Bump requests from 2.32.3 to 2.32.4

Bumps [requests](https://github.com/psf/requests) from 2.32.3 to 2.32.4.
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](https://github.com/psf/requests/compare/v2.32.3...v2.32.4)

---
updated-dependencies:
- dependency-name: requests
  dependency-version: 2.32.4
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>

.dockerignore

@@ -0,0 +1,11 @@
+.git
+.github
+.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 +7,6 @@ dist/
 .DS_Store
 output/
 venv/
+.vscode/
+test-output
+*.whl

.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 +1,9 @@
+FROM python:3
+
+WORKDIR /usr/src/nhentai
+
+COPY . .
+RUN pip install --no-cache-dir .
+
+WORKDIR /output
+ENTRYPOINT ["nhentai"]

MANIFEST.in

@@ -1,8 +0,0 @@
-include README.md
-include requirements.txt
-include nhentai/viewer/index.html
-include nhentai/viewer/styles.css
-include nhentai/viewer/scripts.js
-include nhentai/viewer/main.html
-include nhentai/viewer/main.css
-include nhentai/viewer/main.js

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
+    pip install --no-cache-dir .
+
+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
+   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
+   pipx install nhentai
+
+Pull from Dockerhub:
 
-=====================
-Installation (Gentoo)
-=====================
 .. code-block::
 
-    layman -fa glicOne
+    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 glibOne
     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):
 
@@ -98,44 +129,57 @@ Download your favorites with delay:
 
 .. code-block:: bash
 
-    nhentai --favorites --download --delay 1
+    nhentai --favorites --download --delay 1 --page 3-5,7
 
 Format output doujinshi folder name:
 
 .. code-block:: bash
 
     nhentai --id 261100 --format '[%i]%s'
+    # for Windows
+    nhentai --id 261100 --format "[%%i]%%s"
 
 Supported doujinshi folder formatter:
 
 - %i: Doujinshi id
+- %f: Doujinshi favorite count
 - %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
 
+Note: for Windows operation system, please use double "%", such as "%%i".
 
 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 +188,37 @@ 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
+      --retry=RETRY         retry times when downloading failed
+      --exit-on-fail        exit on fail to prevent generating incomplete files
+      --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 +229,28 @@ 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 +258,8 @@ 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__ = '0.4.4'
+__version__ = '0.6.0-beta'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,40 +1,21 @@
 # coding: utf-8
-from __future__ import print_function
+
 import os
 import sys
 import json
-from optparse import OptionParser
-
-try:
-    from itertools import ifilter as filter
-except ImportError:
-    pass
-
 import nhentai.constant as constant
+
+from urllib.parse import urlparse
+from argparse import ArgumentParser
+
 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, EXTENSIONS
 from nhentai.logger import logger
-
-try:
-    if sys.version_info < (3, 0, 0):
-        import codecs
-        import locale
-        sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
-        sys.stderr = codecs.getwriter(locale.getpreferredencoding())(sys.stderr)
-
-except NameError:
-    # python3
-    pass
+from nhentai.constant import PATH_SEPARATOR
 
 
 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():
@@ -43,7 +24,7 @@ def load_config():
 
     try:
         with open(constant.NHENTAI_CONFIG_FILE, 'r') as f:
-            constant.CONFIG = json.load(f)
+            constant.CONFIG.update(json.load(f))
     except json.JSONDecodeError:
         logger.error('Failed to load config file.')
         write_config()
@@ -57,156 +38,235 @@ 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 --file [filename]'
-                          '\n\nEnvironment Variable:\n'
-                          '  NHENTAI                 nhentai mirror url')
+    parser = ArgumentParser(
+        description='\n  nhentai --search [keyword] --download'
+                    '\n  NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]'
+                    '\n  nhentai --file [filename]'
+                    '\n\nEnvironment Variable:\n'
+                    '  NHENTAI                 nhentai mirror url'
+    )
+
     # operation options
-    parser.add_option('--download', '-D', dest='is_download', action='store_true',
-                      help='download doujinshi (for search results)')
-    parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
+    parser.add_argument('--download', '-D', dest='is_download', action='store_true',
+                        help='download doujinshi (for search results)')
+    parser.add_argument('--no-download', dest='no_download', action='store_true', default=False,
+                        help='download doujinshi (for search results)')
+    parser.add_argument('--show', '-S', dest='is_show', action='store_true',
+                        help='just show the doujinshi information')
 
     # doujinshi options
-    parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
-    parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
-                      help='search doujinshi by keyword')
-    parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
-                      help='list or download your favorites.')
+    parser.add_argument('--id', dest='id', nargs='+', type=int,
+                        help='doujinshi ids set, e.g. 167680 167681 167682')
+    parser.add_argument('--search', '-s', type=str, dest='keyword',
+                        help='search doujinshi by keyword')
+    parser.add_argument('--favorites', '-F', action='store_true', dest='favorites',
+                        help='list or download your favorites')
+    parser.add_argument('--artist', '-a', type=str, 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='',
-                      help='page number of search results. e.g. 1,2-5,14')
-    parser.add_option('--sorting', dest='sorting', action='store', default='recent',
-                      help='sorting of doujinshi (recent / popular / popular-[today|week])',
-                      choices=['recent', 'popular', 'popular-today', 'popular-week'])
+    parser.add_argument('--page-all', dest='page_all', action='store_true', default=False,
+                        help='all search results')
+    parser.add_argument('--page', '--page-range', type=str, dest='page',
+                        help='page number of search results. e.g. 1,2-5,14')
+    parser.add_argument('--sorting', '--sort', dest='sorting', type=str, default='popular',
+                        help='sorting of doujinshi (recent / popular / popular-[today|week])',
+                        choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
-    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='',
-                      help='output dir')
-    parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
-                      help='thread count for downloading doujinshi')
-    parser.add_option('--timeout', '-T', type='int', dest='timeout', action='store', default=30,
-                      help='timeout for downloading doujinshi')
-    parser.add_option('--delay', '-d', type='int', dest='delay', action='store', default=0,
-                      help='slow down between downloading every doujinshi')
-    parser.add_option('--proxy', '-p', type='string', dest='proxy', action='store', default='',
-                      help='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_argument('--output', '-o', type=str, dest='output_dir', default='.',
+                        help='output dir')
+    parser.add_argument('--threads', '-t', type=int, dest='threads', default=5,
+                        help='thread count for downloading doujinshi')
+    parser.add_argument('--timeout', '-T', type=int, dest='timeout', default=30,
+                        help='timeout for downloading doujinshi')
+    parser.add_argument('--delay', '-d', type=int, dest='delay', default=0,
+                        help='slow down between downloading every doujinshi')
+    parser.add_argument('--retry', type=int, dest='retry', default=3,
+                        help='retry times when downloading failed')
+    parser.add_argument('--exit-on-fail', dest='exit_on_fail', action='store_true', default=False,
+                        help='exit on fail to prevent generating incomplete files')
+    parser.add_argument('--proxy', type=str, dest='proxy',
+                        help='store a proxy, for example: -p "http://127.0.0.1:1080"')
+    parser.add_argument('--file', '-f', type=str, dest='file',
+                        help='read gallery IDs from file.')
+    parser.add_argument('--format', type=str, dest='name_format', default='[%i][%a][%t]',
+                        help='format the saved folder name')
+
+    parser.add_argument('--no-filename-padding', action='store_true', dest='no_filename_padding',
+                        default=False, help='no padding in the images filename, such as \'001.jpg\'')
 
