0.5.15 fix some bugs

add favorites count metadata

.dockerignore

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

.github/workflows/docker-image.yml

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

.gitignore

@@ -6,3 +6,6 @@ dist/
 .python-version
 .DS_Store
 output/
+venv/
+.vscode/
+test-output

.travis.yml

@@ -1,20 +0,0 @@
-os:
-    - linux
-
-language: python
-python:
-    - 2.7
-    - 3.7
-
-install:
-    - python setup.py install
-
-script:
-    - echo 268642 > /tmp/test.txt
-    - nhentai --cookie "csrftoken=xIh7s9d4NB8qSLN7eJZG9064zsV84aHEYFoAU49Ib9anqmoT0pZRw6TIdayLzQuT; sessionid=un101zfgpglsyffdnsm72le4euuisp7t"
-    - nhentai --search umaru
-    - nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - nhentai --tag lolicon --sorting popular
-    - 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

@@ -1,8 +1,5 @@
-include README.md
+include README.rst
 include requirements.txt
-include nhentai/viewer/index.html
+include nhentai/viewer/*
-include nhentai/viewer/styles.css
+include nhentai/viewer/default/*
-include nhentai/viewer/scripts.js
+include nhentai/viewer/minimal/*
-include nhentai/viewer/main.html
-include nhentai/viewer/main.css
-include nhentai/viewer/main.js

README.rst

@@ -1,60 +1,108 @@
 nhentai
 =======
 
-.. code-block::
-
-           _   _            _        _
-     _ __ | | | | ___ _ __ | |_ __ _(_)
-    | '_ \| |_| |/ _ \ '_ \| __/ _` | |
-    | | | |  _  |  __/ | | | || (_| | |
-    |_| |_|_| |_|\___|_| |_|\__\__,_|_|
-
-
 あなたも変態。 いいね?
 
 |travis|
 |pypi|
+|version|
 |license|
 
 
-nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
+nhentai is a CLI tool for downloading doujinshi from `nhentai.net <https://nhentai.net>`_
+
+GUI version: `https://github.com/edgar1016/nhentai-GUI <https://github.com/edgar1016/nhentai-GUI>`_
+
+===================
+Manual Installation
+===================
+From Github:
 
-============
-Installation
-============
 .. code-block::
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
     python setup.py install
-    
+
-=====================
+Build Docker container:
-Installation (Gentoo)
+
-=====================
+.. 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
+==================
+From PyPI with pip:
+
+.. code-block::
+
+   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:
+
 .. code-block::
 
     layman -fa glicOne
     sudo emerge net-misc/nhentai
 
+On NixOS:
+
+.. code-block::
+
+    nix-env -iA nixos.nhentai
+    
 =====
 Usage
 =====
-**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--cookie` option to store your cookie.
+**⚠️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:**
+
+- The format of the cookie is `"csrftoken=TOKEN; sessionid=ID; cf_clearance=CLOUDFLARE"`
+- `cf_clearance` cookie and useragent must be set if you encounter "blocked by cloudflare captcha" error. Make sure you use the same IP and useragent as when you got it
+
+| To get csrftoken and sessionid, first login to your nhentai account in web browser, then:
+| (Chrome) |ve| |ld| More tools    |ld| Developer tools     |ld| Application |ld| Storage |ld| Cookies |ld| https://nhentai.net
+| (Firefox) |hv| |ld| Web Developer |ld| Web Developer Tools                  |ld| Storage |ld| Cookies |ld| https://nhentai.net
+| 
+
+.. |hv| unicode:: U+2630 .. https://www.compart.com/en/unicode/U+2630
+.. |ve| unicode:: U+22EE .. https://www.compart.com/en/unicode/U+22EE
+.. |ld| unicode:: U+2014 .. https://www.compart.com/en/unicode/U+2014
+
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/usage.png
+    :alt: nhentai
+    :align: center
+
+*The default download folder will be the path where you run the command (%cd% or $PWD).*
+
 Download specified doujinshi:
 
 .. code-block:: bash
 
-    nhentai --id=123855,123866
+    nhentai --id 123855 123866 123877
 
 Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
@@ -62,53 +110,20 @@ Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
     nhentai --file=doujinshi.txt
 
+Set search default language
+
+.. code-block:: bash
+
+    nhentai --language=english
+
 Search a keyword and download the first page:
 
 .. code-block:: bash
 
     nhentai --search="tomori" --page=1 --download
-
+    # you also can download by tags and multiple keywords
-Download by tag name:
+    nhentai --search="tag:lolicon, artist:henreader, tag:full color"
-
+    nhentai --search="lolicon, henreader, full color"
-.. code-block:: bash
-
-    nhentai --tag lolicon --download --page=2
-
-Download by language:
-
-.. code-block:: bash
-
-    nhentai --language english --download --page=2
-
-Download by artist name:
-
-.. code-block:: bash
-
-    nhentai --artist henreader --download
-
-Download by character name:
-
-.. code-block:: bash
-
-    nhentai --character "kuro von einsbern" --download
-
-Download by parody name:
-
-.. code-block:: bash
-
-    nhentai --parody "the idolmaster" --download
-
-Download by group name:
-
-.. code-block:: bash
-
-    nhentai --group clesta --download
-
-Download using multiple tags (--tag, --character, --paordy and --group supported):
-
-.. code-block:: bash
-
-    nhentai --tag "lolicon, teasing" --artist "tamano kedama, atte nanakusa"
 
 Download your favorites with delay:
 
@@ -125,33 +140,43 @@ Format output doujinshi folder name:
 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
 
 
 Other options:
 
 .. code-block::
 
+    Usage:
+      nhentai --search [keyword] --download
+      NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]
+      nhentai --file [filename]
+
+    Environment Variable:
+      NHENTAI                 nhentai mirror url
+
     Options:
-      # Operation options
       -h, --help            show this help message and exit
       -D, --download        download doujinshi (for search results)
       -S, --show            just show the doujinshi information
-
+      --id                  doujinshi ids set, e.g. 167680 167681 167682
-      # Doujinshi options
-      --id=ID               doujinshi ids set, e.g. 1,2,3
       -s KEYWORD, --search=KEYWORD
                             search doujinshi by keyword
-      --tag=TAG             download doujinshi by tag
+      -F, --favorites       list or download your favorites
-      -F, --favorites       list or download your favorites.
+      -a ARTIST, --artist=ARTIST
-
+                            list doujinshi by artist name
-      # Multi-page options
+      --page-all            all search results
-      --page=PAGE           page number of search results
+      --page=PAGE, --page-range=PAGE
-      --max-page=MAX_PAGE   The max page when recursive download tagged doujinshi
+                            page number of search results. e.g. 1,2-5,14
-
+      --sorting=SORTING, --sort=SORTING
-      # Download options
+                            sorting of doujinshi (recent / popular /
+                            popular-[today|week])
       -o OUTPUT_DIR, --output=OUTPUT_DIR
                             output dir
       -t THREADS, --threads=THREADS
@@ -160,22 +185,35 @@ Other options:
                             timeout for downloading doujinshi
       -d DELAY, --delay=DELAY
                             slow down between downloading every doujinshi
-      -p PROXY, --proxy=PROXY
+      --proxy=PROXY         store a proxy, for example: -p "http://127.0.0.1:1080"
-                            uses a proxy, for example: http://127.0.0.1:1080
       -f FILE, --file=FILE  read gallery IDs from file.
       --format=NAME_FORMAT  format the saved folder name
-
+      --dry-run             Dry run, skip file download
-      # Generating options
       --html                generate a html viewer at current directory
       --no-html             don't generate HTML after downloading
-      --gen-main            generate a main viewer contain all the doujin in the folder
+      --gen-main            generate a main viewer contain all the doujin in the
+                            folder
       -C, --cbz             generate Comic Book CBZ File
-      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ
+      -P, --pdf             generate PDF file
-                            file.
+      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ or
-
+                            PDF file
-      # nHentai options
+      --move-to-folder      remove files in doujinshi dir then move new file to
-      --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
+                            folder when generated CBZ or PDF file
-
+      --meta                generate a metadata file in doujinshi format
+      --regenerate          regenerate the cbz or pdf file if exists
+      --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
+      --useragent=USERAGENT, --user-agent=USERAGENT
+                            set useragent to bypass Cloudflare captcha
+      --language=LANGUAGE   set default language to parse doujinshis
+      --clean-language      set DEFAULT as language to parse doujinshis
+      --save-download-history
+                            save downloaded doujinshis, whose will be skipped if
+                            you re-download them
+      --clean-download-history
+                            clean download history
+      --template=VIEWER_TEMPLATE
+                            set viewer template
+      --legacy              use legacy searching method
 
 ==============
 nHentai Mirror
@@ -183,36 +221,31 @@ nHentai Mirror
 If you want to use a mirror, you should set up a reverse proxy of `nhentai.net` and `i.nhentai.net`.
 For example:
 
-.. code-block:: 
+.. code-block::
 
     i.h.loli.club -> i.nhentai.net
+    i3.h.loli.club -> i3.nhentai.net
+    i5.h.loli.club -> i5.nhentai.net
+    i7.h.loli.club -> i7.nhentai.net
     h.loli.club -> nhentai.net
 
 Set `NHENTAI` env var to your nhentai mirror.
 
