0.6.0-beta #394

Update installation instructions in README.rst

.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

@@ -8,3 +8,5 @@ dist/
 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

@@ -1,5 +0,0 @@
-include README.md
-include requirements.txt
-include nhentai/viewer/*
-include nhentai/viewer/default/*
-include nhentai/viewer/minimal/*

README.rst

@@ -9,43 +9,61 @@ nhentai
 |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
 
-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
 
-=====================
+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:
-Installation (NixOs)
+
-=====================
 .. code-block::
 
     nix-env -iA nixos.nhentai
@@ -55,17 +73,12 @@ Usage
 =====
 **⚠️IMPORTANT⚠️**: To bypass the nhentai frequency limit, you should use `--cookie` and `--useragent` options to store your cookie and your user-agent.
 
-*The default download folder will be the path where you run the command (CLI path).*
-
-
-Set your nhentai cookie against captcha:
-
 .. code-block:: bash
 
     nhentai --useragent "USER AGENT of YOUR BROWSER"
     nhentai --cookie "YOUR COOKIE FROM nhentai.net"
 
-**NOTE**
+**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
@@ -79,10 +92,12 @@ Set your nhentai cookie against captcha:
 .. |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:: ./images/usage.png?raw=true
+.. 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
@@ -114,22 +129,28 @@ 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:
 
@@ -144,25 +165,21 @@ Other options:
       NHENTAI                 nhentai mirror url
 
     Options:
-      # Operation options, control the program behaviors
       -h, --help            show this help message and exit
       -D, --download        download doujinshi (for search results)
       -S, --show            just show the doujinshi information
-
-      # Doujinshi options, specify id, keyword, etc.
       --id                  doujinshi ids set, e.g. 167680 167681 167682
       -s KEYWORD, --search=KEYWORD
                             search doujinshi by keyword
       -F, --favorites       list or download your favorites
-
+      -a ARTIST, --artist=ARTIST
-      # Page options, control the page to fetch / download
+                            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     sorting of doujinshi (recent / popular /
+      --sorting=SORTING, --sort=SORTING
+                            sorting of doujinshi (recent / popular /
                             popular-[today|week])
-
-      # Download options, the output directory, threads, timeout, delay, etc.
       -o OUTPUT_DIR, --output=OUTPUT_DIR
                             output dir
       -t THREADS, --threads=THREADS
@@ -171,12 +188,12 @@ Other options:
                             timeout for downloading doujinshi
       -d DELAY, --delay=DELAY
                             slow down between downloading every doujinshi
+      --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
       --dry-run             Dry run, skip file download
-
-      # Generate options, for generate html viewer, cbz file, pdf file, etc
       --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
@@ -185,10 +202,10 @@ Other options:
       -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-cbz      regenerate the cbz file if exists
+      --regenerate          regenerate the cbz or pdf file if exists
-
-      # nhentai options, set cookie, user-agent, language, remove caches, histories, etc
       --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
       --useragent=USERAGENT, --user-agent=USERAGENT
                             set useragent to bypass Cloudflare captcha
@@ -212,6 +229,9 @@ 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.
@@ -221,13 +241,13 @@ Set `NHENTAI` env var to your nhentai mirror.
     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
 

doujinshi.txt

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

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.1'
+__version__ = '0.6.0-beta'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -3,17 +3,15 @@
 import os
 import sys
 import json
+import nhentai.constant as constant
+
+from urllib.parse import urlparse
 from optparse import OptionParser
 
-try:
-    from itertools import ifilter as filter
-except ImportError:
-    pass
-
-import nhentai.constant as constant
 from nhentai import __version__
-from nhentai.utils import urlparse, generate_html, generate_main_html, DB
+from nhentai.utils import generate_html, generate_main_html, DB
 from nhentai.logger import logger
+from nhentai.constant import PATH_SEPARATOR
 
 
 def banner():
@@ -40,7 +38,7 @@ def write_config():
         f.write(json.dumps(constant.CONFIG))
 
 
-def callback(option, opt_str, value, parser):
+def callback(option, _opt_str, _value, parser):
     if option == '--id':
         pass
     value = []
@@ -67,7 +65,10 @@ def cmd_parser():
     # 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_option('--no-download', dest='no_download', action='store_true', default=False,
+                      help='download doujinshi (for search results)')
+    parser.add_option('--show', '-S', dest='is_show', action='store_true',
+                      help='just show the doujinshi information')
 
