0.5.4

Bump urllib3 from 1.26.14 to 1.26.18

.dockerignore

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

.github/workflows/docker-image.yml

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

.travis.yml

@@ -1,19 +0,0 @@
-os:
-    - linux
-
-language: python
-python:
-    - 3.7
-    - 3.8
-
-install:
-    - python setup.py install
-
-script:
-    - echo 268642 > /tmp/test.txt
-    - nhentai --cookie "_ga=GA1.2.1651446371.1545407218; __cfduid=d0ed34dfb81167d2a51a1d6392c1768a81601380350; csrftoken=KRN0GR1ft86m3HTefpQA99pp6R1Bo7hUs5QxNGOAIuwB5g4EcJj04fwMB8QKgLaB; sessionid=7hzoowox78c90wi5ud5ibphm4axcck7c"
-    - nhentai --search umaru
-    - nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - nhentai -F
-    - nhentai --file /tmp/test.txt
-    - nhentai --id=152503,146134 --gen-main --output=/tmp/

Dockerfile

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

MANIFEST.in

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

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
 
-==================
+Build Docker container:
-Installation (pip)
-==================
-Alternatively, install from PyPI with pip:
 
 .. code-block::
 
-           pip install nhentai
+    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
 
-For a self-contained installation, use `Pipx <https://github.com/pipxproject/pipx/>`_:
+==================
+Installation
+==================
+From PyPI with pip:
 
 .. code-block::
 
-           pipx install nhentai
+   pip install nhentai
+
+For a self-contained installation, use `pipx <https://github.com/pipxproject/pipx/>`_:
+
+.. code-block::
+
+   pipx install nhentai
+
+Pull from Dockerhub:
+
+.. code-block::
+
+    docker pull ricterz/nhentai
+    docker run --rm -it -v ~/Downloads/doujinshi:/output -v ~/.nhentai/:/root/.nhentai ricterz/nhentai --id 123855
+
+On Gentoo Linux:
 
-=====================
-Installation (Gentoo)
-=====================
 .. code-block::
 
     layman -fa glicOne
     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
@@ -128,7 +143,9 @@ Supported doujinshi folder formatter:
 - %t: Doujinshi name
 - %s: Doujinshi subtitle (translated name)
 - %a: Doujinshi authors' name
+- %g: Doujinshi groups name
 - %p: Doujinshi pretty name
+- %ag: Doujinshi authors name or groups name
 
 
 Other options:
@@ -185,6 +202,8 @@ 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
 
@@ -221,13 +240,13 @@ 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__ = '0.5.4'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -3,16 +3,13 @@
 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
 
 
@@ -80,9 +77,9 @@ def cmd_parser():
     # page options
     parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
                       help='all search results')
-    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='',
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='1',
                       help='page number of search results. e.g. 1,2-5,14')
-    parser.add_option('--sorting', dest='sorting', action='store', default='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'])
 
@@ -115,6 +112,8 @@ def cmd_parser():
                       help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
                       help='remove downloaded doujinshi dir when generated CBZ or PDF file')
+    parser.add_option('--move-to-folder', dest='move_to_folder', action='store_true', default=False,
+                      help='remove files in doujinshi dir then move new file to folder when generated CBZ or PDF file')
     parser.add_option('--meta', dest='generate_metadata', action='store_true',
                       help='generate a metadata file in doujinshi format')
     parser.add_option('--regenerate-cbz', dest='regenerate_cbz', action='store_true', default=False,
@@ -142,35 +141,35 @@ 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
         write_config()
         logger.info('Cookie saved.')
-        exit(0)
+        sys.exit(0)
     elif args.useragent is not None:
         constant.CONFIG['useragent'] = args.useragent
         write_config()
         logger.info('User-Agent saved.')
-        exit(0)
+        sys.exit(0)
     elif args.language is not None:
         constant.CONFIG['language'] = args.language
         write_config()
         logger.info(f'Default language now set to "{args.language}"')
-        exit(0)
+        sys.exit(0)
         # TODO: search without language
 