 .. code-block:: bash
 
-    NHENTAI=http://h.loli.club nhentai --id 123456
+    NHENTAI=https://h.loli.club nhentai --id 123456
 
 
-.. image:: ./images/search.png?raw=true
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/search.png
     :alt: nhentai
     :align: center
-.. image:: ./images/download.png?raw=true
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/download.png
     :alt: nhentai
     :align: center
-.. image:: ./images/viewer.png?raw=true
+.. image:: https://github.com/RicterZ/nhentai/raw/master/images/viewer.png
     :alt: nhentai
     :align: center
 
-============
-あなたも変態
-============
-.. image:: ./images/image.jpg?raw=true
-    :alt: nhentai
-    :align: center
-
-
 
 .. |travis| image:: https://travis-ci.org/RicterZ/nhentai.svg?branch=master
    :target: https://travis-ci.org/RicterZ/nhentai
@@ -220,5 +253,8 @@ Set `NHENTAI` env var to your nhentai mirror.
 .. |pypi| image:: https://img.shields.io/pypi/dm/nhentai.svg
    :target: https://pypi.org/project/nhentai/
 
+.. |version| image:: https://img.shields.io/pypi/v/nhentai
+   :target: https://pypi.org/project/nhentai/
+
 .. |license| image:: https://img.shields.io/github/license/ricterz/nhentai.svg
    :target: https://github.com/RicterZ/nhentai/blob/master/LICENSE

doujinshi.txt

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

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.3.8'
+__version__ = '0.5.15'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,44 +1,64 @@
 # coding: utf-8
-from __future__ import print_function
+
 import os
 import sys
-from optparse import OptionParser
+import json
-try:
-    from itertools import ifilter as filter
-except ImportError:
-    pass
-
 import nhentai.constant as constant
+
+from urllib.parse import urlparse
+from optparse import OptionParser
+
 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
 
-try:
-    if sys.version_info < (3, 0, 0):
-        import codecs
-        import locale
-        sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
-        sys.stderr = codecs.getwriter(locale.getpreferredencoding())(sys.stderr)
-
-except NameError:
-    # python3
-    pass
-
 
 def banner():
-    logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
+    logger.debug(f'nHentai ver {__version__}: あなたも変態。 いいね?')
-       _   _            _        _
+
- _ __ | | | | ___ _ __ | |_ __ _(_)
+
-| '_ \| |_| |/ _ \ '_ \| __/ _` | |
+def load_config():
-| | | |  _  |  __/ | | | || (_| | |
+    if not os.path.exists(constant.NHENTAI_CONFIG_FILE):
-|_| |_|_| |_|\___|_| |_|\__\__,_|_|
+        return
-''' % __version__)
+
+    try:
+        with open(constant.NHENTAI_CONFIG_FILE, 'r') as f:
+            constant.CONFIG.update(json.load(f))
+    except json.JSONDecodeError:
+        logger.error('Failed to load config file.')
+        write_config()
+
+
+def write_config():
+    if not os.path.exists(constant.NHENTAI_HOME):
+        os.mkdir(constant.NHENTAI_HOME)
+
+    with open(constant.NHENTAI_CONFIG_FILE, 'w') as f:
+        f.write(json.dumps(constant.CONFIG))
+
+
+def callback(option, opt_str, value, parser):
+    if option == '--id':
+        pass
+    value = []
+
+    for arg in parser.rargs:
+        if arg.isdigit():
+            value.append(int(arg))
+        elif arg.startswith('-'):
+            break
+        else:
+            logger.warning(f'Ignore invalid id {arg}')
+
+    setattr(parser.values, option.dest, value)
 
 
 def cmd_parser():
+    load_config()
+
     parser = OptionParser('\n  nhentai --search [keyword] --download'
-                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n  NHENTAI=https://nhentai-mirror-url/ nhentai --id [ID ...]'
-                          '\n  nhentai --file [filename]'    
+                          '\n  nhentai --file [filename]'
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
     # operation options
@@ -47,32 +67,26 @@ def cmd_parser():
     parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
 
     # doujinshi options
-    parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
+    parser.add_option('--id', dest='id', action='callback', callback=callback,
+                      help='doujinshi ids set, e.g. 167680 167681 167682')
     parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
                       help='search doujinshi by keyword')
-    parser.add_option('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
-    parser.add_option('--artist', type='string', dest='artist', action='store', help='download doujinshi by artist')
-    parser.add_option('--character', type='string', dest='character', action='store',
-                      help='download doujinshi by character')
-    parser.add_option('--parody', type='string', dest='parody', action='store', help='download doujinshi by parody')
-    parser.add_option('--group', type='string', dest='group', action='store', help='download doujinshi by group')
-    parser.add_option('--language', type='string', dest='language', action='store',
-                      help='download doujinshi by language')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
-                      help='list or download your favorites.')
+                      help='list or download your favorites')
+    parser.add_option('--artist', '-a', action='store', dest='artist',
+                      help='list doujinshi by artist name')
 
     # page options
-    parser.add_option('--page', type='int', dest='page', action='store', default=1,
+    parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
-                      help='page number of search results')
+                      help='all search results')
-    parser.add_option('--max-page', type='int', dest='max_page', action='store', default=1,
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='1',
-                      help='The max page when recursive download tagged doujinshi')
+                      help='page number of search results. e.g. 1,2-5,14')
-    parser.add_option('--page-range', type='string', dest='page_range', action='store',
+    parser.add_option('--sorting', '--sort', dest='sorting', action='store', default='popular',
-                      help='page range of favorites.  e.g. 1,2-5,14')
+                      help='sorting of doujinshi (recent / popular / popular-[today|week])',
-    parser.add_option('--sorting', dest='sorting', action='store', default='date',
+                      choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
-                      help='sorting of doujinshi (date / popular)', choices=['date', 'popular'])
 
     # 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='./',
                       help='output dir')
     parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
                       help='thread count for downloading doujinshi')
@@ -80,11 +94,12 @@ 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('--proxy', '-p', type='string', dest='proxy', action='store', default='',
+    parser.add_option('--proxy', type='string', dest='proxy', action='store',
-                      help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
+                      help='store a proxy, for example: -p "http://127.0.0.1:1080"')
-    parser.add_option('--file',  '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+    parser.add_option('--file', '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
                       help='format the saved folder name', default='[%i][%a][%t]')
+    parser.add_option('--dry-run', action='store_true', dest='dryrun', help='Dry run, skip file download')
 
