a1da60cdcd2e1f6e2b4f66ef7c077680739f1641f62f555"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:31a9ddf4718d10ae04d9b18801bd776693487cbb57d74cc3458a7673f6f34639"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:44ba614de5361b3e5278e1241fda3dc1838deed864b50a10d7ce92983797fa76"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:12db3b2c533c23ab812c2b25934f60383361f8a376ae272665f8e48b88e8e1c6"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c512accbd6ff0270939b9ac214b84fb5ada5f0409c44298361b2f5e13f9aed9e"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-win32.whl", hash = "sha256:502218f52498a36d6bf5ea77081844017bf7982cdbe521ad85e64cabee1b608b"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:601f36512f9e28f029d9481bdaf8e89e5148ac5d89cffd3b05cd533eeb423b59"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0298eafff88c99982a4cf66ba2efa1128e4ddaca0b05eec4c456bbc7db691d8d"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a8d0fc946c784ff7f7c3742310cc8a57c5c6dc31631269876a88b809dbeff3d3"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:87701167f2a5c930b403e9756fab1d31d4d4da52856143b609e30a1ce7160f3c"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14e76c0f23218b8f46c4d87018ca2e441535aed3632ca134b10239dfb6dadd6b"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c0a590235ccd933d9892c627dec5bc7511ce6ad6c1011fdf5b11363022746c1"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c7fe7afa480e3e82eed58e0ca89f751cd14d767638e2550c77a92a9e749c317"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79909e27e8e4fcc9db4addea88aa63f6423ebb171db091fb4373e3312cb6d603"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ac7b6a045b814cf0c47f3623d21ebd88b3e8cf216a14790b455ea7ff0135d18"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:72966d1b297c741541ca8cf1223ff262a6febe52481af742036a0b296e35fa5a"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f9d0c5c045a3ca9bedfc35dca8526798eb91a07aa7a2c0fee134c6c6f321cbd7"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:5995f0164fa7df59db4746112fec3f49c461dd6b31b841873443bdb077c13cfc"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4a8fcf28c05c1f6d7e177a9a46a1c52798bfe2ad80681d275b10dcf317deaf0b"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:761e8904c07ad053d285670f36dd94e1b6ab7f16ce62b9805c475b7aa1cffde6"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-win32.whl", hash = "sha256:71140351489970dfe5e60fc621ada3e0f41104a5eddaca47a7acb3c1b851d6d3"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:9ab77acb98eba3fd2a85cd160851816bfce6871d944d885febf012713f06659c"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:84c3990934bae40ea69a82034912ffe5a62c60bbf6ec5bc9691419641d7d5c9a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74292fc76c905c0ef095fe11e188a32ebd03bc38f3f3e9bcb85e4e6db177b7ea"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c95a03c79bbe30eec3ec2b7f076074f4281526724c8685a42872974ef4d36b72"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f4c39b0e3eac288fedc2b43055cfc2ca7a60362d0e5e87a637beac5d801ef478"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df2c707231459e8a4028eabcd3cfc827befd635b3ef72eada84ab13b52e1574d"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93ad6d87ac18e2a90b0fe89df7c65263b9a99a0eb98f0a3d2e079f12a0735837"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:59e5686dd847347e55dffcc191a96622f016bc0ad89105e24c14e0d6305acbc6"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:cd6056167405314a4dc3c173943f11249fa0f1b204f8b51ed4bde1a9cd1834dc"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:083c8d17153ecb403e5e1eb76a7ef4babfc2c48d58899c98fcaa04833e7a2f9a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:f5057856d21e7586765171eac8b9fc3f7d44ef39425f85dbcccb13b3ebea806c"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:7eb33a30d75562222b64f569c642ff3dc6689e09adda43a082208397f016c39a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-win32.whl", hash = "sha256:95dea361dd73757c6f1c0a1480ac499952c16ac83f7f5f4f84f0658a01b8ef41"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:eaa379fcd227ca235d04152ca6704c7cb55564116f8bc52545ff357628e10602"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3e45867f1f2ab0711d60c6c71746ac53537f1684baa699f4f668d4c6f6ce8e14"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cadaeaba78750d58d3cc6ac4d1fd867da6fc73c88156b7a3212a3cd4819d679d"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:911d8a40b2bef5b8bbae2e36a0b103f142ac53557ab421dc16ac4aafee6f53dc"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:503e65837c71b875ecdd733877d852adbc465bd82c768a067badd953bf1bc5a3"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a60332922359f920193b1d4826953c507a877b523b2395ad7bc716ddd386d866"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:16a8663d6e281208d78806dbe14ee9903715361cf81f6d4309944e4d1e59ac5b"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:a16418ecf1329f71df119e8a65f3aa68004a3f9383821edcb20f0702934d8087"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:9d9153257a3f70d5f69edf2325357251ed20f772b12e593f3b3377b5f78e7ef8"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:02a51034802cbf38db3f89c66fb5d2ec57e6fe7ef2f4a44d070a593c3688667b"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:2e396d70bc4ef5325b72b593a72c8979999aa52fb8bcf03f701c1b03e1166918"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:11b53acf2411c3b09e6af37e4b9005cba376c872503c8f28218c7243582df45d"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-win32.whl", hash = "sha256:0bf2dae5291758b6f84cf923bfaa285632816007db0330002fa1de38bfcb7154"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2c03cc56021a4bd59be889c2b9257dae13bf55041a3372d3295416f86b295fb5"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:024e606be3ed92216e2b6952ed859d86b4cfa52cd5bc5f050e7dc28f9b43ec42"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4b0d02d7102dd0f997580b51edc4cebcf2ab6397a7edf89f1c73b586c614272c"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:358a7c4cb8ba9b46c453b1dd8d9e431452d5249072e4f56cfda3149f6ab1405e"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81d6741ab457d14fdedc215516665050f3822d3e56508921cc7239f8c8e66a58"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8b8af03d2e37866d023ad0ddea594edefc31e827fee64f8de5611a1dbc373174"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9cf4e8ad252f7c38dd1f676b46514f92dc0ebeb0db5552f5f403509705e24753"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e696f0dd336161fca9adbb846875d40752e6eba585843c768935ba5c9960722b"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c22d3fe05ce11d3671297dc8973267daa0f938b93ec716e12e0f6dee81591dc1"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:109487860ef6a328f3eec66f2bf78b0b72400280d8f8ea05f69c51644ba6521a"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:37f8febc8ec50c14f3ec9637505f28e58d4f66752207ea177c1d67df25da5aed"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:f97e83fa6c25693c7a35de154681fcc257c1c41b38beb0304b9c4d2d9e164479"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a152f5f33d64a6be73f1d30c9cc82dfc73cec6477ec268e7c6e4c7d23c2d2291"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:39049da0ffb96c8cbb65cbf5c5f3ca3168990adf3551bd1dee10c48fce8ae820"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-win32.whl", hash = "sha256:4457ea6774b5611f4bed5eaa5df55f70abde42364d498c5134b7ef4c6958e20e"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:e62164b50f84e20601c1ff8eb55620d2ad25fb81b59e3cd776a1902527a788af"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8eade758719add78ec36dc13201483f8e9b5d940329285edcd5f70c0a9edbd7f"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8499ca8f4502af841f68135133d8258f7b32a53a1d594aa98cc52013fff55678"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3fc1c4a2ffd64890aebdb3f97e1278b0cc72579a08ca4de8cd2c04799a3a22be"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d3ffdaafe92a5dc603cb9bd5111aaa36dfa187c8285c543be562e61b755f6b"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c2ac1b08635a8cd4e0cbeaf6f5e922085908d48eb05d44c5ae9eabab148512ca"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6f45710b4459401609ebebdbcfb34515da4fc2aa886f95107f556ac69a9147e"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ae1de54a77dc0d6d5fcf623290af4266412a7c4be0b1ff7444394f03f5c54e3"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b590df687e3c5ee0deef9fc8c547d81986d9a1b56073d82de008744452d6541"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ab5de034a886f616a5668aa5d098af2b5385ed70142090e2a31bcbd0af0fdb3d"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9cb3032517f1627cc012dbc80a8ec976ae76d93ea2b5feaa9d2a5b8882597579"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:608862a7bf6957f2333fc54ab4399e405baad0163dc9f8d99cb236816db169d4"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0f438ae3532723fb6ead77e7c604be7c8374094ef4ee2c5e03a3a17f1fca256c"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:356541bf4381fa35856dafa6a965916e54bed415ad8a24ee6de6e37deccf2786"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-win32.whl", hash = "sha256:39cf9ed17fe3b1bc81f33c9ceb6ce67683ee7526e65fde1447c772afc54a1bb8"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:0a11e971ed097d24c534c037d298ad32c6ce81a45736d31e0ff0ad37ab437d59"},
+    {file = "charset_normalizer-3.0.1-py3-none-any.whl", hash = "sha256:7e189e2e1d3ed2f4aebabd2d5b0f931e883676e51c7624826e0a4e5fe8a0bf24"},
+]
+
+[[package]]
+name = "idna"
+version = "3.7"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"},
+    {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"},
+]
+
+[[package]]
+name = "iso8601"
+version = "1.1.0"
+description = "Simple module to parse ISO 8601 dates"
+optional = false
+python-versions = ">=3.6.2,<4.0"
+files = [
+    {file = "iso8601-1.1.0-py3-none-any.whl", hash = "sha256:8400e90141bf792bce2634df533dc57e3bee19ea120a87bebcd3da89a58ad73f"},
+    {file = "iso8601-1.1.0.tar.gz", hash = "sha256:32811e7b81deee2063ea6d2e94f8819a86d1f3811e49d23623a41fa832bef03f"},
+]
+
+[[package]]
+name = "requests"
+version = "2.32.0"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "requests-2.32.0-py3-none-any.whl", hash = "sha256:f2c3881dddb70d056c5bd7600a4fae312b2a300e39be6a118d30b90bd27262b5"},
+    {file = "requests-2.32.0.tar.gz", hash = "sha256:fa5490319474c82ef1d2c9bc459d3652e3ae4ef4c4ebdd18a21145a47ca4b6b8"},
+]
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "soupsieve"
+version = "2.4"
+description = "A modern CSS selector implementation for Beautiful Soup."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "soupsieve-2.4-py3-none-any.whl", hash = "sha256:49e5368c2cda80ee7e84da9dbe3e110b70a4575f196efb74e51b94549d921955"},
+    {file = "soupsieve-2.4.tar.gz", hash = "sha256:e28dba9ca6c7c00173e34e4ba57448f0688bb681b7c5e8bf4971daafc093d69a"},
+]
+
+[[package]]
+name = "tabulate"
+version = "0.9.0"
+description = "Pretty-print tabular data"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"},
+    {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"},
+]
+
+[package.extras]
+widechars = ["wcwidth"]
+
+[[package]]
+name = "urllib3"
+version = "1.26.19"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
+files = [
+    {file = "urllib3-1.26.19-py2.py3-none-any.whl", hash = "sha256:37a0344459b199fce0e80b0d3569837ec6b6937435c5244e7fd73fa6006830f3"},
+    {file = "urllib3-1.26.19.tar.gz", hash = "sha256:3e3d753a8618b86d7de333b4223005f68720bcd6a7d2bcb9fbd2229ec7c1e429"},
+]
+
+[package.extras]
+brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.8"
+content-hash = "0a1d5abd47a669c7a1f2dc7b43824a449e29ba94908a4338d2ea0f2dfb4f805e"