     if args.proxy is not None:
@@ -178,7 +177,7 @@ def cmd_parser():
         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'] = {
                 'http': args.proxy,
@@ -186,7 +185,7 @@ def cmd_parser():
             }
             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 +194,7 @@ 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()
@@ -205,7 +204,7 @@ 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:
@@ -215,21 +214,21 @@ def cmd_parser():
     if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
-        exit(1)
+        sys.exit(1)
 
     if not args.keyword and not args.id and not args.favorites:
         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)
+        sys.exit(1)
 
     return args

nhentai/command.py

@@ -20,7 +20,7 @@ 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}')
@@ -39,7 +39,6 @@ def main():
 
     doujinshis = []
     doujinshi_ids = []
-    doujinshi_list = []
 
     page_list = paging(options.page)
 
@@ -47,7 +46,7 @@ def main():
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshis = favorites_parser(page=page_list)
+        doujinshis = favorites_parser() if options.page_all else favorites_parser(page=page_list)
 
     elif options.keyword:
         if constant.CONFIG['language']:
@@ -97,9 +96,9 @@ def main():
             if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
             elif options.is_cbz:
-                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir, True, options.move_to_folder)
             elif options.is_pdf:
-                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)

nhentai/constant.py

@@ -5,6 +5,7 @@ import tempfile
 from urllib.parse import urlparse
 
 
+DEBUG = os.getenv('DEBUG', False)
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
 DETAIL_URL = f'{BASE_URL}/g'

nhentai/doujinshi.py

@@ -20,9 +20,10 @@ 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):
@@ -38,8 +39,12 @@ 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('%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 +52,16 @@ class Doujinshi(object):
         self.filename = format_filename(name_format, 255, True)
 
         self.table = [
-            ["Parodies", self.info.parodies],
+            ['Parodies', self.info.parodies],
-            ["Doujinshi", self.name],
+            ['Doujinshi', self.name],
-            ["Subtitle", self.info.subtitle],
+            ['Subtitle', self.info.subtitle],
-            ["Characters", self.info.characters],
+            ['Characters', self.info.characters],
-            ["Authors", self.info.artists],
+            ['Authors', self.info.artists],
-            ["Languages", self.info.languages],
+            ['Groups', self.info.groups],
-            ["Tags", self.info.tags],
+            ['Languages', self.info.languages],
-            ["URL", self.url],
+            ['Tags', self.info.tags],
-            ["Pages", self.pages],
+            ['URL', self.url],
+            ['Pages', self.pages],
         ]
 
     def __repr__(self):

nhentai/downloader.py

@@ -123,6 +123,7 @@ class Downloader(Singleton):
                 logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
                 return
 
+        logger.info(f'Doujinshi will be saved at "{folder}"')
         if not os.path.exists(folder):
             try:
                 os.makedirs(folder)

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):
@@ -103,7 +103,7 @@ def favorites_parser(page=None):
     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 +121,15 @@ 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')
@@ -151,7 +157,7 @@ def doujinshi_parser(id_):
 
     if not img_id:
         logger.critical('Tried yo get image id failed')
-        exit(1)
+        sys.exit(1)
 