     # doujinshi options
     parser.add_option('--id', dest='id', action='callback', callback=callback,
@@ -76,18 +77,21 @@ def cmd_parser():
                       help='search doujinshi by keyword')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
                       help='list or download your favorites')
+    parser.add_option('--artist', '-a', action='store', dest='artist',
+                      help='list doujinshi by artist name')
 
     # page options
     parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
                       help='all search results')
-    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='',
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store',
                       help='page number of search results. e.g. 1,2-5,14')
-    parser.add_option('--sorting', dest='sorting', action='store', default='popular',
+    parser.add_option('--sorting', '--sort', dest='sorting', action='store', default='popular',
                       help='sorting of doujinshi (recent / popular / popular-[today|week])',
                       choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
-    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='./',
+    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store',
+                      default=f'.{PATH_SEPARATOR}',
                       help='output dir')
     parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
                       help='thread count for downloading doujinshi')
@@ -95,12 +99,19 @@ def cmd_parser():
                       help='timeout for downloading doujinshi')
     parser.add_option('--delay', '-d', type='int', dest='delay', action='store', default=0,
                       help='slow down between downloading every doujinshi')
+    parser.add_option('--retry', type='int', dest='retry', action='store', default=3,
+                      help='retry times when downloading failed')
+    parser.add_option('--exit-on-fail', dest='exit_on_fail', action='store_true', default=False,
+                      help='exit on fail to prevent generating incomplete files')
     parser.add_option('--proxy', type='string', dest='proxy', action='store',
                       help='store a proxy, for example: -p "http://127.0.0.1:1080"')
-    parser.add_option('--file', '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+    parser.add_option('--file', '-f', type='string', dest='file', action='store',
+                      help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
                       help='format the saved folder name', default='[%i][%a][%t]')
-    parser.add_option('--dry-run', action='store_true', dest='dryrun', help='Dry run, skip file download')
+
+    parser.add_option('--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',
@@ -113,12 +124,19 @@ def cmd_parser():
                       help='generate Comic Book CBZ File')
     parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
                       help='generate PDF file')
+
+    parser.add_option('--meta', dest='generate_metadata', action='store_true', default=False,
+                      help='generate a metadata file in doujinshi format')
+    parser.add_option('--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_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_option('--meta', dest='generate_metadata', action='store_true',
+    parser.add_option('--move-to-folder', dest='move_to_folder', action='store_true', default=False,
-                      help='generate a metadata file in doujinshi format')
+                      help='remove files in doujinshi dir then move new file to folder when generated CBZ or PDF file')
-    parser.add_option('--regenerate-cbz', dest='regenerate_cbz', action='store_true', default=False,
+
-                      help='regenerate the cbz file if exists')
+    parser.add_option('--regenerate', dest='regenerate', action='store_true', default=False,
+                      help='regenerate the cbz or pdf file if exists')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
@@ -142,51 +160,50 @@ def cmd_parser():
 
     if args.html_viewer:
         generate_html(template=constant.CONFIG['template'])
-        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 is not None:
-        constant.CONFIG['cookie'] = args.cookie
+        constant.CONFIG['cookie'] = args.cookie.strip()
         write_config()
         logger.info('Cookie saved.')
-        exit(0)
+
-    elif args.useragent is not None:
+    if args.useragent is not None:
-        constant.CONFIG['useragent'] = args.useragent
+        constant.CONFIG['useragent'] = args.useragent.strip()
         write_config()
         logger.info('User-Agent saved.')
-        exit(0)
+
-    elif args.language is not None:
+    if args.language is not None:
         constant.CONFIG['language'] = args.language
         write_config()
         logger.info(f'Default language now set to "{args.language}"')
-        exit(0)
         # TODO: search without language
 