     # generate options
     parser.add_option('--html', dest='html_viewer', action='store_true',
@@ -95,117 +110,127 @@ def cmd_parser():
                       help='generate a main viewer contain all the doujin in the folder')
     parser.add_option('--cbz', '-C', dest='is_cbz', action='store_true',
                       help='generate Comic Book CBZ File')
+    parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
+                      help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
-                      help='remove downloaded doujinshi dir when generated CBZ file.')
+                      help='remove downloaded doujinshi dir when generated CBZ or PDF file')
+    parser.add_option('--move-to-folder', dest='move_to_folder', action='store_true', default=False,
+                      help='remove files in doujinshi dir then move new file to folder when generated CBZ or PDF file')
+    parser.add_option('--meta', dest='generate_metadata', action='store_true',
+                      help='generate a metadata file in doujinshi format')
+    parser.add_option('--regenerate', dest='regenerate', action='store_true', default=False,
+                      help='regenerate the cbz or pdf file if exists')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
-                      help='set cookie of nhentai to bypass Google recaptcha')
+                      help='set cookie of nhentai to bypass Cloudflare captcha')
+    parser.add_option('--useragent', '--user-agent', type='str', dest='useragent', action='store',
+                      help='set useragent to bypass Cloudflare captcha')
+    parser.add_option('--language', type='str', dest='language', action='store',
+                      help='set default language to parse doujinshis')
+    parser.add_option('--clean-language', dest='clean_language', action='store_true', default=False,
+                      help='set DEFAULT as language to parse doujinshis')
     parser.add_option('--save-download-history', dest='is_save_download_history', action='store_true',
                       default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
     parser.add_option('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
                       help='clean download history')
-
+    parser.add_option('--template', dest='viewer_template', action='store',
-    try:
+                      help='set viewer template', default='')
-        sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
+    parser.add_option('--legacy', dest='legacy', action='store_true', default=False,
-        print()
+                      help='use legacy searching method')
-    except (NameError, TypeError):
-        pass
-    except UnicodeDecodeError:
-        exit(0)
 
     args, _ = parser.parse_args(sys.argv[1:])
 
     if args.html_viewer:
-        generate_html()
+        generate_html(template=constant.CONFIG['template'])
-        exit(0)
+        sys.exit(0)
 
-    if args.main_viewer and not args.id and not args.keyword and \
+    if args.main_viewer and not args.id and not args.keyword and not args.favorites:
-            not args.tag and not args.artist and not args.character and \
-            not args.parody and not args.group and not args.language 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)
-
-    if os.path.exists(constant.NHENTAI_COOKIE):
-        with open(constant.NHENTAI_COOKIE, 'r') as f:
-            constant.COOKIE = f.read()
-
-    if args.cookie:
-        try:
-            if not os.path.exists(constant.NHENTAI_HOME):
-                os.mkdir(constant.NHENTAI_HOME)
-
-            with open(constant.NHENTAI_COOKIE, 'w') as f:
-                f.write(args.cookie)
-        except Exception as e:
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
 
+    # --- 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.')
+        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}"')
+        sys.exit(0)
+        # TODO: search without language
 
-    if os.path.exists(constant.NHENTAI_PROXY):
+    if args.proxy is not None:
-        with open(constant.NHENTAI_PROXY, 'r') as f:
+        proxy_url = urlparse(args.proxy)
-            link = f.read()
+        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h',
-            constant.PROXY = {'http': link, 'https': link}
+                                                             'socks4', 'socks4a'):
+            logger.error(f'Invalid protocol "{proxy_url.scheme}" of proxy, ignored')
+            sys.exit(0)
+        else:
+            constant.CONFIG['proxy'] = {
+                'http': args.proxy,
+                'https': args.proxy,
+            }
+            logger.info(f'Proxy now set to "{args.proxy}"')
+            write_config()
+            sys.exit(0)
 
-    if args.proxy:
+    if args.viewer_template is not None:
-        try:
+        if not args.viewer_template:
-            if not os.path.exists(constant.NHENTAI_HOME):
+            args.viewer_template = 'default'
-                os.mkdir(constant.NHENTAI_HOME)
 
-            proxy_url = urlparse(args.proxy)
+        if not os.path.exists(os.path.join(os.path.dirname(__file__),
-            if proxy_url.scheme not in ('http', 'https'):
+                                           f'viewer/{args.viewer_template}/index.html')):
-                logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
+            logger.error(f'Template "{args.viewer_template}" does not exists')
-            else:
+            sys.exit(1)
-                with open(constant.NHENTAI_PROXY, 'w') as f:
+        else:
-                    f.write(args.proxy)
+            constant.CONFIG['template'] = args.viewer_template
+            write_config()
 
-        except Exception as e:
+    # --- end set config ---
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
-
-        logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
-        exit(0)
 
     if args.favorites:
-        if not constant.COOKIE:
+        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.id:
-        _ = [i.strip() for i in args.id.split(',')]
-        args.id = set(int(i) for i in _ if i.isdigit())
 
     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 \
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites and not args.artist:
-            not args.tag and not args.artist and not args.character and \
-            not args.parody and not args.group and not args.language 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.tag and not args.artist and \
+    if not args.keyword and not args.id and not args.favorites and not args.artist:
-            not args.character and not args.parody and not args.group and not args.language 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')
+        sys.exit(1)
 
     return args

nhentai/command.py

@@ -1,62 +1,67 @@
-#!/usr/bin/env python2.7
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+import os
+import shutil
+import sys
 import signal
 import platform
-import time
+import urllib3.exceptions
 
+from nhentai import constant
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser, tag_parser
+from nhentai.parser import doujinshi_parser, search_parser, legacy_search_parser, print_doujinshi, favorites_parser
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, check_cookie, signal_handler, DB
+from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata_file, \
+    paging, check_cookie, signal_handler, DB, move_to_folder
 
 
 def main():
     banner()
-    options = cmd_parser()
-    logger.info('Using mirror: {0}'.format(BASE_URL))
 
-    from nhentai.constant import PROXY
+    if sys.version_info < (3, 0, 0):
-    # constant.PROXY will be changed after cmd_parser()
+        logger.error('nhentai now only support Python 3.x')
-    if PROXY != {}:
+        sys.exit(1)
-        logger.info('Using proxy: {0}'.format(PROXY))
+
+    options = cmd_parser()
+    logger.info(f'Using mirror: {BASE_URL}')
+
+    # CONFIG['proxy'] will be changed after cmd_parser()
+    if constant.CONFIG['proxy']['http']:
+        logger.info(f'Using proxy: {constant.CONFIG["proxy"]["http"]}')
+
+    if not constant.CONFIG['template']:
+        constant.CONFIG['template'] = 'default'
+
+    logger.info(f'Using viewer template "{constant.CONFIG["template"]}"')
 
     # check your cookie
     check_cookie()
 
     doujinshis = []
     doujinshi_ids = []
-    doujinshi_list = []
+
+    page_list = paging(options.page)
 
     if options.favorites:
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshis = favorites_parser(options.page_range)
+        doujinshis = favorites_parser() if options.page_all else favorites_parser(page=page_list)
-
-    elif options.tag:
-        doujinshis = tag_parser(options.tag, sorting=options.sorting, max_page=options.max_page)
-
-    elif options.artist:
-        doujinshis = tag_parser(options.artist, max_page=options.max_page, index=1)
-
-    elif options.character:
-        doujinshis = tag_parser(options.character, max_page=options.max_page, index=2)
-
-    elif options.parody:
-        doujinshis = tag_parser(options.parody, max_page=options.max_page, index=3)
-
-    elif options.group:
-        doujinshis = tag_parser(options.group, max_page=options.max_page, index=4)
-
-    elif options.language:
-        doujinshis = tag_parser(options.language, max_page=options.max_page, index=5)
 
     elif options.keyword:
-        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
+        if constant.CONFIG['language']:
+            logger.info(f'Using default language: {constant.CONFIG["language"]}')
+            options.keyword += f' language:{constant.CONFIG["language"]}'
+
+        _search_parser = legacy_search_parser if options.legacy else search_parser
+        doujinshis = _search_parser(options.keyword, sorting=options.sorting, page=page_list,
+                                    is_page_all=options.page_all)
+
+    elif options.artist:
+        doujinshis = legacy_search_parser(options.artist, sorting=options.sorting, page=page_list,
+                                          is_page_all=options.page_all, type_='ARTIST')
 
     elif not doujinshi_ids:
         doujinshi_ids = options.id
@@ -65,56 +70,80 @@ def main():
     if options.is_download and doujinshis:
         doujinshi_ids = [i['id'] for i in doujinshis]
 