     # generate options
-    parser.add_option('--html', dest='html_viewer', action='store_true',
-                      help='generate a html viewer at current directory')
-    parser.add_option('--no-html', dest='is_nohtml', action='store_true',
-                      help='don\'t generate HTML after downloading')
-    parser.add_option('--gen-main', dest='main_viewer', action='store_true',
-                      help='generate a main viewer contain all the doujin in the folder')
-    parser.add_option('--cbz', '-C', dest='is_cbz', action='store_true',
-                      help='generate Comic Book CBZ File')
-    parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
-                      help='generate PDF file')
-    parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
-                      help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
+    parser.add_argument('--html', dest='html_viewer', type=str, nargs='?', const='.',
+                        help='generate an HTML viewer in the specified directory, or scan all subfolders '
+                             'within the entire directory to generate the HTML viewer. By default, current '
+                             'working directory is used.')
+    parser.add_argument('--no-html', dest='is_nohtml', action='store_true',
+                        help='don\'t generate HTML after downloading')
+    parser.add_argument('--gen-main', dest='main_viewer', action='store_true',
+                        help='generate a main viewer contain all the doujin in the folder')
+    parser.add_argument('--cbz', '-C', dest='is_cbz', action='store_true',
+                        help='generate Comic Book CBZ File')
+    parser.add_argument('--pdf', '-P', dest='is_pdf', action='store_true',
+                        help='generate PDF file')
+
+    parser.add_argument('--meta', dest='generate_metadata', action='store_true', default=False,
+                        help='generate a metadata file in doujinshi format')
+    parser.add_argument('--update-meta', dest='update_metadata', action='store_true', default=False,
+                        help='update the metadata file of a doujinshi, update CBZ metadata if exists')
+
+    parser.add_argument('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
+                        help='remove downloaded doujinshi dir when generated CBZ or PDF file')
+    parser.add_argument('--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_argument('--regenerate', dest='regenerate', action='store_true', default=False,
+                        help='regenerate the cbz or pdf file if exists')
+    parser.add_argument('--zip', action='store_true', help='Package into a single zip file')
 
     # nhentai options
-    parser.add_option('--cookie', type='str', dest='cookie', action='store',
-                      help='set cookie of nhentai to bypass Google recaptcha')
-    parser.add_option('--language', type='str', dest='language', action='store',
-                      help='set default language to parse doujinshis')
-    parser.add_option('--clean-language', dest='clean_language', action='store_true', default=False,
-                      help='set DEFAULT as language to parse doujinshis')
-    parser.add_option('--save-download-history', dest='is_save_download_history', action='store_true',
-                      default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
-    parser.add_option('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
-                      help='clean download history')
+    parser.add_argument('--cookie', type=str, dest='cookie',
+                        help='set cookie of nhentai to bypass Cloudflare captcha')
+    parser.add_argument('--useragent', '--user-agent', type=str, dest='useragent',
+                        help='set useragent to bypass Cloudflare captcha')
+    parser.add_argument('--language', type=str, dest='language',
+                        help='set default language to parse doujinshis')
+    parser.add_argument('--clean-language', dest='clean_language', action='store_true', default=False,
+                        help='set DEFAULT as language to parse doujinshis')
+    parser.add_argument('--save-download-history', dest='is_save_download_history', action='store_true',
+                        default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
+    parser.add_argument('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
+                        help='clean download history')
+    parser.add_argument('--template', dest='viewer_template', type=str, default='',
+                        help='set viewer template')
+    parser.add_argument('--legacy', dest='legacy', action='store_true', default=False,
+                        help='use legacy searching method')
 
-    try:
-        sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
-        print()
-    except (NameError, TypeError):
-        pass
-    except UnicodeDecodeError:
-        exit(0)
-
-    args, _ = parser.parse_args(sys.argv[1:])
+    args = parser.parse_args()
 
     if args.html_viewer:
-        generate_html()
-        exit(0)
+        if not os.path.exists(args.html_viewer):
+            logger.error(f'Path \'{args.html_viewer}\' not exists')
+            sys.exit(1)
+
+        for root, dirs, files in os.walk(args.html_viewer):
+            if not dirs:
+                generate_html(output_dir=args.html_viewer, template=constant.CONFIG['template'])
+                sys.exit(0)
+
+            for dir_name in dirs:
+                # it will scan the entire subdirectories
+                doujinshi_dir = os.path.join(root, dir_name)
+                items = set(map(lambda s: os.path.splitext(s)[1], os.listdir(doujinshi_dir)))
+
+                # skip directory without any images
+                if items & set(EXTENSIONS):
+                    generate_html(output_dir=doujinshi_dir, template=constant.CONFIG['template'])
+
+            sys.exit(0)
+
+        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:
-        constant.CONFIG['cookie'] = args.cookie
+    if args.cookie is not None:
+        constant.CONFIG['cookie'] = args.cookie.strip()
+        write_config()
         logger.info('Cookie saved.')
-        write_config()
-        exit(0)
 
-    if args.language:
-        constant.CONFIG['language'] = args.language
-        logger.info('LANGUAGE now set to \'{0}\''.format(args.language))
+    if args.useragent is not None:
+        constant.CONFIG['useragent'] = args.useragent.strip()
         write_config()
-        exit(0)
+        logger.info('User-Agent saved.')
+
+    if args.language is not None:
+        constant.CONFIG['language'] = args.language
+        write_config()
+        logger.info(f'Default language now set to "{args.language}"')
         # TODO: search without language
 
-    if args.proxy:
+    if any([args.cookie, args.useragent, args.language]):
+        sys.exit(0)
+
+    if args.proxy is not None:
         proxy_url = urlparse(args.proxy)
-        if proxy_url.scheme not in ('http', 'https'):
-            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
-        constant.CONFIG['proxy'] = {
-            'http': args.proxy,
-            'https': args.proxy,
-        }
-        logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
-        write_config()
-        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'] = args.proxy
+            logger.info(f'Proxy now set to "{args.proxy}"')
+            write_config()
+            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__),
+                                           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()
+
     # --- end set config ---
 
     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)
 
     return args

nhentai/command.py

@@ -1,53 +1,75 @@
-#!/usr/bin/env python2.7
 # coding: utf-8
-from __future__ import unicode_literals, print_function
-import json
 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.cmdline import cmd_parser, banner, write_config
+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.downloader import Downloader, CompressedDownloader
 from nhentai.logger import logger
-from nhentai.constant import NHENTAI_CONFIG_FILE, BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
-    paging, check_cookie, signal_handler, DB
+from nhentai.constant import BASE_URL
+from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata, \
+    paging, check_cookie, signal_handler, DB, move_to_folder
 
 
 def main():
     banner()
+
+    if sys.version_info < (3, 0, 0):
+        logger.error('nhentai now only support Python 3.x')
+        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']:
-        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']))
+        if isinstance(constant.CONFIG['proxy'], dict):
+            constant.CONFIG['proxy'] = constant.CONFIG['proxy'].get('http', '')
+            logger.warning(f'Update proxy config to: {constant.CONFIG["proxy"]}')
+            write_config()
+
+        logger.info(f'Using proxy: {constant.CONFIG["proxy"]}')
+
+    if not constant.CONFIG['template']:
+        constant.CONFIG['template'] = 'default'
+
+    logger.info(f'Using viewer template "{constant.CONFIG["template"]}"')
 
     # check your cookie
     check_cookie()
 
     doujinshis = []
     doujinshi_ids = []
-    doujinshi_list = []
 
     page_list = paging(options.page)
 
+    if options.retry:
+        constant.RETRY_TIMES = int(options.retry)
+
     if options.favorites:
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshis = favorites_parser(page=page_list)
+        doujinshis = favorites_parser(page=page_list) if options.page else favorites_parser()
 
     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,
-                                   is_page_all=options.page_all)
+            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
@@ -56,56 +78,83 @@ def main():
     if options.is_download and doujinshis:
         doujinshi_ids = [i['id'] for i in doujinshis]
 
-        if options.is_save_download_history:
-            with DB() as db:
-                data = set(db.get_all())
+    if options.is_save_download_history:
+        with DB() as db:
+            data = set(map(int, db.get_all()))
 
-            doujinshi_ids = list(set(doujinshi_ids) - data)
+        doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
+        logger.info(f'New doujinshis account: {len(doujinshi_ids)}')
 
-    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)))
+    if options.zip:
+        options.is_nohtml = True
 
     if not options.is_show:
-        downloader = Downloader(path=options.output_dir, size=options.threads,
-                                timeout=options.timeout, delay=options.delay)
+        downloader = (CompressedDownloader if options.zip else Downloader)(path=options.output_dir, threads=options.threads,
+                                timeout=options.timeout, delay=options.delay,
+                                exit_on_fail=options.exit_on_fail,
+                                no_filename_padding=options.no_filename_padding)
 
-        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.downloader = downloader
-            doujinshi.download()
+
+            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}')
+
+            if options.generate_metadata:
+                generate_metadata(options.output_dir, doujinshi)
+
             if options.is_save_download_history:
                 with DB() as db:
                     db.add_one(doujinshi.id)
 
-            if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
-                generate_html(options.output_dir, doujinshi)
-            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 not options.is_nohtml:
+                generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
+
+            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__':

nhentai/constant.py

@@ -1,37 +1,73 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 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/'
+
+PATH_SEPARATOR = os.path.sep
+
+RETRY_TIMES = 3
 