+    if any([args.cookie, args.useragent, args.language]):
+        sys.exit(0)
+
     if args.proxy is not None:
         proxy_url = urlparse(args.proxy)
         if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h',
                                                              'socks4', 'socks4a'):
             logger.error(f'Invalid protocol "{proxy_url.scheme}" of proxy, ignored')
-            exit(0)
+            sys.exit(0)
         else:
-            constant.CONFIG['proxy'] = {
+            constant.CONFIG['proxy'] = args.proxy
-                'http': args.proxy,
-                'https': args.proxy,
-            }
             logger.info(f'Proxy now set to "{args.proxy}"')
             write_config()
-            exit(0)
+            sys.exit(0)
 
     if args.viewer_template is not None:
         if not args.viewer_template:
@@ -195,7 +212,7 @@ def cmd_parser():
         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')
-            exit(1)
+            sys.exit(1)
         else:
             constant.CONFIG['template'] = args.viewer_template
             write_config()
@@ -205,31 +222,27 @@ def cmd_parser():
     if args.favorites:
         if not constant.CONFIG['cookie']:
             logger.warning('Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.')
-            exit(1)
+            sys.exit(1)
 
     if args.file:
         with open(args.file, 'r') as f:
             _ = [i.strip() for i in f.readlines()]
             args.id = set(int(i) for i in _ if i.isdigit())
 
-    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites:
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites and not args.artist:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
-        exit(1)
+        sys.exit(1)
 
-    if not args.keyword and not args.id and not args.favorites:
+    if not args.keyword and not args.id and not args.favorites and not args.artist:
         parser.print_help()
-        exit(1)
+        sys.exit(1)
 
     if args.threads <= 0:
         args.threads = 1
 
     elif args.threads > 15:
         logger.critical('Maximum number of used threads is 15')
-        exit(1)
+        sys.exit(1)
-
-    if args.dryrun and (args.is_cbz or args.is_pdf):
-        logger.critical('Cannot generate PDF or CBZ during dry-run')
-        exit(1)
 
     return args

nhentai/command.py

@@ -1,18 +1,20 @@
 # coding: utf-8
+import os
+import shutil
 import sys
 import signal
 import platform
 import urllib3.exceptions
 
 from nhentai import constant
-from nhentai.cmdline import cmd_parser, banner
+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.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
+from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata, \
-    paging, check_cookie, signal_handler, DB
+    paging, check_cookie, signal_handler, DB, move_to_folder
 
 
 def main():
@@ -20,14 +22,19 @@ def main():
 
     if sys.version_info < (3, 0, 0):
         logger.error('nhentai now only support Python 3.x')
-        exit(1)
+        sys.exit(1)
 
     options = cmd_parser()
     logger.info(f'Using mirror: {BASE_URL}')
 
     # CONFIG['proxy'] will be changed after cmd_parser()
-    if constant.CONFIG['proxy']['http']:
+    if constant.CONFIG['proxy']:
-        logger.info(f'Using proxy: {constant.CONFIG["proxy"]["http"]}')
+        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'
@@ -39,15 +46,17 @@ def main():
 
     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']:
@@ -58,6 +67,10 @@ def main():
         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
 
@@ -72,8 +85,10 @@ def main():
         doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
 
     if not options.is_show:
-        downloader = Downloader(path=options.output_dir, size=options.threads,
+        downloader = Downloader(path=options.output_dir, threads=options.threads,
-                                timeout=options.timeout, delay=options.delay)
+                                timeout=options.timeout, delay=options.delay,
+                                exit_on_fail=options.exit_on_fail,
+                                no_filename_padding=options.no_filename_padding)
 
         for doujinshi_id in doujinshi_ids:
             doujinshi_info = doujinshi_parser(doujinshi_id)
@@ -82,24 +97,40 @@ def main():
             else:
                 continue
 
-            if not options.dryrun:
             doujinshi.downloader = downloader
-                doujinshi.download(regenerate_cbz=options.regenerate_cbz)
+
+            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:
-                table = doujinshi.table
+                generate_metadata(options.output_dir, doujinshi)
-                generate_metadata_file(options.output_dir, table, doujinshi)
 
             if options.is_save_download_history:
                 with DB() as db:
                     db.add_one(doujinshi.id)
 
-            if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
+            if not options.is_nohtml:
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
-            elif options.is_cbz:
+
-                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+            if options.is_cbz:
-            elif options.is_pdf:
+                generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
-                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
+
+            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)

nhentai/constant.py

@@ -3,33 +3,66 @@ import os
 import tempfile
 
 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')
 