-        if options.is_save_download_history:
+    if options.is_save_download_history:
-            with DB() as db:
+        with DB() as db:
-                data = set(db.get_all())
+            data = map(int, db.get_all())
 
-            doujinshi_ids = list(set(doujinshi_ids) - data)
+        doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
-
-    if doujinshi_ids:
-        for i, id_ in enumerate(doujinshi_ids):
-            if options.delay:
-                time.sleep(options.delay)
-
-            doujinshi_info = doujinshi_parser(id_)
-
-            if doujinshi_info:
-                doujinshi_list.append(Doujinshi(name_format=options.name_format, **doujinshi_info))
-
-            if (i + 1) % 10 == 0:
-                logger.info('Progress: %d / %d' % (i + 1, len(doujinshi_ids)))
 
     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)
 
-        for doujinshi in doujinshi_list:
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
+
+            if not options.dryrun:
+                doujinshi.downloader = downloader
+
+                if doujinshi.check_if_need_download(options):
+                    doujinshi.download()
+                else:
+                    logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {doujinshi.name}')
+                    continue
+
+            if options.generate_metadata:
+                generate_metadata_file(options.output_dir, doujinshi)
 
-            doujinshi.downloader = downloader
-            doujinshi.download()
             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:
+            if not options.is_nohtml:
-                generate_html(options.output_dir, doujinshi)
+                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:
+                generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
+
+            if options.is_pdf:
+                generate_doc('pdf', options.output_dir, doujinshi, options.regenerate)
+
+            if options.move_to_folder:
+                if options.is_cbz:
+                    move_to_folder(options.output_dir, doujinshi, 'cbz')
+                if options.is_pdf:
+                    move_to_folder(options.output_dir, doujinshi, 'pdf')
+
+            if options.rm_origin_dir:
+                if options.move_to_folder:
+                    logger.critical('You specified both --move-to-folder and --rm-origin-dir options, '
+                                    'you will not get anything :(')
+                shutil.rmtree(os.path.join(options.output_dir, doujinshi.filename), ignore_errors=True)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)
 
         if not platform.system() == 'Windows':
-            logger.log(15, '🍻 All done.')
+            logger.log(16, '🍻 All done.')
         else:
-            logger.log(15, 'All done.')
+            logger.log(16, 'All done.')
 
     else:
-        [doujinshi.show() for doujinshi in doujinshi_list]
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
+            doujinshi.show()
 
 
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/constant.py

@@ -1,42 +1,66 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 import os
 import tempfile
 
-try:
+from urllib.parse import urlparse
-    from urlparse import urlparse
+from platform import system
-except ImportError:
-    from urllib.parse import urlparse
 
 
+def get_nhentai_home() -> str:
+    home = os.getenv('HOME', tempfile.gettempdir())
+
+    if system() == 'Linux':
+        xdgdat = os.getenv('XDG_DATA_HOME')
+        if xdgdat and os.path.exists(os.path.join(xdgdat, 'nhentai')):
+            return os.path.join(xdgdat, 'nhentai')
+        if home and os.path.exists(os.path.join(home, '.nhentai')):
+            return os.path.join(home, '.nhentai')
+        if xdgdat:
+            return os.path.join(xdgdat, 'nhentai')
+
+    # Use old default path in other systems
+    return os.path.join(home, '.nhentai')
+
+
+DEBUG = os.getenv('DEBUG', False)
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-__api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
+DETAIL_URL = f'{BASE_URL}/g'
-__api_suspended_SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+LEGACY_SEARCH_URL = f'{BASE_URL}/search/'
+SEARCH_URL = f'{BASE_URL}/api/galleries/search'
+ARTIST_URL = f'{BASE_URL}/artist/'
 
-DETAIL_URL = '%s/g' % BASE_URL
+TAG_API_URL = f'{BASE_URL}/api/galleries/tagged'
-SEARCH_URL = '%s/search/' % BASE_URL
+LOGIN_URL = f'{BASE_URL}/login/'
+CHALLENGE_URL = f'{BASE_URL}/challenge'
+FAV_URL = f'{BASE_URL}/favorites/'
 
-TAG_URL = ['%s/tag' % BASE_URL,
-           '%s/artist' % BASE_URL,
-           '%s/character' % BASE_URL,
-           '%s/parody' % BASE_URL,
-           '%s/group' % BASE_URL,
-           '%s/language' % BASE_URL]
 
-TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
+IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
-LOGIN_URL = '%s/login/' % BASE_URL
+IMAGE_URL_MIRRORS = [
-CHALLENGE_URL = '%s/challenge' % BASE_URL
+    f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}',
-FAV_URL = '%s/favorites/' % BASE_URL
+    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}',
+]
 
-u = urlparse(BASE_URL)
+NHENTAI_HOME = get_nhentai_home()
-IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
-
-NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
-NHENTAI_PROXY = os.path.join(NHENTAI_HOME, 'proxy')
-NHENTAI_COOKIE = os.path.join(NHENTAI_HOME, 'cookie')
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
+NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
-PROXY = {}
+__api_suspended_DETAIL_URL = f'{BASE_URL}/api/gallery'
 
-COOKIE = ''
+CONFIG = {
+    'proxy': {'http': '', 'https': ''},
+    'cookie': '',
+    'language': '',
+    'template': '',
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+    'max_filename': 85
+}
+
+LANGUAGE_ISO = {
+    'english': 'en',
+    'chinese': 'zh',
+    'japanese': 'ja',
+    'translated': 'translated'
+}

nhentai/doujinshi.py

@@ -1,7 +1,7 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
+import os
+
 from tabulate import tabulate
-from future.builtins import range
 
 from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
@@ -12,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -21,64 +22,102 @@ class DoujinshiInfo(dict):
 
     def __getattr__(self, item):
         try:
-            return dict.__getitem__(self, item)
+            ret = dict.__getitem__(self, item)
+            return ret if ret else 'Unknown'
         except KeyError:
-            return ''
+            return 'Unknown'
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
+    def __init__(self, name=None, pretty_name=None, id=None, favorite_counts=0, img_id=None,
+                 ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
+        self.pretty_name = pretty_name
         self.id = id
+        self.favorite_counts = favorite_counts
         self.img_id = img_id
         self.ext = ext
         self.pages = pages
         self.downloader = None
-        self.url = '%s/%d' % (DETAIL_URL, self.id)
+        self.url = f'{DETAIL_URL}/{self.id}'
         self.info = DoujinshiInfo(**kwargs)
 
-        name_format = name_format.replace('%i', str(self.id))
+        ag_value = self.info.groups if self.info.artists == 'Unknown' else self.info.artists
-        name_format = name_format.replace('%a', self.info.artists)
+        name_format = name_format.replace('%ag', format_filename(ag_value))
-        name_format = name_format.replace('%t', self.name)
+
-        name_format = name_format.replace('%s', self.info.subtitle)
+        name_format = name_format.replace('%i', format_filename(str(self.id)))
-        self.filename = format_filename(name_format)
+        name_format = name_format.replace('%f', format_filename(str(self.favorite_counts)))
+        name_format = name_format.replace('%a', format_filename(self.info.artists))
+        name_format = name_format.replace('%g', format_filename(self.info.groups))
+
+        name_format = name_format.replace('%t', format_filename(self.name))
+        name_format = name_format.replace('%p', format_filename(self.pretty_name))
+        name_format = name_format.replace('%s', format_filename(self.info.subtitle))
+        self.filename = format_filename(name_format, 255, True)
+
+        self.table = [
+            ['Parodies', self.info.parodies],
+            ['Doujinshi', self.name],
+            ['Subtitle', self.info.subtitle],
+            ['Date', self.info.date],
+            ['Characters', self.info.characters],
+            ['Authors', self.info.artists],
+            ['Groups', self.info.groups],
+            ['Languages', self.info.languages],
+            ['Tags', self.info.tags],
+            ['Favorite Counts', self.info.favorite_counts],
+            ['URL', self.url],
+            ['Pages', self.pages],
+        ]
 