 
-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}://i1.{urlparse(BASE_URL).hostname}/galleries'
+IMAGE_URL_MIRRORS = [
+    f'{urlparse(BASE_URL).scheme}://i2.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i4.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i6.{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': {},
+    'proxy': '',
     '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

@@ -1,7 +1,7 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
+import os
+
 from tabulate import tabulate
-from future.builtins import range
 
 from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
@@ -12,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -21,65 +22,105 @@ 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, favorite_counts=0, img_id=None,
+                 ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
+        self.pretty_name = pretty_name
         self.id = id
+        self.favorite_counts = favorite_counts
         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('%f', format_filename(str(self.favorite_counts)))
+        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],
+            ['Title', 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],
+            ['Favorite Counts', self.favorite_counts],
+            ['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):
+        if options.no_download:
+            return False
+
+        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__':
@@ -89,4 +130,4 @@ if __name__ == '__main__':
     try:
         test.download()
     except Exception as e:
-        print('Exception: %s' % str(e))
+        print(f'Exception: {e}')

nhentai/downloader.py

@@ -1,156 +1,195 @@
 # coding: utf-
-from __future__ import unicode_literals, print_function
 
-import multiprocessing
-import signal
-
-from future.builtins import str as text
-import sys
 import os
-import requests
-import time
-
-try:
-    from urllib.parse import urlparse
-except ImportError:
-    from urlparse import urlparse
+import asyncio
+import httpx
+import urllib3.exceptions
+import zipfile
+import io
 
+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()
-semaphore = multiprocessing.Semaphore(1)
+from nhentai.utils import Singleton, async_request
 
 
-class NHentaiImageNotExistException(Exception):
-    pass
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+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):
-        self.size = size
+    def __init__(self, path='', threads=5, timeout=30, delay=0, exit_on_fail=False,
+                 no_filename_padding=False):
+        self.threads = threads
         self.path = str(path)
         self.timeout = timeout
         self.delay = delay
+        self.exit_on_fail = exit_on_fail
+        self.folder = None
+        self.semaphore = None
+        self.no_filename_padding = no_filename_padding
+
+    async def fiber(self, tasks):
+        self.semaphore = asyncio.Semaphore(self.threads)
+        for completed_task in asyncio.as_completed(tasks):
+            try:
+                result = await completed_task
+                if result[0] > 0:
+                    logger.info(f'{result[1]} download completed')
+                else:
+                    raise Exception(f'{result[1]} download failed, return value {result[0]}')
+            except Exception as e:
+                logger.error(f'An error occurred: {e}')
+                if self.exit_on_fail:
+                    raise Exception('User intends to exit on fail')
+
+    async def _semaphore_download(self, *args, **kwargs):
+        async with self.semaphore:
+            return await self.download(*args, **kwargs)
+
+    async def download(self, url, folder='', filename='', retried=0, proxy=None, length=0):
+        logger.info(f'Starting to download {url} ...')
 
-    def download_(self, url, folder='', filename='', retried=0):
         if self.delay:
-            time.sleep(self.delay)
-        logger.info('Starting to download {0} ...'.format(url))
+            await asyncio.sleep(self.delay)
+
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
+
+        if not self.no_filename_padding:
+            filename = base_filename.zfill(length) + extension
+        else:
+            filename = base_filename + 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)))
-                return 1, url
+            response = await async_request('GET', url, timeout=self.timeout, proxy=proxy)
 
-            response = None
-            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
-                i = 0
-                while i < 10:
-                    try:
-                        response = request('get', url, stream=True, timeout=self.timeout)
-                        if response.status_code != 200:
-                            raise NHentaiImageNotExistException
+            if response.status_code != 200:
+                path = urlparse(url).path
+                for mirror in constant.IMAGE_URL_MIRRORS:
+                    logger.info(f"Try mirror: {mirror}{path}")
+                    mirror_url = f'{mirror}{path}'
+                    response = await async_request('GET', mirror_url, timeout=self.timeout, proxies=proxy)
+                    if response.status_code == 200:
+                        break
 
-                    except NHentaiImageNotExistException as e:
-                        raise e
+            if not await self.save(filename, response):
+                logger.error(f'Can not download image {url}')
+                return -1, url
 
-                    except Exception as e:
-                        i += 1
-                        if not i < 10:
-                            logger.critical(str(e))
-                            return 0, None
-                        continue
+        except (httpx.HTTPStatusError, httpx.TimeoutException, httpx.ConnectError) as e:
+            if retried < constant.RETRY_TIMES:
+                logger.warning(f'Download {filename} failed, retrying({retried + 1}) times...')
+                return await self.download(
+                    url=url,
+                    folder=folder,
+                    filename=filename,
+                    retried=retried + 1,
+                    proxy=proxy,
+                )
+            else:
+                logger.warning(f'Download {filename} failed with {constant.RETRY_TIMES} times retried, skipped')
+                return -2, url
 
-                    break
+        except Exception as e:
+            import traceback
 
+            logger.error(f"Exception type: {type(e)}")
+            traceback.print_stack()
+            logger.critical(str(e))
+            return -9, url
+
+        except KeyboardInterrupt:
+            return -4, url
+
+        return 1, url
+
+    async def save(self, filename, response) -> bool:
+        if response is None:
+            logger.error('Error: Response is None')
+            return False
+        save_file_path = os.path.join(self.folder, filename)
+        with open(save_file_path, 'wb') as f:
+            if response is not None:
                 length = response.headers.get('content-length')
                 if length is None:
                     f.write(response.content)
                 else:
-                    for chunk in response.iter_content(2048):
+                    async for chunk in response.aiter_bytes(2048):
                         f.write(chunk)
+        return True
 
-        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)
-            else:
-                return 0, None
+    def create_storage_object(self, folder:str):
+        if not os.path.exists(folder):
+            try:
+                os.makedirs(folder)
+            except EnvironmentError as e:
+                logger.critical(str(e))
+        self.folder:str = folder
+        self.close = lambda: None # Only available in class CompressedDownloader
 
-        except NHentaiImageNotExistException as e:
-            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
-            return -1, url
-
-        except Exception as e:
-            import traceback
-            traceback.print_stack()
-            logger.critical(str(e))
-            return 0, None
-
-        except KeyboardInterrupt:
-            return -3, None
-
-        return 1, url
-
-    def _download_callback(self, 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)
 
-        if not os.path.exists(folder):
-            logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
-            try:
-                os.makedirs(folder)
-            except EnvironmentError as e:
-                logger.critical('{0}'.format(str(e)))
+        logger.info(f'Doujinshi will be saved at "{folder}"')
+        self.create_storage_object(folder)
 
+        if os.getenv('DEBUG', None) == 'NODOWNLOAD':
+            # Assuming we want to continue with rest of process.
+            return True
+
+        digit_length = len(str(len(queue)))
+        logger.info(f'Total download pages: {len(queue)}')
+        coroutines = [
+            self._semaphore_download(url, filename=os.path.basename(urlparse(url).path), length=digit_length)
+            for url in queue
+        ]
+
+        # Prevent coroutines infection
+        asyncio.run(self.fiber(coroutines))
+
+        self.close()
+
+        return True
+
+class CompressedDownloader(Downloader):
+    def create_storage_object(self, folder):
+        filename = f'{folder}.zip'
+        print(filename)
+        self.zipfile = zipfile.ZipFile(filename,'w')
+        self.close = lambda: self.zipfile.close()
+
+    async def save(self, filename, response) -> bool:
+        if response is None:
+            logger.error('Error: Response is None')
+            return False
+
+        image_data = io.BytesIO()
+        length = response.headers.get('content-length')
+        if length is None:
+            content = await response.read()
+            image_data.write(content)
         else:
-            logger.warn('Path \'{0}\' already exist.'.format(folder))
+            async for chunk in response.aiter_bytes(2048):
+                image_data.write(chunk)
 