pyproject.toml

@@ -0,0 +1,21 @@
+[tool.poetry]
+name = "nhentai"
+version = "0.5.10"
+description = "nhentai doujinshi downloader"
+authors = ["Ricter Z <ricterzheng@gmail.com>"]
+license = "MIT"
+readme = "README.rst"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+requests = "^2.28.2"
+soupsieve = "^2.4"
+beautifulsoup4 = "^4.11.2"
+tabulate = "^0.9.0"
+iso8601 = "^1.1.0"
+urllib3 = "^1.26.14"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -1,7 +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
+requests
+soupsieve
+setuptools
+BeautifulSoup4
+tabulate
+iso8601
+urllib3

setup.cfg

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

setup.py

@@ -1,6 +1,4 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
-import sys
 import codecs
 from setuptools import setup, find_packages
 from nhentai import __version__, __author__, __email__
@@ -12,7 +10,6 @@ with open('requirements.txt') as f:
 
 def long_description():
     with codecs.open('README.rst', 'rb') as readme:
-        if not sys.version_info < (3, 0, 0):
         return readme.read().decode('utf-8')
 
 

tests/test_download.py

@@ -0,0 +1,36 @@
+import unittest
+import os
+import urllib3.exceptions
+
+from nhentai import constant
+from nhentai.cmdline import load_config
+from nhentai.downloader import Downloader
+from nhentai.parser import doujinshi_parser
+from nhentai.doujinshi import Doujinshi
+from nhentai.utils import generate_html, generate_cbz
+
+
+class TestDownload(unittest.TestCase):
+    def setUp(self) -> None:
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        load_config()
+        constant.CONFIG['cookie'] = os.getenv('NHENTAI_COOKIE')
+        constant.CONFIG['useragent'] = os.getenv('NHENTAI_UA')
+
+    def test_download(self):
+        did = 440546
+        info = Doujinshi(**doujinshi_parser(did), name_format='%i')
+        info.downloader = Downloader(path='/tmp', size=5)
+        info.download()
+
+        self.assertTrue(os.path.exists(f'/tmp/{did}/001.jpg'))
+
+        generate_html('/tmp', info)
+        self.assertTrue(os.path.exists(f'/tmp/{did}/index.html'))
+
+        generate_cbz('/tmp', info)
+        self.assertTrue(os.path.exists(f'/tmp/{did}.cbz'))
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_login.py

@@ -0,0 +1,26 @@
+import os
+import unittest
+import urllib3.exceptions
+
+from nhentai import constant
+from nhentai.cmdline import load_config
+from nhentai.utils import check_cookie
+
+
+class TestLogin(unittest.TestCase):
+    def setUp(self) -> None:
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        load_config()
+        constant.CONFIG['cookie'] = os.getenv('NHENTAI_COOKIE')
+        constant.CONFIG['useragent'] = os.getenv('NHENTAI_UA')
+
+    def test_cookie(self):
+        try:
+            check_cookie()
+            self.assertTrue(True)
+        except Exception as e:
+            self.assertIsNone(e)
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_parser.py

@@ -0,0 +1,27 @@
+import unittest
+import os
+import urllib3.exceptions
+
+from nhentai import constant
+from nhentai.cmdline import load_config
+from nhentai.parser import search_parser, doujinshi_parser, favorites_parser
+
+
+class TestParser(unittest.TestCase):
+    def setUp(self) -> None:
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        load_config()
+        constant.CONFIG['cookie'] = os.getenv('NHENTAI_COOKIE')
+        constant.CONFIG['useragent'] = os.getenv('NHENTAI_UA')
+
+    def test_search(self):
+        result = search_parser('umaru', 'recent', [1], False)
+        self.assertTrue(len(result) > 0)
+
+    def test_doujinshi_parser(self):
+        result = doujinshi_parser(123456)
+        self.assertTrue(result['pages'] == 84)
+
+    def test_favorites_parser(self):
+        result = favorites_parser(page=[1])
+        self.assertTrue(len(result) > 0)