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
@@ -178,97 +184,7 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def legacy_search_parser(keyword, sorting, page, is_page_all=False):
+def legacy_doujinshi_parser(id_):
-    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
-    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
-    headers = ['id', 'doujinshi']
-    logger.info(f'Search Result || Found {doujinshi_list.__len__()} doujinshis')
-    print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
-
-
-def search_parser(keyword, sorting, page, is_page_all=False):
-    result = []
-    response = None
-    if not page:
-        page = [1]
-
-    if is_page_all:
-        url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
-        init_response = request('get', url.replace('%2B', '+')).json()
-        page = range(1, init_response['num_pages']+1)
-
-    total = f'/{page[-1]}' if is_page_all else ''
-    not_exists_persist = False
-    for p in page:
-        i = 0
-
-        logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
-        while i < 3:
-            try:
-                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
-                                                                      'page': p, 'sort': sorting}).url
-                response = request('get', url.replace('%2B', '+')).json()
-            except Exception as e:
-                logger.critical(str(e))
-                response = None
-            break
-
-        if response is None or 'result' not in response:
-            logger.warning(f'No result in response in page {p}')
-            if not_exists_persist is True:
-                break
-            continue
-
-        for row in response['result']:
-            title = row['title']['english']
-            title = title[:85] + '..' if len(title) > 85 else title
-            result.append({'id': row['id'], 'title': title})
-
-        not_exists_persist = False
-        if not result:
-            logger.warning(f'No results for keywords {keyword}')
-
-    return result
-
-
-def __api_suspended_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
         raise Exception(f'Doujinshi id({id_}) is not valid')
 
@@ -285,7 +201,7 @@ def __api_suspended_doujinshi_parser(id_):
             i += 1
             if not i < 5:
                 logger.critical(str(e))
-                exit(1)
+                sys.exit(1)
             continue
         break
 
@@ -315,5 +231,97 @@ def __api_suspended_doujinshi_parser(id_):
     return doujinshi
 
 
+def print_doujinshi(doujinshi_list):
+    if not doujinshi_list:
+        return
+    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
+    headers = ['id', 'doujinshi']
+    logger.info(f'Search Result || Found {doujinshi_list.__len__()} doujinshis')
+    print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+
+
+def legacy_search_parser(keyword, sorting, page, is_page_all=False):
+    logger.info(f'Searching doujinshis of keyword {keyword}')
+    result = []
+
+    if is_page_all:
+        response = request('get', url=constant.LEGACY_SEARCH_URL,
+                           params={'q': keyword, 'page': 1, 'sort': sorting}).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} ...')
+        response = request('get', url=constant.LEGACY_SEARCH_URL,
+                           params={'q': keyword, 'page': p, 'sort': sorting}).content
+        if response is None:
+            logger.warning(f'No result in response in page {p}')
+            continue
+        result.extend(_get_title_and_id(response))
+
+    if not result:
+        logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
+def search_parser(keyword, sorting, page, is_page_all=False):
+    result = []
+    response = None
+    if not page:
+        page = [1]
+
+    if is_page_all:
+        url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
+        init_response = request('get', url.replace('%2B', '+')).json()
+        page = range(1, init_response['num_pages']+1)
+
+    total = f'/{page[-1]}' if is_page_all else ''
+    not_exists_persist = False
+    for p in page:
+        i = 0
+
+        logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
+        while i < 3:
+            try:
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+                                                                      'page': p, 'sort': sorting}).url
+
+                if constant.DEBUG:
+                    logger.debug(f'Request URL: {url}')
+
+                response = request('get', url.replace('%2B', '+')).json()
+            except Exception as e:
+                logger.critical(str(e))
+                response = None
+            break
+
+        if constant.DEBUG:
+            logger.debug(f'Response: {response}')
+
+        if response is None or 'result' not in response:
+            logger.warning(f'No result in response in page {p}')
+            if not_exists_persist is True:
+                break
+            continue
+
+        for row in response['result']:
+            title = row['title']['english']
+            title = title[:85] + '..' if len(title) > 85 else title
+            result.append({'id': row['id'], 'title': title})
+
+        not_exists_persist = False
+        if not result:
+            logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/utils.py

@@ -32,9 +32,9 @@ def request(method, url, **kwargs):
 
 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:
@@ -57,15 +57,6 @@ 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__)
 