-        queue = [(self, url, folder) for url in queue]
-
-        pool = multiprocessing.Pool(self.size, init_worker)
-        [pool.apply_async(download_wrapper, args=item) for item in queue]
-
-        pool.close()
-        pool.join()
-
-
-def download_wrapper(obj, url, folder=''):
-    if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download_(obj, url=url, folder=folder)
-    else:
-        return -3, None
-
-
-def init_worker():
-    signal.signal(signal.SIGINT, subprocess_signal)
-
-
-def subprocess_signal(signal, frame):
-    if semaphore.acquire(timeout=1):
-        logger.warning('Ctrl-C pressed, exiting sub processes ...')
-
-    raise KeyboardInterrupt
+        image_data.seek(0)
+        self.zipfile.writestr(filename, image_data.read())
+        return True

nhentai/logger.py

@@ -1,7 +1,6 @@
 #
 # Copyright (C) 2010-2012 Vinay Sajip. All rights reserved. Licensed under the new BSD license.
 #
-from __future__ import print_function, unicode_literals
 import logging
 import re
 import platform
@@ -35,7 +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)
@@ -161,20 +160,20 @@ 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.warn('warn')
+    logger.warning('warning')
     logger.debug('debug')
     logger.error('error')
     logger.critical('critical')

nhentai/parser.py

@@ -1,6 +1,5 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
-
+import sys
 import os
 import re
 import time
@@ -27,7 +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,
@@ -42,11 +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):
@@ -57,7 +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
@@ -68,7 +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(',', ''))
@@ -85,7 +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
@@ -93,64 +92,100 @@ def favorites_parser(page=None):
         page_range_list = range(1, pages + 1)
 
     for page in page_range_list:
-        try:
-            logger.info('Getting doujinshi ids of page %d' % page)
-            resp = request('get', constant.FAV_URL + '?page=%d' % page).content
+        logger.info(f'Getting doujinshi ids of page {page}')
 
-            result.extend(_get_title_and_id(resp))
-        except Exception as e:
-            logger.error('Error: %s, continue', str(e))
+        i = 0
+        while i <= constant.RETRY_TIMES + 1:
+            i += 1
+            if i > 3:
+                logger.error(f'Failed to get favorites at page {page} after 3 times retried, skipped')
+                break
+
+            try:
+                resp = request('get', f'{constant.FAV_URL}?page={page}').content
+                temp_result = _get_title_and_id(resp)
+                if not temp_result:
+                    logger.warning(f'Failed to get favorites at page {page}, retrying ({i} times) ...')
+                    continue
+                else:
+                    result.extend(temp_result)
+                    break
+
+            except Exception as e:
+                logger.warning(f'Error: {e}, retrying ({i} times) ...')
 
     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,):
+        if response.status_code in (200, ):
             response = response.content
+        elif response.status_code in (404,):
+            logger.error(f'Doujinshi with id {id_} cannot be found')
+            return []
         else:
-            logger.debug('Slow down and retry ({}) ...'.format(id_))
+            counter += 1
+
+            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_))
+            return doujinshi_parser(str(id_), counter)
 
     except Exception as e:
-        logger.warn('Error: {}, ignored'.format(str(e)))
+        logger.warning(f'Error: {e}, ignored')
         return None
 
     html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
+    pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
     subtitle = doujinshi_info.find('h2')
+    favorite_counts = doujinshi_info.find('span', class_='nobold').text.strip('(').strip(')')
 
     doujinshi['name'] = title
+    doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
+    doujinshi['favorite_counts'] = int(favorite_counts) if favorite_counts and favorite_counts.isdigit() else 0
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+    # img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
+    #                   doujinshi_cover.a.img.attrs['data-src'])
+
+    # fix cover.webp.webp
+    img_id = re.search(r'/galleries/(\d+)/cover(\.webp|\.jpg|\.png)?\.\w+$', doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
-        _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
-        ext.append(ext_name)
+        base_name = os.path.basename(i.img.attrs['data-src'])
+        ext_name = base_name.split('.')
+        if len(ext_name) == 3:
+            ext.append(ext_name[1])
+        else:
+            ext.append(ext_name[-1])
 
     if not img_id:
-        logger.critical('Tried yo get image id failed')
-        exit(1)
+        logger.critical(f'Tried yo get image id failed of id: {id_}')
+        return None
 
     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
@@ -172,29 +207,62 @@ 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.warn('Not found anything of keyword {}'.format(keyword))
-
-    return result
-
-
 def print_doujinshi(doujinshi_list):
     if not doujinshi_list:
         return
     doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
-    logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
-                tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+    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):
-    # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     result = []
+    response = None
     if not page:
         page = [1]
 
@@ -203,82 +271,48 @@ def search_parser(keyword, sorting, page, is_page_all=False):
         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 ''
+    total = f'/{page[-1]}' if is_page_all else ''
+    not_exists_persist = False
     for p in page:
         i = 0
 
-        logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
-        while i < 3:
+        logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
+        while i < constant.RETRY_TIMES:
             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 'result' not in response:
-            logger.warn('No result in response in page {}'.format(p))
-            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[:85] + '..' if len(title) > 85 else title
+            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.warn('No results for keywords {}'.format(keyword))
+            logger.warning(f'No results for keywords {keyword}')
 
     return result
 
 
-def __api_suspended_doujinshi_parser(id_):
-    if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
-
-    id_ = int(id_)
-    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
-    doujinshi = dict()
-    doujinshi['id'] = id_
-    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
-    i = 0
-    while 5 > i:
-        try:
-            response = request('get', url).json()
-        except Exception as e:
-            i += 1
-            if not i < 5:
-                logger.critical(str(e))
-                exit(1)
-            continue
-        break
-
-    doujinshi['name'] = response['title']['english']
-    doujinshi['subtitle'] = response['title']['japanese']
-    doujinshi['img_id'] = response['media_id']
-    doujinshi['ext'] = ''.join([i['t'] for i in response['images']['pages']])
-    doujinshi['pages'] = len(response['images']['pages'])
-
-    # gain information of the doujinshi
-    needed_fields = ['character', 'artist', 'language', 'tag', 'parody', 'group', 'category']
-    for tag in response['tags']:
-        tag_type = tag['type']
-        if tag_type in needed_fields:
-            if tag_type == 'tag':
-                if tag_type not in doujinshi:
-                    doujinshi[tag_type] = {}
-
-                tag['name'] = tag['name'].replace(' ', '-')
-                tag['name'] = tag['name'].lower()
-                doujinshi[tag_type][tag['name']] = tag['id']
-            elif tag_type not in doujinshi:
-                doujinshi[tag_type] = tag['name']
-            else:
-                doujinshi[tag_type] += ', ' + tag['name']
-
-    return doujinshi
-
-
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/serializer.py

@@ -1,12 +1,17 @@
 # coding: utf-8
 import json
 import os
+
+from nhentai.constant import PATH_SEPARATOR, LANGUAGE_ISO
 from xml.sax.saxutils import escape
+from requests.structures import CaseInsensitiveDict
 
 
-def serialize_json(doujinshi, dir):
+def serialize_json(doujinshi, output_dir: str):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
+    if doujinshi.info.favorite_counts:
+        metadata['favorite_counts'] = doujinshi.favorite_counts
     if doujinshi.info.date:
         metadata['upload_date'] = doujinshi.info.date
     if doujinshi.info.parodies:
@@ -21,17 +26,17 @@ 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')
@@ -43,9 +48,11 @@ def serialize_comicxml(doujinshi, dir):
         xml_write_simple_tag(f, 'PageCount', doujinshi.pages)
         xml_write_simple_tag(f, 'URL', doujinshi.url)
         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
+        xml_write_simple_tag(f, 'Favorites', doujinshi.favorite_counts)
         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)
@@ -54,29 +61,52 @@ def serialize_comicxml(doujinshi, dir):
             xml_write_simple_tag(f, 'Day', dt.day)
         if doujinshi.info.parodies:
             xml_write_simple_tag(f, 'Series', doujinshi.info.parodies)
+        if doujinshi.info.groups:
+            xml_write_simple_tag(f, 'Groups', doujinshi.info.groups)
         if doujinshi.info.characters:
             xml_write_simple_tag(f, 'Characters', doujinshi.info.characters)
         if doujinshi.info.tags:
             xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
         if doujinshi.info.artists:
-            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in doujinshi.info.artists.split(',')]))
-        # if doujinshi.info.groups:
-        #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
+            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 serialize_info_txt(doujinshi, output_dir: str):
+    info_txt_path = os.path.join(output_dir, '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',  'FAVORITE COUNTS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+
+    temp_dict = CaseInsensitiveDict(dict(doujinshi.table))
+    for i in fields:
+        v = temp_dict.get(i)
+        v = temp_dict.get(f'{i}s') if v is None else v
+        v = doujinshi.info.get(i.lower(), None) if v is None else v
+        v = doujinshi.info.get(f'{i.lower()}s', "Unknown") if v is None else v
+        f.write(f'{i}: {v}\n')
+
+    f.close()
+
+
 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():
     lst = []
-    output_dir = "./"
+    output_dir = f".{PATH_SEPARATOR}"
     os.chdir(output_dir)
     doujinshi_dirs = next(os.walk('.'))[1]
     for folder in doujinshi_dirs:
@@ -120,7 +150,8 @@ def serialize_unique(lst):
 def set_js_database():
     with open('data.js', 'w') as f:
         indexed_json = merge_json()
-        unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
-        indexed_json = json.dumps(indexed_json, separators=','':')
+        unique_json = json.dumps(serialize_unique(indexed_json), separators=(',', ':'))
+        indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)
+