 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/'
 
 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/'
 
-IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
+PATH_SEPARATOR = os.path.sep
 
-NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
+RETRY_TIMES = 3
+
+
+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}',
+]
+
+NHENTAI_HOME = get_nhentai_home()
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
 NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
 __api_suspended_DETAIL_URL = f'{BASE_URL}/api/gallery'
 
 CONFIG = {
-    'proxy': {'http': '', 'https': ''},
+    'proxy': '',
     'cookie': '',
     'language': '',
     'template': '',
-    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+    'max_filename': 85
 }
 
 LANGUAGE_ISO = {

nhentai/doujinshi.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+import os
 
 from tabulate import tabulate
 
@@ -11,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -20,17 +22,19 @@ 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, pretty_name=None, id=None, img_id=None,
+    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
@@ -38,8 +42,13 @@ class Doujinshi(object):
         self.url = f'{DETAIL_URL}/{self.id}'
         self.info = DoujinshiInfo(**kwargs)
 
+        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))
@@ -47,15 +56,18 @@ class Doujinshi(object):
         self.filename = format_filename(name_format, 255, True)
 
         self.table = [
-            ["Parodies", self.info.parodies],
+            ['Parodies', self.info.parodies],
-            ["Doujinshi", self.name],
+            ['Title', self.name],
-            ["Subtitle", self.info.subtitle],
+            ['Subtitle', self.info.subtitle],
-            ["Characters", self.info.characters],
+            ['Date', self.info.date],
-            ["Authors", self.info.artists],
+            ['Characters', self.info.characters],
-            ["Languages", self.info.languages],
+            ['Authors', self.info.artists],
-            ["Tags", self.info.tags],
+            ['Groups', self.info.groups],
-            ["URL", self.url],
+            ['Languages', self.info.languages],
-            ["Pages", self.pages],
+            ['Tags', self.info.tags],
+            ['Favorite Counts', self.favorite_counts],
+            ['URL', self.url],
+            ['Pages', self.pages],
         ]
 
     def __repr__(self):
@@ -64,7 +76,38 @@ class Doujinshi(object):
     def show(self):
         logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
 
-    def download(self, regenerate_cbz=False):
+    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(f'Starting to download doujinshi: {self.name}')
         if self.downloader:
             download_queue = []
@@ -74,9 +117,10 @@ class Doujinshi(object):
             for i in range(1, min(self.pages, len(self.ext)) + 1):
                 download_queue.append(f'{IMAGE_URL}/{self.img_id}/{i}.{self.ext[i-1]}')
 
-            self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
+            return self.downloader.start_download(download_queue, self.filename)
         else:
             logger.critical('Downloader has not been loaded')
+            return False
 
 
 if __name__ == '__main__':

nhentai/downloader.py

@@ -1,23 +1,17 @@
 # coding: utf-
 
-import multiprocessing
-import signal
-
-import sys
 import os
-import requests
+import asyncio
-import time
+import httpx
 import urllib3.exceptions
 
 from urllib.parse import urlparse
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.parser import request
+from nhentai.utils import Singleton, async_request
-from nhentai.utils import Singleton
 
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-semaphore = multiprocessing.Semaphore(1)
 
 
 class NHentaiImageNotExistException(Exception):
@@ -40,120 +34,144 @@ def download_callback(result):
 
 
 class Downloader(Singleton):
-
+    def __init__(self, path='', threads=5, timeout=30, delay=0, exit_on_fail=False,
-    def __init__(self, path='', size=5, timeout=30, delay=0):
+                 no_filename_padding=False):
-        self.size = size
+        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
 
-    def download(self, url, folder='', filename='', retried=0, proxy=None):
+    async def fiber(self, tasks):
-        if self.delay:
+        self.semaphore = asyncio.Semaphore(self.threads)
-            time.sleep(self.delay)
+        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} ...')
+
+        if self.delay:
+            await asyncio.sleep(self.delay)
+
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
 
-        save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
+        if not self.no_filename_padding:
+            filename = base_filename.zfill(length) + extension
+        else:
+            filename = base_filename + extension
+
+        save_file_path = os.path.join(self.folder, filename)
+
         try:
             if os.path.exists(save_file_path):
-                logger.warning(f'Ignored exists file: {save_file_path}')
+                logger.warning(f'Skipped download: {save_file_path} already exists')
                 return 1, url
 