     def __repr__(self):
-        return '<Doujinshi: {0}>'.format(self.name)
+        return f'<Doujinshi: {self.name}>'
 
     def show(self):
-        table = [
+        logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
-            ["Doujinshi", self.name],
+
-            ["Subtitle", self.info.subtitle],
+    def check_if_need_download(self, options):
-            ["Characters", self.info.characters],
+        base_path = os.path.join(self.downloader.path, self.filename)
-            ["Authors", self.info.artists],
+
-            ["Languages", self.info.languages],
+        # regenerate, re-download
-            ["Tags", self.info.tags],
+        if options.regenerate:
-            ["URL", self.url],
+            return True
-            ["Pages", self.pages],
+
-        ]
+        # pdf or cbz file exists, skip re-download
-        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
+        # doujinshi directory may not exist b/c of --rm-origin-dir option set.
+        # user should pass --regenerate option to get back origin dir.
+        ret_pdf = ret_cbz = None
+        if options.is_pdf:
+            ret_pdf = os.path.exists(f'{base_path}.pdf') or os.path.exists(f'{base_path}/{self.filename}.pdf')
+
+        if options.is_cbz:
+            ret_cbz = os.path.exists(f'{base_path}.cbz') or os.path.exists(f'{base_path}/{self.filename}.cbz')
+
+        ret = list(filter(lambda s: s is not None, [ret_cbz, ret_pdf]))
+        if ret and all(ret):
+            return False
+
+        # doujinshi directory doesn't exist, re-download
+        if not (os.path.exists(base_path) and os.path.isdir(base_path)):
+            return True
+
+        # fallback
+        return True
 
     def download(self):
-        logger.info('Starting to download doujinshi: %s' % self.name)
+        logger.info(f'Starting to download doujinshi: {self.name}')
         if self.downloader:
             download_queue = []
-
             if len(self.ext) != self.pages:
                 logger.warning('Page count and ext count do not equal')
 
             for i in range(1, min(self.pages, len(self.ext)) + 1):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))
+                download_queue.append(f'{IMAGE_URL}/{self.img_id}/{i}.{self.ext[i-1]}')
-
-            self.downloader.download(download_queue, self.filename)
-
-            '''
-            for i in range(len(self.ext)):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i+1, EXT_MAP[self.ext[i]]))
-            '''
 
+            return self.downloader.start_download(download_queue, self.filename)
         else:
             logger.critical('Downloader has not been loaded')
+            return False
 
 
 if __name__ == '__main__':
@@ -88,4 +127,4 @@ if __name__ == '__main__':
     try:
         test.download()
     except Exception as e:
-        print('Exception: %s' % str(e))
+        print(f'Exception: {e}')

nhentai/downloader.py

@@ -1,94 +1,110 @@
 # coding: utf-
-from __future__ import unicode_literals, print_function
 
-import multiprocessing
-import signal
-
-from future.builtins import str as text
 import os
-import requests
+import asyncio
-import threadpool
+import httpx
-import time
+import urllib3.exceptions
-import multiprocessing as mp
-
-try:
-    from urllib.parse import urlparse
-except ImportError:
-    from urlparse import urlparse
 
+from urllib.parse import urlparse
+from nhentai import constant
 from nhentai.logger import logger
-from nhentai.parser import request
+from nhentai.utils import Singleton, async_request
-from nhentai.utils import Singleton, signal_handler
 
-requests.packages.urllib3.disable_warnings()
-semaphore = mp.Semaphore()
 
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 class NHentaiImageNotExistException(Exception):
     pass
 
 
-class Downloader(Singleton):
+def download_callback(result):
+    result, data = result
+    if result == 0:
+        logger.warning('fatal errors occurred, ignored')
+    elif result == -1:
+        logger.warning(f'url {data} return status code 404')
+    elif result == -2:
+        logger.warning('Ctrl-C pressed, exiting sub processes ...')
+    elif result == -3:
+        # workers won't be run, just pass
+        pass
+    else:
+        logger.log(16, f'{data} downloaded successfully')
 
-    def __init__(self, path='', size=5, timeout=30, delay=0):
+
-        self.size = size
+
+class Downloader(Singleton):
+    def __init__(self, path='', threads=5, timeout=30, delay=0):
+        self.threads = threads
         self.path = str(path)
         self.timeout = timeout
         self.delay = delay
 
-    def download_(self, url, folder='', filename='', retried=0):
+    async def fiber(self, tasks):
+        self.semaphore = asyncio.Semaphore(self.threads)
+        for completed_task in asyncio.as_completed(tasks):
+            try:
+                result = await completed_task
+                logger.info(f'{result[1]} download completed')
+            except Exception as e:
+                logger.error(f'An error occurred: {e}')
+
+
+    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):
+        logger.info(f'Starting to download {url} ...')
+
         if self.delay:
-            time.sleep(self.delay)
+            await asyncio.sleep(self.delay)
-        logger.info('Starting to download {0} ...'.format(url))
+
         filename = filename if filename else os.path.basename(urlparse(url).path)
-        base_filename, extension = os.path.splitext(filename)
+
+        save_file_path = os.path.join(self.folder, filename)
+
         try:
-            if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
+            if os.path.exists(save_file_path):
-                logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
+                logger.warning(f'Skipped download: {save_file_path} already exists')
-                                                                                extension)))
                 return 1, url
 
-            response = None
+            response = await async_request('GET', url, timeout=self.timeout, proxies=proxy)
-            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
-                i = 0
-                while i < 10:
-                    try:
-                        response = request('get', url, stream=True, timeout=self.timeout)
-                        if response.status_code != 200:
-                            raise NHentaiImageNotExistException
 
-                    except NHentaiImageNotExistException as e:
+            if response.status_code != 200:
-                        raise e
+                path = urlparse(url).path
+                for mirror in constant.IMAGE_URL_MIRRORS:
+                    logger.info(f"Try mirror: {mirror}{path}")
+                    mirror_url = f'{mirror}{path}'
+                    response = await async_request('GET', mirror_url, timeout=self.timeout, proxies=proxy)
+                    if response.status_code == 200:
+                        break
 
-                    except Exception as e:
+            if not await self.save(filename, response):
-                        i += 1
+                logger.error(f'Can not download image {url}')
-                        if not i < 10:
+                return 1, None
-                            logger.critical(str(e))
-                            return 0, None
-                        continue
 
-                    break
+        except (httpx.HTTPStatusError, httpx.TimeoutException, httpx.ConnectError) as e:
-
-                length = response.headers.get('content-length')
-                if length is None:
-                    f.write(response.content)
-                else:
-                    for chunk in response.iter_content(2048):
-                        f.write(chunk)
-
-        except (requests.HTTPError, requests.Timeout) as e:
             if retried < 3:
-                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
+                logger.info(f'Download {filename} failed, retrying({retried + 1}) times...')
-                return 0, self.download_(url=url, folder=folder, filename=filename, retried=retried+1)
+                return await self.download(
+                    url=url,
+                    folder=folder,
+                    filename=filename,
+                    retried=retried + 1,
+                    proxy=proxy,
+                )
             else:
                 return 0, None
 
         except NHentaiImageNotExistException as e:
-            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            os.remove(save_file_path)
             return -1, url
 
         except Exception as e:
             import traceback
+
+            logger.error(f"Exception type: {type(e)}")
             traceback.print_stack()
             logger.critical(str(e))
             return 0, None
@@ -98,62 +114,48 @@ class Downloader(Singleton):
 
         return 1, url
 
-    def _download_callback(self, result):
+    async def save(self, save_file_path, response) -> bool:
-        result, data = result
+        if response is None:
-        if result == 0:
+            logger.error('Error: Response is None')
-            logger.warning('fatal errors occurred, ignored')
+            return False
-            # exit(1)
+        save_file_path = os.path.join(self.folder, save_file_path)
-        elif result == -1:
+        with open(save_file_path, 'wb') as f:
-            logger.warning('url {} return status code 404'.format(data))
+            if response is not None:
-        elif result == -2:
+                length = response.headers.get('content-length')
-            logger.warning('Ctrl-C pressed, exiting sub processes ...')
+                if length is None:
-        elif result == -3:
+                    f.write(response.content)
-            # workers wont be run, just pass
+                else:
-            pass
+                    async for chunk in response.aiter_bytes(2048):
-        else:
+                        f.write(chunk)
-            logger.log(15, '{0} downloaded successfully'.format(data))
+        return True
 