nhentai/utils.py

@@ -1,37 +1,81 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
-
+import json
 import sys
 import re
 import os
-import string
 import zipfile
 import shutil
+
+import httpx
 import requests
 import sqlite3
+import urllib.parse
+from typing import Tuple
 
 from nhentai import constant
+from nhentai.constant import PATH_SEPARATOR
 from nhentai.logger import logger
-from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
+from nhentai.serializer import serialize_comic_xml, serialize_json, serialize_info_txt, set_js_database
 
+MAX_FIELD_LENGTH = 100
+EXTENSIONS = ('.png', '.jpg', '.jpeg', '.gif', '.webp')
+
+def get_headers():
+    headers = {
+        'Referer': constant.LOGIN_URL
+    }
+
+    user_agent = constant.CONFIG.get('useragent')
+    if user_agent and user_agent.strip():
+        headers['User-Agent'] = user_agent
+
+    cookie = constant.CONFIG.get('cookie')
+    if cookie and cookie.strip():
+        headers['Cookie'] = cookie
+
+    return headers
 
 def request(method, url, **kwargs):
     session = requests.Session()
-    session.headers.update({
-        'Referer': constant.LOGIN_URL,
-        'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
-        'Cookie': constant.CONFIG['cookie']
-    })
-    return getattr(session, method)(url, proxies=constant.CONFIG['proxy'], verify=False, **kwargs)
+    session.headers.update(get_headers())
+
+    if not kwargs.get('proxies', None):
+        kwargs['proxies'] = {
+            'https': constant.CONFIG['proxy'],
+            'http': constant.CONFIG['proxy'],
+        }
+
+    return getattr(session, method)(url, verify=False, **kwargs)
+
+
+async def async_request(method, url, proxy = None, **kwargs):
+    headers=get_headers()
+
+    if proxy is None:
+        proxy = constant.CONFIG['proxy']
+
+    if isinstance(proxy, (str, )) and not proxy:
+        proxy = None
+
+    async with httpx.AsyncClient(headers=headers, verify=False, proxy=proxy, **kwargs) as client:
+        response = await client.request(method, url, **kwargs)
+
+    return response
 
 
 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):
@@ -48,15 +92,6 @@ 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__)
 
@@ -64,52 +99,102 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None):
-    image_html = ''
+def parse_doujinshi_obj(
+        output_dir: str,
+        doujinshi_obj=None,
+        file_type: str = ''
+) -> Tuple[str, str]:
 
+    filename = f'.{PATH_SEPARATOR}doujinshi.{file_type}'
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+        _filename = f'{doujinshi_obj.filename}.{file_type}'
+
+        if file_type == 'pdf':
+            _filename = _filename.replace('/', '-')
+
+        filename = os.path.join(output_dir, _filename)
     else:
-        doujinshi_dir = '.'
+        if file_type == 'html':
+            return output_dir, 'index.html'
+
+        doujinshi_dir = f'.{PATH_SEPARATOR}'
+
+    if not os.path.exists(doujinshi_dir):
+        os.makedirs(doujinshi_dir)
+
+    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 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()
 
     for image in file_list:
-        if not os.path.splitext(image)[1] in ('.jpg', '.png'):
+        if not os.path.splitext(image)[1] in EXTENSIONS:
             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')
-    css = readfile('viewer/styles.css')
-    js = readfile('viewer/scripts.js')
+    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)
+        # 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'}
+        metadata_path = os.path.join(doujinshi_dir, "metadata.json")
+        if os.path.exists(metadata_path):
+            with open(metadata_path, 'r') as file:
+                doujinshi_info = json.loads(file.read())
+            name = doujinshi_info.get("title")
+        else:
+            name = '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'))
+        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 generate_main_html(output_dir='./'):
+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=f'.{PATH_SEPARATOR}'):
     """
-    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.
     """
@@ -138,7 +223,7 @@ 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
 
@@ -148,115 +233,115 @@ 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', './')
+        with open('./main.html', 'wb') as f:
+            f.write(data.encode('utf-8'))
+        shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
         set_js_database()
-        logger.log(
-            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
+        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_cbz(doujinshi_dir, filename):
     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))
+    logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
 
 
-def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
-    try:
-        import img2pdf
-    except ImportError:
-        logger.error("Please install img2pdf package by using pip.")
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
 
-    """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)
-        )
+    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':
+        serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+        generate_cbz(doujinshi_dir, filename)
+
+    elif file_type == 'pdf':
+        try:
+            import img2pdf
+
+            """Write images to a PDF file using img2pdf."""
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(EXTENSIONS)]
+            file_list.sort()
+
+            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, rotation=img2pdf.Rotation.ifvalid))
+
+            logger.log(16, f'PDF file has been written to "{filename}"')
+
+        except ImportError:
+            logger.error("Please install img2pdf package by using pip.")
     else:
-        pdf_filename = './doujinshi.pdf'
-        doujinshi_dir = '.'
-
-    file_list = os.listdir(doujinshi_dir)
-    file_list.sort()
-
-    logger.info('Writing PDF file to path: {}'.format(pdf_filename))
-    with open(pdf_filename, 'wb') as pdf_f:
-        full_path_list = (
-            [os.path.join(doujinshi_dir, image) for image in file_list]
-        )
-        pdf_f.write(img2pdf.convert(full_path_list))
-
-    if rm_origin_dir:
-        shutil.rmtree(doujinshi_dir, ignore_errors=True)
-
-    logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
+        raise ValueError('invalid file type')
 
 
-def format_filename(s):
-    """Take a string and return a valid filename constructed from the string.
-Uses a whitelist approach: any characters not present in valid_chars are
-removed. Also spaces are replaced with underscores.
+def generate_metadata(output_dir, doujinshi_obj=None):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '')
+    serialize_json(doujinshi_obj, doujinshi_dir)
+    serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+    serialize_info_txt(doujinshi_obj, doujinshi_dir)
+    logger.log(16, f'Metadata files have been written to "{doujinshi_dir}"')
 
-Note: this method may produce invalid filenames such as ``, `.` or `..`
-When I use this method I prepend a date string like '2009_01_15_19_46_32_'
-and append a file extension like '.txt', so I avoid the potential of using
-an invalid filename.
 
-"""
+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.
+    so it is using blacklist approach now.
+    if filename include forbidden characters (\'/:,;*?"<>|) ,it replaces space character(" ").
+    """
     # maybe you can use `--format` to select a suitable filename
-    valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
-    filename = ''.join(c for c in s if c in valid_chars)
-    if len(filename) > 100:
-        filename = filename[:100] + '...]'
+
+    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())
+
+        while filename.endswith('.'):
+            filename = filename[:-1]
+    else:
+        filename = s
+
+    # limit `length` chars
+    if len(filename) >= length:
+        filename = filename[:length - 1] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
     return filename
 