-            response = None
+            response = await async_request('GET', url, timeout=self.timeout, proxy=proxy)
-            with open(save_file_path, "wb") as f:
+
-                i = 0
-                while i < 10:
-                    try:
-                        response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
             if response.status_code != 200:
-                            raise NHentaiImageNotExistException
+                path = urlparse(url).path
-
+                for mirror in constant.IMAGE_URL_MIRRORS:
-                    except NHentaiImageNotExistException as e:
+                    logger.info(f"Try mirror: {mirror}{path}")
-                        raise e
+                    mirror_url = f'{mirror}{path}'
-
+                    response = await async_request('GET', mirror_url, timeout=self.timeout, proxies=proxy)
-                    except Exception as e:
+                    if response.status_code == 200:
-                        i += 1
-                        if not i < 10:
-                            logger.critical(str(e))
-                            return 0, None
-                        continue
-
                         break
 
+            if not await self.save(filename, response):
+                logger.error(f'Can not download image {url}')
+                return -1, url
+
+        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
+
+        except NHentaiImageNotExistException as e:
+            os.remove(save_file_path)
+            return -3, url
+
+        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, save_file_path, response) -> bool:
+        if response is None:
+            logger.error('Error: Response is None')
+            return False
+        save_file_path = os.path.join(self.folder, save_file_path)
+        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:
+    def start_download(self, queue, folder='') -> bool:
-            if retried < 3:
-                logger.warning(f'Warning: {e}, retrying({retried}) ...')
-                return 0, self.download(url=url, folder=folder, filename=filename,
-                                        retried=retried+1, proxy=proxy)
-            else:
-                return 0, None
-
-        except NHentaiImageNotExistException as e:
-            os.remove(save_file_path)
-            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 start_download(self, queue, folder='', regenerate_cbz=False):
         if not isinstance(folder, (str,)):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
-        if os.path.exists(folder + '.cbz'):
+        logger.info(f'Doujinshi will be saved at "{folder}"')
-            if not regenerate_cbz:
-                logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
-                return
-
         if not os.path.exists(folder):
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
                 logger.critical(str(e))
+        self.folder = folder
 
-        else:
+        if os.getenv('DEBUG', None) == 'NODOWNLOAD':
-            logger.warning(f'Path "{folder}" already exist.')
+            # Assuming we want to continue with rest of process.
+            return True
 
-        queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
+        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
+        ]
 
-        pool = multiprocessing.Pool(self.size, init_worker)
+        # Prevent coroutines infection
-        [pool.apply_async(download_wrapper, args=item) for item in queue]
+        asyncio.run(self.fiber(coroutines))
 
-        pool.close()
+        return True
-        pool.join()
-
-
-def download_wrapper(obj, url, folder='', proxy=None):
-    if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download(obj, url=url, folder=folder, proxy=proxy)
-    else:
-        return -3, None
-
-
-def init_worker():
-    signal.signal(signal.SIGINT, subprocess_signal)
-
-
-def subprocess_signal(sig, frame):
-    if semaphore.acquire(timeout=1):
-        logger.warning('Ctrl-C pressed, exiting sub processes ...')
-
-    raise KeyboardInterrupt

nhentai/parser.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-
+import sys
 import os
 import re
 import time
@@ -41,11 +41,11 @@ def login(username, password):
 
     if 'Invalid username/email or password' in resp.text:
         logger.error('Login failed, please check your username and password')
-        exit(1)
+        sys.exit(1)
 
     if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
         logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
-        exit(2)
+        sys.exit(2)
 
 
 def _get_title_and_id(response):
@@ -92,18 +92,32 @@ def favorites_parser(page=None):
         page_range_list = range(1, pages + 1)
 
     for page in page_range_list:
-        try:
         logger.info(f'Getting doujinshi ids of page {page}')
-            resp = request('get', f'{constant.FAV_URL}?page={page}').content
 
-            result.extend(_get_title_and_id(resp))
+        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.error(f'Error: {e}, continue')
+                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(f'Doujinshi id({id_}) is not valid')
 