@@ -108,12 +99,8 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
 
     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'), 'wb') as f:
-            with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
+            f.write(data.encode('utf-8'))
-                f.write(data)
-        else:
-            with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
-                f.write(data.encode('utf-8'))
 
         logger.log(16, f'HTML Viewer has been written to "{os.path.join(doujinshi_dir, "index.html")}"')
     except Exception as e:
@@ -167,12 +154,8 @@ def generate_main_html(output_dir='./'):
         return
     try:
         data = main.format(STYLES=css, SCRIPTS=js, PICTURE=image_html)
-        if sys.version_info < (3, 0):
+        with open('./main.html', 'wb') as f:
-            with open('./main.html', 'w') as f:
+            f.write(data.encode('utf-8'))
-                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"')
@@ -180,7 +163,7 @@ def generate_main_html(output_dir='./'):
         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(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True, move_to_folder=False):
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
         if write_comic_info:
@@ -202,10 +185,21 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
+    if move_to_folder:
+            for filename in os.listdir(doujinshi_dir):
+                file_path = os.path.join(doujinshi_dir, filename)
+                if os.path.isfile(file_path):
+                    try:
+                        os.remove(file_path)
+                    except Exception as e:
+                        print(f"Error deleting file: {e}")
+
+            shutil.move(cbz_filename, doujinshi_dir)
+
     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_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, move_to_folder=False):
     try:
         import img2pdf
 
@@ -233,6 +227,17 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
         if rm_origin_dir:
             shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
+        if move_to_folder:
+            for filename in os.listdir(doujinshi_dir):
+                file_path = os.path.join(doujinshi_dir, filename)
+                if os.path.isfile(file_path):
+                    try:
+                        os.remove(file_path)
+                    except Exception as e:
+                        print(f"Error deleting file: {e}")
+
+            shutil.move(pdf_filename, doujinshi_dir)
+
         logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
 
     except ImportError:
@@ -249,7 +254,7 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
     # 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())
 
@@ -269,7 +274,7 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
 
 def signal_handler(signal, frame):
     logger.error('Ctrl-C signal received. Stopping...')
-    exit(1)
+    sys.exit(1)
 
 
 def paging(page_string):
@@ -304,11 +309,11 @@ def generate_metadata_file(output_dir, table, doujinshi_obj=None):
 
     f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
 
-    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'CIRCLE', 'SCANLATOR',
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
               'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
               'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
               'SERIES', 'PARODY', 'URL']
-    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR',
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
                       'LANGUAGE', 'TAGS', 'URL', 'PAGES']
 
     for i in range(len(fields)):