 
-def signal_handler(signal, frame):
+def signal_handler(_signal, _frame):
     logger.error('Ctrl-C signal received. Stopping...')
-    exit(1)
+    sys.exit(1)
 
 
 def paging(page_string):
     # 1,3-5,14 -> [1, 3, 4, 5, 14]
     if not page_string:
-        return []
+        # default, the first page
+        return [1]
 
     page_list = []
     for i in page_string.split(','):
@@ -264,7 +349,7 @@ 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')

nhentai/viewer/default/scripts.js

@@ -0,0 +1,87 @@
+const pages = Array.from(document.querySelectorAll('img.image-item'));
+let currentPage = 0;
+
+function changePage(pageNum) {
+    const previous = pages[currentPage];
+    const current = pages[pageNum];
+
+    if (current == null) {
+        return;
+    }
+    
+    previous.classList.remove('current');
+    current.classList.add('current');
+
+    currentPage = pageNum;
+
+    const display = document.getElementById('dest');
+    display.style.backgroundImage = `url("${current.src}")`;
+
+    scroll(0,0)
+
+    document.getElementById('page-num')
+        .innerText = [
+                (pageNum + 1).toLocaleString(),
+                pages.length.toLocaleString()
+            ].join('\u200a/\u200a');
+}
+
+changePage(0);
+
+document.getElementById('list').onclick = event => {
+    if (pages.includes(event.target)) {
+        changePage(pages.indexOf(event.target));
+    }
+};
+
+document.getElementById('image-container').onclick = event => {
+    const width = document.getElementById('image-container').clientWidth;
+    const clickPos = event.clientX / width;
+
+    if (clickPos < 0.5) {
+        changePage(currentPage - 1);
+    } else {
+        changePage(currentPage + 1);
+    }
+};
+
+document.onkeypress = event => {
+    switch (event.key.toLowerCase()) {
+        // Previous Image
+        case 'w':
+            scrollBy(0, -40);
+            break;
+        case 'a':
+            changePage(currentPage - 1);
+            break;
+        // Return to previous page
+        case 'q':
+            window.history.go(-1);
+            break;
+        // Next Image
+        case ' ':
+        case 's':
+            scrollBy(0, 40);
+            break;
+        case 'd':
+            changePage(currentPage + 1);
+            break;
+    }// remove arrow cause it won't work
+};
+
+document.onkeydown = event =>{
+    switch (event.keyCode) {
+        case 37: //left
+            changePage(currentPage - 1);
+            break;
+        case 38: //up
+            changePage(currentPage - 1);
+            break;
+        case 39: //right
+            changePage(currentPage + 1);
+            break;
+        case 40: //down
+            changePage(currentPage + 1);
+            break;
+    }
+};

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++){
@@ -174,4 +174,4 @@ function tag_maker(data){
 			document.getElementById("tags").appendChild(node);
 		}
 	}
-}
+}

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

@@ -28,12 +28,6 @@ function changePage(pageNum) {
 
 changePage(0);
 
-document.getElementById('list').onclick = event => {
-    if (pages.includes(event.target)) {
-        changePage(pages.indexOf(event.target));
-    }
-};
-
 document.getElementById('image-container').onclick = event => {
     const width = document.getElementById('image-container').clientWidth;
     const clickPos = event.clientX / width;