@@ -121,9 +135,15 @@ def doujinshi_parser(id_):
             logger.error(f'Doujinshi with id {id_} cannot be found')
             return []
         else:
+            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.warning(f'Error: {e}, ignored')
@@ -135,23 +155,32 @@ def doujinshi_parser(id_):
     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/([0-9]+)/cover.(jpg|png|gif)$',
+    # img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
-                       doujinshi_cover.a.img.attrs['data-src'])
+    #                   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)
+        base_name = os.path.basename(i.img.attrs['data-src'])
-        ext.append(ext_name)
+        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')
+        logger.critical(f'Tried yo get image id failed of id: {id_}')
-        exit(1)
+        return None
 
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
@@ -178,42 +207,6 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def legacy_search_parser(keyword, sorting, page, is_page_all=False):
-    logger.debug(f'Searching doujinshis of keyword {keyword}')
-
-    response = None
-    result = []
-
-    if is_page_all and len(page) != 1:
-        # `--page-all` option will override the `--page` option
-        page = [1]
-
-    for p in page:
-        logger.debug(f'Fetching page {p} ...')
-        response = request('get', url=constant.LEGACY_SEARCH_URL,
-                           params={'q': keyword, 'page': p, 'sort': sorting}).content
-        result.extend(_get_title_and_id(response))
-
-    if not result:
-        logger.warning(f'Not found anything of keyword {keyword} on page {page[0]}')
-        return result
-
-    if is_page_all:
-        html = BeautifulSoup(response, 'lxml')
-        pagination = html.find(attrs={'class': 'pagination'})
-        next_page = pagination.find(attrs={'class': 'next'})
-
-        if next_page is None:
-            logger.warning('Reached the last page')
-            return result
-        else:
-            next_page = re.findall('page=([0-9]+)', next_page.attrs['href'])[0]
-            result.extend(legacy_search_parser(keyword, sorting, [next_page], is_page_all))
-            return result
-
-    return result
-
-
 def print_doujinshi(doujinshi_list):
     if not doujinshi_list:
         return
@@ -223,6 +216,50 @@ def print_doujinshi(doujinshi_list):
     print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
+def legacy_search_parser(keyword, sorting, page, is_page_all=False, type_='SEARCH'):
+    logger.info(f'Searching doujinshis of keyword {keyword}')
+    result = []
+
+    if type_ not in ('SEARCH', 'ARTIST', ):
+        raise ValueError('Invalid type')
+
+    if is_page_all:
+        if type_ == 'SEARCH':
+            response = request('get', url=constant.LEGACY_SEARCH_URL,
+                               params={'q': keyword, 'page': 1, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': 1}).content
+
+        html = BeautifulSoup(response, 'lxml')
+        pagination = html.find(attrs={'class': 'pagination'})
+        last_page = pagination.find(attrs={'class': 'last'})
+        last_page = re.findall('page=([0-9]+)', last_page.attrs['href'])[0]
+        logger.info(f'Getting doujinshi ids of {last_page} pages')
+        pages = range(1, int(last_page))
+    else:
+        pages = page
+
+    for p in pages:
+        logger.info(f'Fetching page {p} ...')
+        if type_ == 'SEARCH':
+            response = request('get', url=constant.LEGACY_SEARCH_URL,
+                               params={'q': keyword, 'page': p, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': p}).content
+
+        if response is None:
+            logger.warning(f'No result in response in page {p}')
+            continue
+        result.extend(_get_title_and_id(response))
+
+    if not result:
+        logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
 def search_parser(keyword, sorting, page, is_page_all=False):
     result = []
     response = None
@@ -240,16 +277,23 @@ def search_parser(keyword, sorting, page, is_page_all=False):
         i = 0
 
         logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
-        while i < 3:
+        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 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:
@@ -258,7 +302,9 @@ def search_parser(keyword, sorting, page, is_page_all=False):
 
         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
@@ -268,52 +314,5 @@ def search_parser(keyword, sorting, page, is_page_all=False):
     return result
 
 
-def __api_suspended_doujinshi_parser(id_):
-    if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception(f'Doujinshi id({id_}) is not valid')
-
-    id_ = int(id_)
-    logger.info(f'Fetching information of doujinshi id {id_}')
-    doujinshi = dict()
-    doujinshi['id'] = id_
-    url = f'{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