-    def download(self, queue, folder=''):
+
-        if not isinstance(folder, text):
+    def start_download(self, queue, folder='') -> bool:
+        if not isinstance(folder, (str,)):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
+        logger.info(f'Doujinshi will be saved at "{folder}"')
         if not os.path.exists(folder):
-            logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
-                logger.critical('{0}'.format(str(e)))
+                logger.critical(str(e))
+        self.folder = folder
 
-        else:
+        if os.getenv('DEBUG', None) == 'NODOWNLOAD':
-            logger.warn('Path \'{0}\' already exist.'.format(folder))
+            # Assuming we want to continue with rest of process.
-
+            return True
-        queue = [(self, url, folder) for url in queue]
-
-        pool = multiprocessing.Pool(self.size, init_worker)
-
-        for item in queue:
-            pool.apply_async(download_wrapper, args=item, callback=self._download_callback)
-
-        pool.close()
-        pool.join()
 
 
-def download_wrapper(obj, url, folder=''):
+        coroutines = [
-    if semaphore.get_value():
+            self._semaphore_download(url, filename=os.path.basename(urlparse(url).path))
-        return Downloader.download_(obj, url=url, folder=folder)
+            for url in queue
-    else:
+        ]
-        return -3, None
 
+        # Prevent coroutines infection
+        asyncio.run(self.fiber(coroutines))
 
-def init_worker():
+        return True
-    signal.signal(signal.SIGINT, subprocess_signal)
-
-
-def subprocess_signal(signal, frame):
-    if semaphore.acquire(timeout=1):
-        logger.warning('Ctrl-C pressed, exiting sub processes ...')
-
-    raise KeyboardInterrupt

nhentai/logger.py

@@ -1,7 +1,6 @@
 #
 # Copyright (C) 2010-2012 Vinay Sajip. All rights reserved. Licensed under the new BSD license.
 #
-from __future__ import print_function, unicode_literals
 import logging
 import re
 import platform
@@ -35,7 +34,7 @@ class ColorizingStreamHandler(logging.StreamHandler):
     # levels to (background, foreground, bold/intense)
     level_map = {
         logging.DEBUG: (None, 'blue', False),
-        logging.INFO: (None, 'green', False),
+        logging.INFO: (None, 'white', False),
         logging.WARNING: (None, 'yellow', False),
         logging.ERROR: (None, 'red', False),
         logging.CRITICAL: ('red', 'white', False)
@@ -161,20 +160,20 @@ class ColorizingStreamHandler(logging.StreamHandler):
         return self.colorize(message, record)
 
 
-logging.addLevelName(15, "INFO")
+logging.addLevelName(16, "SUCCESS")
 logger = logging.getLogger('nhentai')
 LOGGER_HANDLER = ColorizingStreamHandler(sys.stdout)
-FORMATTER = logging.Formatter("\r[%(asctime)s] [%(levelname)s] %(message)s", "%H:%M:%S")
+FORMATTER = logging.Formatter("\r[%(asctime)s] %(funcName)s: %(message)s", "%H:%M:%S")
 LOGGER_HANDLER.setFormatter(FORMATTER)
-LOGGER_HANDLER.level_map[logging.getLevelName("INFO")] = (None, "cyan", False)
+LOGGER_HANDLER.level_map[logging.getLevelName("SUCCESS")] = (None, "green", False)
 logger.addHandler(LOGGER_HANDLER)
 logger.setLevel(logging.DEBUG)
 
 
 if __name__ == '__main__':
-    logger.log(15, 'nhentai')
+    logger.log(16, 'nhentai')
     logger.info('info')
-    logger.warn('warn')
+    logger.warning('warning')
     logger.debug('debug')
     logger.error('error')
     logger.critical('critical')

nhentai/parser.py

@@ -1,6 +1,4 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
-
 import sys
 import os
 import re
@@ -28,7 +26,7 @@ def login(username, password):
         logger.info('Getting CSRF token ...')
 
     if os.getenv('DEBUG'):
-        logger.info('CSRF token is {}'.format(csrf_token))
+        logger.info(f'CSRF token is {csrf_token}')
 
     login_dict = {
         'csrfmiddlewaretoken': csrf_token,
@@ -43,11 +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):
@@ -58,18 +56,18 @@ def _get_title_and_id(response):
         doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
         title = doujinshi_container.text.strip()
         title = title if len(title) < 85 else title[:82] + '...'
-        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
+        id_ = re.search('/g/([0-9]+)/', doujinshi.a['href']).group(1)
         result.append({'id': id_, 'title': title})
 
     return result
 
 
-def favorites_parser(page_range=''):
+def favorites_parser(page=None):
     result = []
     html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
     count = html.find('span', attrs={'class': 'count'})
     if not count:
-        logger.error("Can't get your number of favorited doujins. Did the login failed?")
+        logger.error("Can't get your number of favorite doujinshis. Did the login failed?")
         return []
 
     count = int(count.text.strip('(').strip(')').replace(',', ''))
@@ -78,93 +76,81 @@ def favorites_parser(page_range=''):
         return []
     pages = int(count / 25)
 
-    if pages:
+    if page:
-        pages += 1 if count % (25 * pages) else 0
+        page_range_list = page
     else:
-        pages = 1
+        if pages:
+            pages += 1 if count % (25 * pages) else 0
+        else:
+            pages = 1
 
-    logger.info('You have %d favorites in %d pages.' % (count, pages))
+        logger.info(f'You have {count} favorites in {pages} pages.')
 
-    if os.getenv('DEBUG'):
+        if os.getenv('DEBUG'):
-        pages = 1
+            pages = 1
 
-    page_range_list = range(1, pages + 1)
+        page_range_list = range(1, pages + 1)
-    if page_range:
-        logger.info('page range is {0}'.format(page_range))
-        page_range_list = page_range_parser(page_range, pages)
 
     for page in page_range_list:
         try:
-            logger.info('Getting doujinshi ids of page %d' % page)
+            logger.info(f'Getting doujinshi ids of page {page}')
-            resp = request('get', constant.FAV_URL + '?page=%d' % page).content
+            resp = request('get', f'{constant.FAV_URL}?page={page}').content
 
             result.extend(_get_title_and_id(resp))
         except Exception as e:
-            logger.error('Error: %s, continue', str(e))
+            logger.error(f'Error: {e}, continue')
 
     return result
 
 
-def page_range_parser(page_range, max_page_num):
+def doujinshi_parser(id_, counter=0):
-    pages = set()
-    ranges = str.split(page_range, ',')
-    for range_str in ranges:
-        idx = range_str.find('-')
-        if idx == -1:
-            try:
-                page = int(range_str)
-                if page <= max_page_num:
-                    pages.add(page)
-            except ValueError:
-                logger.error('page range({0}) is not valid'.format(page_range))
-        else:
-            try:
-                left = int(range_str[:idx])
-                right = int(range_str[idx+1:])
-                if right > max_page_num:
-                    right = max_page_num
-                for page in range(left, right+1):
-                    pages.add(page)
-            except ValueError:
-                logger.error('page range({0}) is not valid'.format(page_range))
-    
-    return list(pages)    
-
-
-def doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
+        raise Exception(f'Doujinshi id({id_}) is not valid')
 
     id_ = int(id_)
-    logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
+    logger.info(f'Fetching doujinshi information of id {id_}')
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
+    url = f'{constant.DETAIL_URL}/{id_}/'
 
     try:
         response = request('get', url)
         if response.status_code in (200, ):
             response = response.content
+        elif response.status_code in (404,):
+            logger.error(f'Doujinshi with id {id_} cannot be found')
+            return []
         else:
-            logger.debug('Slow down and retry ({}) ...'.format(id_))
+            counter += 1
+
+            if counter == 10:
+                logger.critical(f'Failed to fetch doujinshi information of id {id_}')
+                return None
+
+            logger.debug(f'Slow down and retry ({id_}) ...')
             time.sleep(1)
-            return doujinshi_parser(str(id_))
+            return doujinshi_parser(str(id_), counter)
 
     except Exception as e:
-        logger.warn('Error: {}, ignored'.format(str(e)))
+        logger.warning(f'Error: {e}, ignored')
         return None
 