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 +1,370 @@
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+
+[[package]]
+name = "anyio"
+version = "4.5.2"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "anyio-4.5.2-py3-none-any.whl", hash = "sha256:c011ee36bc1e8ba40e5a81cb9df91925c218fe9b778554e0b56a21e1b5d4716f"},
+    {file = "anyio-4.5.2.tar.gz", hash = "sha256:23009af4ed04ce05991845451e11ef02fc7c5ed29179ac9a420e5ad0ac7ddc5b"},
+]
+
+[package.dependencies]
+exceptiongroup = {version = ">=1.0.2", markers = "python_version < \"3.11\""}
+idna = ">=2.8"
+sniffio = ">=1.1"
+typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "truststore (>=0.9.1) ; python_version >= \"3.10\"", "uvloop (>=0.21.0b1) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
+trio = ["trio (>=0.26.1)"]
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.12.3"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.6.0"
+groups = ["main"]
+files = [
+    {file = "beautifulsoup4-4.12.3-py3-none-any.whl", hash = "sha256:b80878c9f40111313e55da8ba20bdba06d8fa3969fc68304167741bbf9e082ed"},
+    {file = "beautifulsoup4-4.12.3.tar.gz", hash = "sha256:74e3d1928edc070d21748185c46e3fb33490f22f52a3addee9aee0f4f7781051"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+cchardet = ["cchardet"]
+chardet = ["chardet"]
+charset-normalizer = ["charset-normalizer"]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "certifi"
+version = "2024.12.14"
+description = "Python package for providing Mozilla's CA Bundle."
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "certifi-2024.12.14-py3-none-any.whl", hash = "sha256:1275f7a45be9464efc1173084eaa30f866fe2e47d389406136d332ed4967ec56"},
+    {file = "certifi-2024.12.14.tar.gz", hash = "sha256:b650d30f370c2b724812bee08008be0c4163b163ddaec3f2546c1caf65f191db"},
+]
+
+[[package]]
+name = "chardet"
+version = "5.2.0"
+description = "Universal encoding detector for Python 3"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "chardet-5.2.0-py3-none-any.whl", hash = "sha256:e1cf59446890a00105fe7b7912492ea04b6e6f06d4b742b2c788469e34c82970"},
+    {file = "chardet-5.2.0.tar.gz", hash = "sha256:1b3b6ff479a8c414bc3fa2c0852995695c4a026dcd6d0633b2dd092ca39c1cf7"},
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.1"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "charset_normalizer-3.4.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:91b36a978b5ae0ee86c394f5a54d6ef44db1de0815eb43de826d41d21e4af3de"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7461baadb4dc00fd9e0acbe254e3d7d2112e7f92ced2adc96e54ef6501c5f176"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e218488cd232553829be0664c2292d3af2eeeb94b32bea483cf79ac6a694e037"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:80ed5e856eb7f30115aaf94e4a08114ccc8813e6ed1b5efa74f9f82e8509858f"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b010a7a4fd316c3c484d482922d13044979e78d1861f0e0650423144c616a46a"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4532bff1b8421fd0a320463030c7520f56a79c9024a4e88f01c537316019005a"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:d973f03c0cb71c5ed99037b870f2be986c3c05e63622c017ea9816881d2dd247"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:3a3bd0dcd373514dcec91c411ddb9632c0d7d92aed7093b8c3bbb6d69ca74408"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:d9c3cdf5390dcd29aa8056d13e8e99526cda0305acc038b96b30352aff5ff2bb"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:2bdfe3ac2e1bbe5b59a1a63721eb3b95fc9b6817ae4a46debbb4e11f6232428d"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:eab677309cdb30d047996b36d34caeda1dc91149e4fdca0b1a039b3f79d9a807"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-win32.whl", hash = "sha256:c0429126cf75e16c4f0ad00ee0eae4242dc652290f940152ca8c75c3a4b6ee8f"},
+    {file = "charset_normalizer-3.4.1-cp310-cp310-win_amd64.whl", hash = "sha256:9f0b8b1c6d84c8034a44893aba5e767bf9c7a211e313a9605d9c617d7083829f"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:8bfa33f4f2672964266e940dd22a195989ba31669bd84629f05fab3ef4e2d125"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28bf57629c75e810b6ae989f03c0828d64d6b26a5e205535585f96093e405ed1"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f08ff5e948271dc7e18a35641d2f11a4cd8dfd5634f55228b691e62b37125eb3"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:234ac59ea147c59ee4da87a0c0f098e9c8d169f4dc2a159ef720f1a61bbe27cd"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd4ec41f914fa74ad1b8304bbc634b3de73d2a0889bd32076342a573e0779e00"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eea6ee1db730b3483adf394ea72f808b6e18cf3cb6454b4d86e04fa8c4327a12"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c96836c97b1238e9c9e3fe90844c947d5afbf4f4c92762679acfe19927d81d77"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:4d86f7aff21ee58f26dcf5ae81a9addbd914115cdebcbb2217e4f0ed8982e146"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:09b5e6733cbd160dcc09589227187e242a30a49ca5cefa5a7edd3f9d19ed53fd"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:5777ee0881f9499ed0f71cc82cf873d9a0ca8af166dfa0af8ec4e675b7df48e6"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:237bdbe6159cff53b4f24f397d43c6336c6b0b42affbe857970cefbb620911c8"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-win32.whl", hash = "sha256:8417cb1f36cc0bc7eaba8ccb0e04d55f0ee52df06df3ad55259b9a323555fc8b"},
+    {file = "charset_normalizer-3.4.1-cp311-cp311-win_amd64.whl", hash = "sha256:d7f50a1f8c450f3925cb367d011448c39239bb3eb4117c36a6d354794de4ce76"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:73d94b58ec7fecbc7366247d3b0b10a21681004153238750bb67bd9012414545"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dad3e487649f498dd991eeb901125411559b22e8d7ab25d3aeb1af367df5efd7"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c30197aa96e8eed02200a83fba2657b4c3acd0f0aa4bdc9f6c1af8e8962e0757"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2369eea1ee4a7610a860d88f268eb39b95cb588acd7235e02fd5a5601773d4fa"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc2722592d8998c870fa4e290c2eec2c1569b87fe58618e67d38b4665dfa680d"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffc9202a29ab3920fa812879e95a9e78b2465fd10be7fcbd042899695d75e616"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:804a4d582ba6e5b747c625bf1255e6b1507465494a40a2130978bda7b932c90b"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:0f55e69f030f7163dffe9fd0752b32f070566451afe180f99dbeeb81f511ad8d"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:c4c3e6da02df6fa1410a7680bd3f63d4f710232d3139089536310d027950696a"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:5df196eb874dae23dcfb968c83d4f8fdccb333330fe1fc278ac5ceeb101003a9"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e358e64305fe12299a08e08978f51fc21fac060dcfcddd95453eabe5b93ed0e1"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-win32.whl", hash = "sha256:9b23ca7ef998bc739bf6ffc077c2116917eabcc901f88da1b9856b210ef63f35"},
+    {file = "charset_normalizer-3.4.1-cp312-cp312-win_amd64.whl", hash = "sha256:6ff8a4a60c227ad87030d76e99cd1698345d4491638dfa6673027c48b3cd395f"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:aabfa34badd18f1da5ec1bc2715cadc8dca465868a4e73a0173466b688f29dda"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22e14b5d70560b8dd51ec22863f370d1e595ac3d024cb8ad7d308b4cd95f8313"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8436c508b408b82d87dc5f62496973a1805cd46727c34440b0d29d8a2f50a6c9"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2d074908e1aecee37a7635990b2c6d504cd4766c7bc9fc86d63f9c09af3fa11b"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:955f8851919303c92343d2f66165294848d57e9bba6cf6e3625485a70a038d11"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:44ecbf16649486d4aebafeaa7ec4c9fed8b88101f4dd612dcaf65d5e815f837f"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:0924e81d3d5e70f8126529951dac65c1010cdf117bb75eb02dd12339b57749dd"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2967f74ad52c3b98de4c3b32e1a44e32975e008a9cd2a8cc8966d6a5218c5cb2"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:c75cb2a3e389853835e84a2d8fb2b81a10645b503eca9bcb98df6b5a43eb8886"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:09b26ae6b1abf0d27570633b2b078a2a20419c99d66fb2823173d73f188ce601"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:fa88b843d6e211393a37219e6a1c1df99d35e8fd90446f1118f4216e307e48cd"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-win32.whl", hash = "sha256:eb8178fe3dba6450a3e024e95ac49ed3400e506fd4e9e5c32d30adda88cbd407"},
+    {file = "charset_normalizer-3.4.1-cp313-cp313-win_amd64.whl", hash = "sha256:b1ac5992a838106edb89654e0aebfc24f5848ae2547d22c2c3f66454daa11971"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f30bf9fd9be89ecb2360c7d94a711f00c09b976258846efe40db3d05828e8089"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:97f68b8d6831127e4787ad15e6757232e14e12060bec17091b85eb1486b91d8d"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7974a0b5ecd505609e3b19742b60cee7aa2aa2fb3151bc917e6e2646d7667dcf"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc54db6c8593ef7d4b2a331b58653356cf04f67c960f584edb7c3d8c97e8f39e"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:311f30128d7d333eebd7896965bfcfbd0065f1716ec92bd5638d7748eb6f936a"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:7d053096f67cd1241601111b698f5cad775f97ab25d81567d3f59219b5f1adbd"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_i686.whl", hash = "sha256:807f52c1f798eef6cf26beb819eeb8819b1622ddfeef9d0977a8502d4db6d534"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:dccbe65bd2f7f7ec22c4ff99ed56faa1e9f785482b9bbd7c717e26fd723a1d1e"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_s390x.whl", hash = "sha256:2fb9bd477fdea8684f78791a6de97a953c51831ee2981f8e4f583ff3b9d9687e"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:01732659ba9b5b873fc117534143e4feefecf3b2078b0a6a2e925271bb6f4cfa"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-win32.whl", hash = "sha256:7a4f97a081603d2050bfaffdefa5b02a9ec823f8348a572e39032caa8404a487"},
+    {file = "charset_normalizer-3.4.1-cp37-cp37m-win_amd64.whl", hash = "sha256:7b1bef6280950ee6c177b326508f86cad7ad4dff12454483b51d8b7d673a2c5d"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:ecddf25bee22fe4fe3737a399d0d177d72bc22be6913acfab364b40bce1ba83c"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c60ca7339acd497a55b0ea5d506b2a2612afb2826560416f6894e8b5770d4a9"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b7b2d86dd06bfc2ade3312a83a5c364c7ec2e3498f8734282c6c3d4b07b346b8"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dd78cfcda14a1ef52584dbb008f7ac81c1328c0f58184bf9a84c49c605002da6"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6e27f48bcd0957c6d4cb9d6fa6b61d192d0b13d5ef563e5f2ae35feafc0d179c"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:01ad647cdd609225c5350561d084b42ddf732f4eeefe6e678765636791e78b9a"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:619a609aa74ae43d90ed2e89bdd784765de0a25ca761b93e196d938b8fd1dbbd"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:89149166622f4db9b4b6a449256291dc87a99ee53151c74cbd82a53c8c2f6ccd"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:7709f51f5f7c853f0fb938bcd3bc59cdfdc5203635ffd18bf354f6967ea0f824"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:345b0426edd4e18138d6528aed636de7a9ed169b4aaf9d61a8c19e39d26838ca"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:0907f11d019260cdc3f94fbdb23ff9125f6b5d1039b76003b5b0ac9d6a6c9d5b"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-win32.whl", hash = "sha256:ea0d8d539afa5eb2728aa1932a988a9a7af94f18582ffae4bc10b3fbdad0626e"},
+    {file = "charset_normalizer-3.4.1-cp38-cp38-win_amd64.whl", hash = "sha256:329ce159e82018d646c7ac45b01a430369d526569ec08516081727a20e9e4af4"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:b97e690a2118911e39b4042088092771b4ae3fc3aa86518f84b8cf6888dbdb41"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:78baa6d91634dfb69ec52a463534bc0df05dbd546209b79a3880a34487f4b84f"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1a2bc9f351a75ef49d664206d51f8e5ede9da246602dc2d2726837620ea034b2"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:75832c08354f595c760a804588b9357d34ec00ba1c940c15e31e96d902093770"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0af291f4fe114be0280cdd29d533696a77b5b49cfde5467176ecab32353395c4"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0167ddc8ab6508fe81860a57dd472b2ef4060e8d378f0cc555707126830f2537"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:2a75d49014d118e4198bcee5ee0a6f25856b29b12dbf7cd012791f8a6cc5c496"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:363e2f92b0f0174b2f8238240a1a30142e3db7b957a5dd5689b0e75fb717cc78"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:ab36c8eb7e454e34e60eb55ca5d241a5d18b2c6244f6827a30e451c42410b5f7"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:4c0907b1928a36d5a998d72d64d8eaa7244989f7aaaf947500d3a800c83a3fd6"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:04432ad9479fa40ec0f387795ddad4437a2b50417c69fa275e212933519ff294"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-win32.whl", hash = "sha256:3bed14e9c89dcb10e8f3a29f9ccac4955aebe93c71ae803af79265c9ca5644c5"},
+    {file = "charset_normalizer-3.4.1-cp39-cp39-win_amd64.whl", hash = "sha256:49402233c892a461407c512a19435d1ce275543138294f7ef013f0b63d5d3765"},
+    {file = "charset_normalizer-3.4.1-py3-none-any.whl", hash = "sha256:d98b1668f06378c6dbefec3b92299716b931cd4e6061f3c875a71ced1780ab85"},
+    {file = "charset_normalizer-3.4.1.tar.gz", hash = "sha256:44251f18cd68a75b56585dd00dae26183e102cd5e0f9f1466e6df5da2ed64ea3"},
+]
+
+[[package]]
+name = "exceptiongroup"
+version = "1.2.2"
+description = "Backport of PEP 654 (exception groups)"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "python_version < \"3.11\""
+files = [
+    {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
+    {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
+]
+
+[package.extras]
+test = ["pytest (>=6)"]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
+    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.7"
+description = "A minimal low-level HTTP client."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "httpcore-1.0.7-py3-none-any.whl", hash = "sha256:a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd"},
+    {file = "httpcore-1.0.7.tar.gz", hash = "sha256:8551cb62a169ec7162ac7be8d4817d561f60e08eaa485234898414bb5a8a0b4c"},
+]
+
+[package.dependencies]
+certifi = "*"
+h11 = ">=0.13,<0.15"
+
+[package.extras]
+asyncio = ["anyio (>=4.0,<5.0)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (==1.*)"]
+trio = ["trio (>=0.22.0,<1.0)"]
+
+[[package]]
+name = "httpx"
+version = "0.28.1"
+description = "The next generation HTTP client."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad"},
+    {file = "httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc"},
+]
+
+[package.dependencies]
+anyio = "*"
+certifi = "*"
+httpcore = "==1.*"
+idna = "*"
+
+[package.extras]
+brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
+cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (==1.*)"]
+zstd = ["zstandard (>=0.18.0)"]
+
+[[package]]
+name = "idna"
+version = "3.10"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
+    {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
+]
+
+[package.extras]
+all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
+
+[[package]]
+name = "iso8601"
+version = "1.1.0"
+description = "Simple module to parse ISO 8601 dates"
+optional = false
+python-versions = ">=3.6.2,<4.0"
+groups = ["main"]
+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 = "2.32.4"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c"},
+    {file = "requests-2.32.4.tar.gz", hash = "sha256:27d0316682c8a29834d3264820024b62a36942083d52caf2f14c0591336d3422"},
+]
+
+[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 = "sniffio"
+version = "1.3.1"
+description = "Sniff out which async library your code is running under"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2"},
+    {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"},
+]
+
+[[package]]
+name = "soupsieve"
+version = "2.6"
+description = "A modern CSS selector implementation for Beautiful Soup."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "soupsieve-2.6-py3-none-any.whl", hash = "sha256:e72c4ff06e4fb6e4b5a9f0f55fe6e81514581fca1515028625d0f299c602ccc9"},
+    {file = "soupsieve-2.6.tar.gz", hash = "sha256:e2e68417777af359ec65daac1057404a3c8a5455bb8abc36f1a9866ab1a51abb"},
+]
+
+[[package]]
+name = "tabulate"
+version = "0.9.0"
+description = "Pretty-print tabular data"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+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 = "typing-extensions"
+version = "4.12.2"
+description = "Backported and Experimental Type Hints for Python 3.8+"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+markers = "python_version < \"3.11\""
+files = [
+    {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"},
+    {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
+]
+
+[[package]]
+name = "urllib3"
+version = "1.26.20"
+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"
+groups = ["main"]
+files = [
+    {file = "urllib3-1.26.20-py2.py3-none-any.whl", hash = "sha256:0ed14ccfbf1c30a9072c7ca157e4319b70d65f623e91e7b32fadb2853431016e"},
+    {file = "urllib3-1.26.20.tar.gz", hash = "sha256:40c2dc0c681e47eb8f90e7e27bf6ff7df2e677421fd46756da1161c39ca70d32"},
+]
+
+[package.extras]
+brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress ; python_version == \"2.7\"", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[metadata]
+lock-version = "2.1"
+python-versions = "^3.8"
+content-hash = "b17c2cdd4b140f2ab8081bca7d94630e821fa2e882ac768b1bd8cf3ec58726ce"