poetry.lock

@@ -0,0 +1,216 @@
+# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.11.2"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.6.0"
+files = [
+    {file = "beautifulsoup4-4.11.2-py3-none-any.whl", hash = "sha256:0e79446b10b3ecb499c1556f7e228a53e64a2bfcebd455f370d8927cb5b59e39"},
+    {file = "beautifulsoup4-4.11.2.tar.gz", hash = "sha256:bc4bdda6717de5a2987436fb8d72f45dc90dd856bdfd512a1314ce90349a0106"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "certifi"
+version = "2022.12.7"
+description = "Python package for providing Mozilla's CA Bundle."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"},
+    {file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.0.1"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+optional = false
+python-versions = "*"
+files = [
+    {file = "charset-normalizer-3.0.1.tar.gz", hash = "sha256:ebea339af930f8ca5d7a699b921106c6e29c617fe9606fa7baa043c1cdae326f"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:88600c72ef7587fe1708fd242b385b6ed4b8904976d5da0893e31df8b3480cb6"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c75ffc45f25324e68ab238cb4b5c0a38cd1c3d7f1fb1f72b5541de469e2247db"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db72b07027db150f468fbada4d85b3b2729a3db39178abf5c543b784c1254539"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62595ab75873d50d57323a91dd03e6966eb79c41fa834b7a1661ed043b2d404d"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ff6f3db31555657f3163b15a6b7c6938d08df7adbfc9dd13d9d19edad678f1e8"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:772b87914ff1152b92a197ef4ea40efe27a378606c39446ded52c8f80f79702e"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70990b9c51340e4044cfc394a81f614f3f90d41397104d226f21e66de668730d"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:292d5e8ba896bbfd6334b096e34bffb56161c81408d6d036a7dfa6929cff8783"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:2edb64ee7bf1ed524a1da60cdcd2e1f6e2b4f66ef7c077680739f1641f62f555"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:31a9ddf4718d10ae04d9b18801bd776693487cbb57d74cc3458a7673f6f34639"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:44ba614de5361b3e5278e1241fda3dc1838deed864b50a10d7ce92983797fa76"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:12db3b2c533c23ab812c2b25934f60383361f8a376ae272665f8e48b88e8e1c6"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c512accbd6ff0270939b9ac214b84fb5ada5f0409c44298361b2f5e13f9aed9e"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-win32.whl", hash = "sha256:502218f52498a36d6bf5ea77081844017bf7982cdbe521ad85e64cabee1b608b"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:601f36512f9e28f029d9481bdaf8e89e5148ac5d89cffd3b05cd533eeb423b59"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0298eafff88c99982a4cf66ba2efa1128e4ddaca0b05eec4c456bbc7db691d8d"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a8d0fc946c784ff7f7c3742310cc8a57c5c6dc31631269876a88b809dbeff3d3"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:87701167f2a5c930b403e9756fab1d31d4d4da52856143b609e30a1ce7160f3c"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14e76c0f23218b8f46c4d87018ca2e441535aed3632ca134b10239dfb6dadd6b"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c0a590235ccd933d9892c627dec5bc7511ce6ad6c1011fdf5b11363022746c1"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c7fe7afa480e3e82eed58e0ca89f751cd14d767638e2550c77a92a9e749c317"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79909e27e8e4fcc9db4addea88aa63f6423ebb171db091fb4373e3312cb6d603"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ac7b6a045b814cf0c47f3623d21ebd88b3e8cf216a14790b455ea7ff0135d18"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:72966d1b297c741541ca8cf1223ff262a6febe52481af742036a0b296e35fa5a"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f9d0c5c045a3ca9bedfc35dca8526798eb91a07aa7a2c0fee134c6c6f321cbd7"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:5995f0164fa7df59db4746112fec3f49c461dd6b31b841873443bdb077c13cfc"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4a8fcf28c05c1f6d7e177a9a46a1c52798bfe2ad80681d275b10dcf317deaf0b"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:761e8904c07ad053d285670f36dd94e1b6ab7f16ce62b9805c475b7aa1cffde6"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-win32.whl", hash = "sha256:71140351489970dfe5e60fc621ada3e0f41104a5eddaca47a7acb3c1b851d6d3"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:9ab77acb98eba3fd2a85cd160851816bfce6871d944d885febf012713f06659c"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:84c3990934bae40ea69a82034912ffe5a62c60bbf6ec5bc9691419641d7d5c9a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74292fc76c905c0ef095fe11e188a32ebd03bc38f3f3e9bcb85e4e6db177b7ea"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c95a03c79bbe30eec3ec2b7f076074f4281526724c8685a42872974ef4d36b72"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f4c39b0e3eac288fedc2b43055cfc2ca7a60362d0e5e87a637beac5d801ef478"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df2c707231459e8a4028eabcd3cfc827befd635b3ef72eada84ab13b52e1574d"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93ad6d87ac18e2a90b0fe89df7c65263b9a99a0eb98f0a3d2e079f12a0735837"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:59e5686dd847347e55dffcc191a96622f016bc0ad89105e24c14e0d6305acbc6"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:cd6056167405314a4dc3c173943f11249fa0f1b204f8b51ed4bde1a9cd1834dc"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:083c8d17153ecb403e5e1eb76a7ef4babfc2c48d58899c98fcaa04833e7a2f9a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:f5057856d21e7586765171eac8b9fc3f7d44ef39425f85dbcccb13b3ebea806c"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:7eb33a30d75562222b64f569c642ff3dc6689e09adda43a082208397f016c39a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-win32.whl", hash = "sha256:95dea361dd73757c6f1c0a1480ac499952c16ac83f7f5f4f84f0658a01b8ef41"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:eaa379fcd227ca235d04152ca6704c7cb55564116f8bc52545ff357628e10602"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3e45867f1f2ab0711d60c6c71746ac53537f1684baa699f4f668d4c6f6ce8e14"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cadaeaba78750d58d3cc6ac4d1fd867da6fc73c88156b7a3212a3cd4819d679d"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:911d8a40b2bef5b8bbae2e36a0b103f142ac53557ab421dc16ac4aafee6f53dc"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:503e65837c71b875ecdd733877d852adbc465bd82c768a067badd953bf1bc5a3"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a60332922359f920193b1d4826953c507a877b523b2395ad7bc716ddd386d866"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:16a8663d6e281208d78806dbe14ee9903715361cf81f6d4309944e4d1e59ac5b"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:a16418ecf1329f71df119e8a65f3aa68004a3f9383821edcb20f0702934d8087"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:9d9153257a3f70d5f69edf2325357251ed20f772b12e593f3b3377b5f78e7ef8"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:02a51034802cbf38db3f89c66fb5d2ec57e6fe7ef2f4a44d070a593c3688667b"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:2e396d70bc4ef5325b72b593a72c8979999aa52fb8bcf03f701c1b03e1166918"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:11b53acf2411c3b09e6af37e4b9005cba376c872503c8f28218c7243582df45d"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-win32.whl", hash = "sha256:0bf2dae5291758b6f84cf923bfaa285632816007db0330002fa1de38bfcb7154"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2c03cc56021a4bd59be889c2b9257dae13bf55041a3372d3295416f86b295fb5"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:024e606be3ed92216e2b6952ed859d86b4cfa52cd5bc5f050e7dc28f9b43ec42"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4b0d02d7102dd0f997580b51edc4cebcf2ab6397a7edf89f1c73b586c614272c"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:358a7c4cb8ba9b46c453b1dd8d9e431452d5249072e4f56cfda3149f6ab1405e"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81d6741ab457d14fdedc215516665050f3822d3e56508921cc7239f8c8e66a58"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8b8af03d2e37866d023ad0ddea594edefc31e827fee64f8de5611a1dbc373174"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9cf4e8ad252f7c38dd1f676b46514f92dc0ebeb0db5552f5f403509705e24753"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e696f0dd336161fca9adbb846875d40752e6eba585843c768935ba5c9960722b"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c22d3fe05ce11d3671297dc8973267daa0f938b93ec716e12e0f6dee81591dc1"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:109487860ef6a328f3eec66f2bf78b0b72400280d8f8ea05f69c51644ba6521a"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:37f8febc8ec50c14f3ec9637505f28e58d4f66752207ea177c1d67df25da5aed"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:f97e83fa6c25693c7a35de154681fcc257c1c41b38beb0304b9c4d2d9e164479"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a152f5f33d64a6be73f1d30c9cc82dfc73cec6477ec268e7c6e4c7d23c2d2291"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:39049da0ffb96c8cbb65cbf5c5f3ca3168990adf3551bd1dee10c48fce8ae820"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-win32.whl", hash = "sha256:4457ea6774b5611f4bed5eaa5df55f70abde42364d498c5134b7ef4c6958e20e"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:e62164b50f84e20601c1ff8eb55620d2ad25fb81b59e3cd776a1902527a788af"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8eade758719add78ec36dc13201483f8e9b5d940329285edcd5f70c0a9edbd7f"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8499ca8f4502af841f68135133d8258f7b32a53a1d594aa98cc52013fff55678"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3fc1c4a2ffd64890aebdb3f97e1278b0cc72579a08ca4de8cd2c04799a3a22be"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d3ffdaafe92a5dc603cb9bd5111aaa36dfa187c8285c543be562e61b755f6b"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c2ac1b08635a8cd4e0cbeaf6f5e922085908d48eb05d44c5ae9eabab148512ca"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6f45710b4459401609ebebdbcfb34515da4fc2aa886f95107f556ac69a9147e"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ae1de54a77dc0d6d5fcf623290af4266412a7c4be0b1ff7444394f03f5c54e3"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b590df687e3c5ee0deef9fc8c547d81986d9a1b56073d82de008744452d6541"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ab5de034a886f616a5668aa5d098af2b5385ed70142090e2a31bcbd0af0fdb3d"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9cb3032517f1627cc012dbc80a8ec976ae76d93ea2b5feaa9d2a5b8882597579"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:608862a7bf6957f2333fc54ab4399e405baad0163dc9f8d99cb236816db169d4"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0f438ae3532723fb6ead77e7c604be7c8374094ef4ee2c5e03a3a17f1fca256c"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:356541bf4381fa35856dafa6a965916e54bed415ad8a24ee6de6e37deccf2786"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-win32.whl", hash = "sha256:39cf9ed17fe3b1bc81f33c9ceb6ce67683ee7526e65fde1447c772afc54a1bb8"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:0a11e971ed097d24c534c037d298ad32c6ce81a45736d31e0ff0ad37ab437d59"},
+    {file = "charset_normalizer-3.0.1-py3-none-any.whl", hash = "sha256:7e189e2e1d3ed2f4aebabd2d5b0f931e883676e51c7624826e0a4e5fe8a0bf24"},
+]
+
+[[package]]
+name = "idna"
+version = "3.4"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
+    {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
+]
+
+[[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 = "2.31.0"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
+    {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
+]
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "soupsieve"
+version = "2.4"
+description = "A modern CSS selector implementation for Beautiful Soup."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "soupsieve-2.4-py3-none-any.whl", hash = "sha256:49e5368c2cda80ee7e84da9dbe3e110b70a4575f196efb74e51b94549d921955"},
+    {file = "soupsieve-2.4.tar.gz", hash = "sha256:e28dba9ca6c7c00173e34e4ba57448f0688bb681b7c5e8bf4971daafc093d69a"},
+]
+
+[[package]]
+name = "tabulate"
+version = "0.9.0"
+description = "Pretty-print tabular data"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"},
+    {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"},
+]
+
+[package.extras]
+widechars = ["wcwidth"]
+
+[[package]]
+name = "urllib3"
+version = "1.26.18"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+files = [
+    {file = "urllib3-1.26.18-py2.py3-none-any.whl", hash = "sha256:34b97092d7e0a3a8cf7cd10e386f401b3737364026c45e622aa02903dffe0f07"},
+    {file = "urllib3-1.26.18.tar.gz", hash = "sha256:f8ecc1bba5667413457c529ab955bf8c67b45db799d159066261719e328580a0"},
+]
+
+[package.extras]
+brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.8"
+content-hash = "0a1d5abd47a669c7a1f2dc7b43824a449e29ba94908a4338d2ea0f2dfb4f805e"

pyproject.toml

@@ -0,0 +1,21 @@
+[tool.poetry]
+name = "nhentai"
+version = "0.5.3"
+description = "nhentai doujinshi downloader"
+authors = ["Ricter Z <ricterzheng@gmail.com>"]
+license = "MIT"
+readme = "README.rst"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+requests = "^2.28.2"
+soupsieve = "^2.4"
+beautifulsoup4 = "^4.11.2"
+tabulate = "^0.9.0"
+iso8601 = "^1.1.0"
+urllib3 = "^1.26.14"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

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

setup.cfg

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

tests/test_download.py

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

tests/test_login.py

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

tests/test_parser.py

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