+    # print(response)
     html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
+    pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
     subtitle = doujinshi_info.find('h2')
-
+    favorite_counts = doujinshi_info.find('span', class_='nobold').find('span', class_='count').text.strip()
     doujinshi['name'] = title
+    doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
+    doujinshi['favorite_counts'] = favorite_counts
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
+                       doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
@@ -173,17 +159,15 @@ def doujinshi_parser(id_):
 
     if not img_id:
         logger.critical('Tried yo get image id failed')
-        exit(1)
+        sys.exit(1)
 
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
 
     pages = 0
-    for _ in doujinshi_info.find_all('div', class_=''):
+    for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
-        pages = re.search('([\d]+) pages', _.text)
+        if re.search('Pages:', _.text):
-        if pages:
+            pages = _.find('span', class_='name').string
-            pages = pages.group(1)
-            break
     doujinshi['pages'] = int(pages)
 
     # gain information of the doujinshi
@@ -192,7 +176,7 @@ def doujinshi_parser(id_):
     for field in information_fields:
         field_name = field.contents[0].strip().strip(':')
         if field_name in needed_fields:
-            data = [sub_field.contents[0].strip() for sub_field in
+            data = [sub_field.find('span', attrs={'class': 'name'}).contents[0].strip() for sub_field in
                     field.find_all('a', attrs={'class': 'tag'})]
             doujinshi[field_name.lower()] = ', '.join(data)
 
@@ -202,125 +186,15 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def search_parser(keyword, sorting='date', page=1):
+def legacy_doujinshi_parser(id_):
-    logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
-    response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
-
-    result = _get_title_and_id(response)
-    if not result:
-        logger.warn('Not found anything of keyword {}'.format(keyword))
-
-    return result
-
-
-def print_doujinshi(doujinshi_list):
-    if not doujinshi_list:
-        return
-    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
-    headers = ['id', 'doujinshi']
-    logger.info('Search Result\n' +
-                tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
-
-
-def tag_parser(tag_name, sorting='date', max_page=1, index=0):
-    result = []
-    tag_name = tag_name.lower()
-    if ',' in tag_name:
-        tag_name = [i.strip().replace(' ', '-') for i in tag_name.split(',')]
-    else:
-        tag_name = tag_name.strip().replace(' ', '-')
-    if sorting == 'date':
-        sorting = ''
-
-    for p in range(1, max_page + 1):
-        if sys.version_info >= (3, 0, 0):
-            unicode_ = str
-        else:
-            unicode_ = unicode
-
-        if isinstance(tag_name, (str, unicode_)):
-            logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
-            response = request('get', url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], tag_name, sorting, p)).content
-            result += _get_title_and_id(response)
-        else:
-            for i in tag_name:
-                logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, i))
-                response = request('get',
-                                   url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], i, sorting, p)).content
-                result += _get_title_and_id(response)
-
-        if not result:
-            logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
-            return
-
-    if not result:
-        logger.warn('No results for tag \'{}\''.format(tag_name))
-
-    return result
-
-
-def __api_suspended_search_parser(keyword, sorting, page):
-    logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
-    result = []
-    i = 0
-    while i < 5:
-        try:
-            response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).json()
-        except Exception as e:
-            i += 1
-            if not i < 5:
-                logger.critical(str(e))
-                logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
-                exit(1)
-            continue
-        break
-
-    if 'result' not in response:
-        raise Exception('No result in response')
-
-    for row in response['result']:
-        title = row['title']['english']
-        title = title[:85] + '..' if len(title) > 85 else title
-        result.append({'id': row['id'], 'title': title})
-
-    if not result:
-        logger.warn('No results for keywords {}'.format(keyword))
-
-    return result
-
-
-def __api_suspended_tag_parser(tag_id, sorting, max_page=1):
-    logger.info('Searching for doujinshi with tag id {0}'.format(tag_id))
-    result = []
-    response = request('get', url=constant.TAG_API_URL, params={'sort': sorting, 'tag_id': tag_id}).json()
-    page = max_page if max_page <= response['num_pages'] else int(response['num_pages'])
-
-    for i in range(1, page + 1):
-        logger.info('Getting page {} ...'.format(i))
-
-        if page != 1:
-            response = request('get', url=constant.TAG_API_URL,
-                               params={'sort': sorting, 'tag_id': tag_id}).json()
-    for row in response['result']:
-        title = row['title']['english']
-        title = title[:85] + '..' if len(title) > 85 else title
-        result.append({'id': row['id'], 'title': title})
-
-    if not result:
-        logger.warn('No results for tag id {}'.format(tag_id))
-
-    return result
-
-
-def __api_suspended_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
+        raise Exception(f'Doujinshi id({id_}) is not valid')
 
     id_ = int(id_)
-    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
+    logger.info(f'Fetching information of doujinshi id {id_}')
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    url = f'{constant.DETAIL_URL}/{id_}'
     i = 0
     while 5 > i:
         try:
@@ -329,7 +203,7 @@ def __api_suspended_doujinshi_parser(id_):
             i += 1
             if not i < 5:
                 logger.critical(str(e))
-                exit(1)
+                sys.exit(1)
             continue
         break
 
@@ -359,5 +233,112 @@ def __api_suspended_doujinshi_parser(id_):
     return doujinshi
 
 
+def print_doujinshi(doujinshi_list):
+    if not doujinshi_list:
+        return
+    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
+    headers = ['id', 'doujinshi']
+    logger.info(f'Search Result || Found {doujinshi_list.__len__()} doujinshis')
+    print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+
+
+def legacy_search_parser(keyword, sorting, page, is_page_all=False, type_='SEARCH'):
+    logger.info(f'Searching doujinshis of keyword {keyword}')
+    result = []
+
+    if type_ not in ('SEARCH', 'ARTIST', ):
+        raise ValueError('Invalid type')
+
+    if is_page_all:
+        if type_ == 'SEARCH':
+            response = request('get', url=constant.LEGACY_SEARCH_URL,
+                               params={'q': keyword, 'page': 1, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': 1}).content
+
+        html = BeautifulSoup(response, 'lxml')
+        pagination = html.find(attrs={'class': 'pagination'})
+        last_page = pagination.find(attrs={'class': 'last'})
+        last_page = re.findall('page=([0-9]+)', last_page.attrs['href'])[0]
+        logger.info(f'Getting doujinshi ids of {last_page} pages')
+        pages = range(1, int(last_page))
+    else:
+        pages = page
+
+    for p in pages:
+        logger.info(f'Fetching page {p} ...')
+        if type_ == 'SEARCH':
+            response = request('get', url=constant.LEGACY_SEARCH_URL,
+                               params={'q': keyword, 'page': p, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': p}).content
+
+        if response is None:
+            logger.warning(f'No result in response in page {p}')
+            continue
+        result.extend(_get_title_and_id(response))
+
+    if not result:
+        logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
+def search_parser(keyword, sorting, page, is_page_all=False):
+    result = []
+    response = None
+    if not page:
+        page = [1]
+
+    if is_page_all:
+        url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
+        init_response = request('get', url.replace('%2B', '+')).json()
+        page = range(1, init_response['num_pages']+1)
+
+    total = f'/{page[-1]}' if is_page_all else ''
+    not_exists_persist = False
+    for p in page:
+        i = 0
+
+        logger.info(f'Searching doujinshis using keywords "{keyword}" on page {p}{total}')
+        while i < 3:
+            try:
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+                                                                      'page': p, 'sort': sorting}).url
+
+                if constant.DEBUG:
+                    logger.debug(f'Request URL: {url}')
+
+                response = request('get', url.replace('%2B', '+')).json()
+            except Exception as e:
+                logger.critical(str(e))
+                response = None
+            break
+
+        if constant.DEBUG:
+            logger.debug(f'Response: {response}')
+
+        if response is None or 'result' not in response:
+            logger.warning(f'No result in response in page {p}')
+            if not_exists_persist is True:
+                break
+            continue
+
+        for row in response['result']:
+            title = row['title']['english']
+            title = title[:constant.CONFIG['max_filename']] + '..' if \
+                len(title) > constant.CONFIG['max_filename'] else title
+
+            result.append({'id': row['id'], 'title': title})
+
+        not_exists_persist = False
+        if not result:
+            logger.warning(f'No results for keywords {keyword}')
+
+    return result
+
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/serializer.py