pyproject.toml

@@ -0,0 +1,28 @@
+[tool.poetry]
+name = "nhentai"
+version = "0.6.0-beta"
+description = "nhentai doujinshi downloader"
+authors = ["Ricter Z <ricterzheng@gmail.com>"]
+license = "MIT"
+readme = "README.rst"
+include = ["nhentai/viewer/**"]
+
+
+[tool.poetry.dependencies]
+python = "^3.8"
+requests = "^2.32.3"
+soupsieve = "^2.6"
+beautifulsoup4 = "^4.12.3"
+tabulate = "^0.9.0"
+iso8601 = "^1.1.0"
+urllib3 = "^1.26.20"
+httpx = "^0.28.1"
+
+
+chardet = "^5.2.0"
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.scripts]
+nhentai = 'nhentai.command:main'

qodana.yaml

@@ -0,0 +1,29 @@
+#-------------------------------------------------------------------------------#
+#               Qodana analysis is configured by qodana.yaml file               #
+#             https://www.jetbrains.com/help/qodana/qodana-yaml.html            #
+#-------------------------------------------------------------------------------#
+version: "1.0"
+
+#Specify inspection profile for code analysis
+profile:
+  name: qodana.starter
+
+#Enable inspections
+#include:
+#  - name: <SomeEnabledInspectionId>
+
+#Disable inspections
+#exclude:
+#  - name: <SomeDisabledInspectionId>
+#    paths:
+#      - <path/where/not/run/inspection>
+
+#Execute shell command before Qodana execution (Applied in CI/CD pipeline)
+#bootstrap: sh ./prepare-qodana.sh
+
+#Install IDE plugins before Qodana execution (Applied in CI/CD pipeline)
+#plugins:
+#  - id: <plugin.id> #(plugin id can be found at https://plugins.jetbrains.com)
+
+#Specify Qodana linter for analysis (Applied in CI/CD pipeline)
+linter: jetbrains/qodana-python:2024.3

requirements.txt

@@ -1,7 +0,0 @@
-requests>=2.5.0
-soupsieve<2.0
-BeautifulSoup4>=4.0.0
-threadpool>=1.2.7
-tabulate>=0.7.5
-future>=0.15.2
-iso8601 >= 0.1

setup.cfg

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

setup.py

@@ -1,41 +0,0 @@
-# coding: utf-8
-from __future__ import print_function, unicode_literals
-import sys
-import codecs
-from setuptools import setup, find_packages
-from nhentai import __version__, __author__, __email__
-
-
-with open('requirements.txt') as f:
-    requirements = [l for l in f.read().splitlines() if l]
-
-
-def long_description():
-    with codecs.open('README.rst', 'rb') as readme:
-        if not sys.version_info < (3, 0, 0):
-            return readme.read().decode('utf-8')
-
-
-setup(
-    name='nhentai',
-    version=__version__,
-    packages=find_packages(),
-
-    author=__author__,
-    author_email=__email__,
-    keywords=['nhentai', 'doujinshi', 'downloader'],
-    description='nhentai.net doujinshis downloader',
-    long_description=long_description(),
-    url='https://github.com/RicterZ/nhentai',
-    download_url='https://github.com/RicterZ/nhentai/tarball/master',
-    include_package_data=True,
-    zip_safe=False,
-
-    install_requires=requirements,
-    entry_points={
-        'console_scripts': [
-            'nhentai = nhentai.command:main',
-        ]
-    },
-    license='MIT',
-)

tests/test_download.py

@@ -0,0 +1,56 @@
+import unittest
+import os
+import zipfile
+import urllib3.exceptions
+
+from nhentai import constant
+from nhentai.cmdline import load_config
+from nhentai.downloader import Downloader, CompressedDownloader
+from nhentai.parser import doujinshi_parser
+from nhentai.doujinshi import Doujinshi
+from nhentai.utils import generate_html
+
+did = 440546
+
+def has_jepg_file(path):
+    with zipfile.ZipFile(path, 'r') as zf:
+        return '01.jpg' in zf.namelist()
+
+def is_zip_file(path):
+    try:
+        with zipfile.ZipFile(path, 'r') as _:
+            return True
+    except (zipfile.BadZipFile, FileNotFoundError):
+        return False
+
+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')
+
+        self.info = Doujinshi(**doujinshi_parser(did), name_format='%i')
+
+    def test_download(self):
+        info = self.info
+        info.downloader = Downloader(path='/tmp', threads=5)
+        info.download()
+
+        self.assertTrue(os.path.exists(f'/tmp/{did}/01.jpg'))
+
+        generate_html('/tmp', info)
+        self.assertTrue(os.path.exists(f'/tmp/{did}/index.html'))
+
+    def test_zipfile_download(self):
+        info = self.info
+        info.downloader = CompressedDownloader(path='/tmp', threads=5)
+        info.download()
+
+        zipfile_path = f'/tmp/{did}.zip'
+        self.assertTrue(os.path.exists(zipfile_path))
+        self.assertTrue(is_zip_file(zipfile_path))
+        self.assertTrue(has_jepg_file(zipfile_path))
+
+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)