@@ -1,13 +1,17 @@
 # coding: utf-8
 import json
 import os
+
+from nhentai.constant import PATH_SEPARATOR, LANGUAGE_ISO
 from xml.sax.saxutils import escape
-from nhentai.constant import LANGUAGE_ISO
+from requests.structures import CaseInsensitiveDict
 
 
-def serialize_json(doujinshi, output_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:
@@ -22,7 +26,7 @@ def serialize_json(doujinshi, output_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
 
@@ -44,6 +48,7 @@ def serialize_comic_xml(doujinshi, output_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
@@ -73,13 +78,33 @@ def serialize_comic_xml(doujinshi, output_dir):
         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(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:
@@ -127,3 +152,4 @@ def set_js_database():
         indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)
+

nhentai/utils.py

@@ -5,15 +5,20 @@ import re
 import os
 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_comic_xml, 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 request(method, url, **kwargs):
@@ -25,20 +30,44 @@ def request(method, url, **kwargs):
     })
 
     if not kwargs.get('proxies', None):
-        kwargs['proxies'] = constant.CONFIG['proxy']
+        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 = {
+        'Referer': constant.LOGIN_URL,
+        'User-Agent': constant.CONFIG['useragent'],
+        'Cookie': constant.CONFIG['cookie'],
+    }
+
+    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)
-    if response.status_code == 503 and 'cf-browser-verification' in response.text:
+
+    if response.status_code == 403 and 'Just a moment...' in response.text:
         logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
-        exit(-1)
+        sys.exit(1)
 
     username = re.findall('"/users/[0-9]+/(.*?)"', response.text)
     if not username:
-        logger.warning('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.log(16, f'Login successfully! Your username: {username[0]}')
 
@@ -57,15 +86,6 @@ 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__)
 
@@ -73,13 +93,33 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
+def parse_doujinshi_obj(
-    image_html = ''
+        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 = '.'
+        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.')
@@ -92,7 +132,7 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     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'
 
@@ -101,17 +141,13 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     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
     else:
         name = {'title': 'nHentai HTML Viewer'}
 
     data = html.format(TITLE=name, IMAGES=image_html, SCRIPTS=js, STYLES=css)
     try:
-        if sys.version_info < (3, 0):
-            with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
-                f.write(data)
-        else:
         with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
             f.write(data.encode('utf-8'))
 
@@ -120,7 +156,28 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
         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 contains doujinshi.
     With a link to their `index.html`.
@@ -161,82 +218,75 @@ 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', './')
         set_js_database()
-        logger.log(16, f'Main Viewer has been written to "{output_dir}main.html"')
+        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(f'Writing Main Viewer failed ({e})')
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True):
+def generate_cbz(doujinshi_dir, filename):
-    if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-        if write_comic_info:
-            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), f'{doujinshi_obj.filename}.cbz')
-    else:
-        cbz_filename = './doujinshi.cbz'
-        doujinshi_dir = '.'
-
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
-    logger.info(f'Writing CBZ file to path: {cbz_filename}')
+    logger.info(f'Writing CBZ file to path: {filename}')
-    with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
+    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:
+    logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
-        shutil.rmtree(doujinshi_dir, ignore_errors=True)
-
-    logger.log(16, f'Comic Book CBZ file has been written to "{doujinshi_dir}"')
 
 
-def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
+
+    if os.path.exists(f'{doujinshi_dir}.{file_type}') and not regenerate:
+        logger.info(f'Skipped {file_type} file generation: {doujinshi_dir}.{file_type} already exists')
+        return
+
+    if file_type == 'cbz':
+        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."""
-        if doujinshi_obj is not None:
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(EXTENSIONS)]
-            doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-            pdf_filename = os.path.join(
-                os.path.join(doujinshi_dir, '..'),
-                f'{doujinshi_obj.filename}.pdf'
-            )
-        else:
-            pdf_filename = './doujinshi.pdf'
-            doujinshi_dir = '.'
-
-        file_list = os.listdir(doujinshi_dir)
             file_list.sort()
 
-        logger.info(f'Writing PDF file to path: {pdf_filename}')
+            logger.info(f'Writing PDF file to path: {filename}')
-        with open(pdf_filename, 'wb') as pdf_f:
+            with open(filename, 'wb') as pdf_f:
                 full_path_list = (
                     [os.path.join(doujinshi_dir, image) for image in file_list]
                 )
-            pdf_f.write(img2pdf.convert(full_path_list))
+                pdf_f.write(img2pdf.convert(full_path_list, rotation=img2pdf.Rotation.ifvalid))
 
-        if rm_origin_dir:
+            logger.log(16, f'PDF file has been written to "{filename}"')
-            shutil.rmtree(doujinshi_dir, ignore_errors=True)
-
-        logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
 
         except ImportError:
             logger.error("Please install img2pdf package by using pip.")
+    else:
+        raise ValueError('invalid file type')
+
+
+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}"')
 
 
 def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
@@ -244,12 +294,12 @@ 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 replace space character(' '). 
+    if filename include forbidden characters (\'/:,;*?"<>|) ,it replaces space character(" ").
     """
     # maybe you can use `--format` to select a suitable filename
 
     if not _truncate_only:
-        ban_chars = '\\\'/:,;*?"<>|\t'
+        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())
 
@@ -267,15 +317,16 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
     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(','):
@@ -292,34 +343,6 @@ def paging(page_string):
     return page_list
 
 
-def generate_metadata_file(output_dir, table, doujinshi_obj=None):
-    logger.info('Writing Metadata Info')
-
-    if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    else:
-        doujinshi_dir = '.'
-
-    logger.info(doujinshi_dir)
-
-    f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
-
-    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'CIRCLE', 'SCANLATOR',
-              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
-              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
-              'SERIES', 'PARODY', 'URL']
-    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR',
-                      'LANGUAGE', 'TAGS', 'URL', 'PAGES']
-
-    for i in range(len(fields)):
-        f.write(f'{fields[i]}: ')
-        if fields[i] in special_fields:
-            f.write(str(table[special_fields.index(fields[i])][1]))
-        f.write('\n')
-
-    f.close()
-
-
 class DB(object):
     conn = None
     cur = None

nhentai/viewer/default/scripts.js

@@ -75,11 +75,13 @@ document.onkeydown = event =>{
             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++){

poetry.lock

@@ -0,0 +1,351 @@
+# This file is automatically @generated by Poetry 1.8.3 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"
+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)", "uvloop (>=0.21.0b1)"]
+trio = ["trio (>=0.26.1)"]
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.12.3"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.6.0"
+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"
+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"
+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"
+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"
+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"
+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"
+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"
+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", "brotlicffi"]
+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"
+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"
+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 = "2.32.3"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"},
+    {file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"},
+]
+
+[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"
+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"
+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"
+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"
+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"
+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)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.8"
+content-hash = "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

@@ -1,6 +0,0 @@
-requests>=2.5.0
-soupsieve
-BeautifulSoup4>=4.0.0
-tabulate>=0.7.5
-iso8601 >= 0.1
-urllib3

setup.cfg

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

setup.py

@@ -1,38 +0,0 @@
-# coding: utf-8
-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:
-        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 +1,33 @@
+import unittest
+import os
+import urllib3.exceptions
+
+from nhentai import constant
+from nhentai.cmdline import load_config
+from nhentai.downloader import Downloader
+from nhentai.parser import doujinshi_parser
+from nhentai.doujinshi import Doujinshi
+from nhentai.utils import generate_html
+
+
+class TestDownload(unittest.TestCase):
+    def setUp(self) -> None:
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        load_config()
+        constant.CONFIG['cookie'] = os.getenv('NHENTAI_COOKIE')
+        constant.CONFIG['useragent'] = os.getenv('NHENTAI_UA')
+
+    def test_download(self):
+        did = 440546
+        info = Doujinshi(**doujinshi_parser(did), name_format='%i')
+        info.downloader = Downloader(path='/tmp', threads=5)
+        info.download()
+
+        self.assertTrue(os.path.exists(f'/tmp/{did}/001.jpg'))
+
+        generate_html('/tmp', info)
+        self.assertTrue(os.path.exists(f'/tmp/{did}/index.html'))
+
+
+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)