@@ -1,11 +1,15 @@
 # coding: utf-8
 import json
 import os
+from xml.sax.saxutils import escape
+from nhentai.constant import LANGUAGE_ISO
 
 
-def serialize(doujinshi, dir):
+def serialize_json(doujinshi, output_dir):
     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:
@@ -20,12 +24,60 @@ def serialize(doujinshi, dir):
         metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
     if doujinshi.info.languages:
         metadata['language'] = [i.strip() for i in doujinshi.info.languages.split(',')]
-    metadata['category'] = doujinshi.info.categories
+    metadata['category'] = [i.strip() for i in doujinshi.info.categories.split(',')]
     metadata['URL'] = doujinshi.url
     metadata['Pages'] = doujinshi.pages
 
-    with open(os.path.join(dir, 'metadata.json'), 'w') as f:
+    with open(os.path.join(output_dir, 'metadata.json'), 'w') as f:
-        json.dump(metadata, f, separators=','':')
+        json.dump(metadata, f, separators=(',', ':'))
+
+
+def serialize_comic_xml(doujinshi, output_dir):
+    from iso8601 import parse_date
+    with open(os.path.join(output_dir, 'ComicInfo.xml'), 'w', encoding="utf-8") as f:
+        f.write('<?xml version="1.0" encoding="utf-8"?>\n')
+        f.write('<ComicInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" '
+                'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">\n')
+
+        xml_write_simple_tag(f, 'Manga', 'Yes')
+
+        xml_write_simple_tag(f, 'Title', doujinshi.name)
+        xml_write_simple_tag(f, 'Summary', doujinshi.info.subtitle)
+        xml_write_simple_tag(f, 'PageCount', doujinshi.pages)
+        xml_write_simple_tag(f, 'URL', doujinshi.url)
+        xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
+        xml_write_simple_tag(f, 'Favorites', doujinshi.favorite_counts)
+        xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
+
+        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and
+                             'full color' in doujinshi.info.tags else 'Yes')
+
+        if doujinshi.info.date:
+            dt = parse_date(doujinshi.info.date)
+            xml_write_simple_tag(f, 'Year', dt.year)
+            xml_write_simple_tag(f, 'Month', dt.month)
+            xml_write_simple_tag(f, 'Day', dt.day)
+        if doujinshi.info.parodies:
+            xml_write_simple_tag(f, 'Series', doujinshi.info.parodies)
+        if doujinshi.info.characters:
+            xml_write_simple_tag(f, 'Characters', doujinshi.info.characters)
+        if doujinshi.info.tags:
+            xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
+        if doujinshi.info.artists:
+            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in
+                                                          doujinshi.info.artists.split(',')]))
+
+        if doujinshi.info.languages:
+            languages = [i.strip() for i in doujinshi.info.languages.split(',')]
+            xml_write_simple_tag(f, 'Translated', 'Yes' if 'translated' in languages else 'No')
+            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGE_ISO[i]) for i in languages
+             if (i != 'translated' and i in LANGUAGE_ISO)]
+
+        f.write('</ComicInfo>')
+
+
+def xml_write_simple_tag(f, name, val, indent=1):
+    f.write(f'{" "*indent}<{name}>{escape(str(val))}</{name}>\n')
 
 
 def merge_json():
@@ -74,7 +126,7 @@ def serialize_unique(lst):
 def set_js_database():
     with open('data.js', 'w') as f:
         indexed_json = merge_json()
-        unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
+        unique_json = json.dumps(serialize_unique(indexed_json), separators=(',', ':'))
-        indexed_json = json.dumps(indexed_json, separators=','':')
+        indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)

nhentai/utils.py

@@ -1,37 +1,75 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import sys
 import re
 import os
-import string
 import zipfile
 import shutil
+import copy
+
+import httpx
 import requests
 import sqlite3
+import urllib.parse
+from typing import Optional, Tuple
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize, set_js_database
+from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
+
+MAX_FIELD_LENGTH = 100
 
 
 def request(method, url, **kwargs):
     session = requests.Session()
     session.headers.update({
         'Referer': constant.LOGIN_URL,
-        'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+        'User-Agent': constant.CONFIG['useragent'],
-        'Cookie': constant.COOKIE
+        'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
+
+    if not kwargs.get('proxies', None):
+        kwargs['proxies'] = constant.CONFIG['proxy']
+
+    return getattr(session, method)(url, verify=False, **kwargs)
+
+
+async def async_request(method, url, proxies = None, **kwargs):
+    headers = {
+        'Referer': constant.LOGIN_URL,
+        'User-Agent': constant.CONFIG['useragent'],
+        'Cookie': constant.CONFIG['cookie'],
+    }
+
+    if proxies is None:
+        proxies = constant.CONFIG['proxy']
+
+    if proxies.get('http') == '' and proxies.get('https') == '':
+        proxies = None
+
+    if proxies:
+        _proxies = {f'{k}://': v for k, v in proxies.items() if v}
+        proxies = _proxies
+
+    async with httpx.AsyncClient(headers=headers, verify=False, proxies=proxies, **kwargs) as client:
+        response = await client.request(method, url, **kwargs)
+
+    return response
 
 
 def check_cookie():
-    response = request('get', constant.BASE_URL).text
+    response = request('get', constant.BASE_URL)
-    username = re.findall('"/users/\d+/(.*?)"', response)
+
+    if response.status_code == 403 and 'Just a moment...' in response.text:
+        logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
+        sys.exit(1)
+
+    username = re.findall('"/users/[0-9]+/(.*?)"', response.text)
     if not username:
-        logger.error('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
+        logger.warning(
+            'Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
     else:
-        logger.info('Login successfully! Your username: {}'.format(username[0]))
+        logger.log(16, f'Login successfully! Your username: {username[0]}')
 
 
 class _Singleton(type):
@@ -48,15 +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__)
 
@@ -64,52 +93,91 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None):
+def parse_doujinshi_obj(
+        output_dir: str,
+        doujinshi_obj=None,
+        file_type: str = ''
+) -> Tuple[str, str]:
+
+    filename = f'./doujinshi.{file_type}'
+    doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    if doujinshi_obj is not None:
+        _filename = f'{doujinshi_obj.filename}.{file_type}'
+
+        if file_type == 'cbz':
+            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+
+        if file_type == 'pdf':
+            _filename = _filename.replace('/', '-')
+
+        filename = os.path.join(output_dir, _filename)
+
+    return doujinshi_dir, filename
+
+
+def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '.html')
     image_html = ''
 
-    if doujinshi_obj is not None:
+    if not os.path.exists(doujinshi_dir):
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+        logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
-    else:
+        try:
-        doujinshi_dir = '.'
+            os.makedirs(doujinshi_dir)
+        except EnvironmentError as e:
+            logger.critical(e)
 
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
     for image in file_list:
-        if not os.path.splitext(image)[1] in ('.jpg', '.png'):
+        if not os.path.splitext(image)[1] in ('.jpg', '.png', '.webp'):
             continue
+        image_html += f'<img src="{image}" class="image-item"/>\n'
 
-        image_html += '<img src="{0}" class="image-item"/>\n'\
+    html = readfile(f'viewer/{template}/index.html')
-            .format(image)
+    css = readfile(f'viewer/{template}/styles.css')
-    html = readfile('viewer/index.html')
+    js = readfile(f'viewer/{template}/scripts.js')
-    css = readfile('viewer/styles.css')
-    js = readfile('viewer/scripts.js')
 
     if doujinshi_obj is not None:
-        serialize(doujinshi_obj, doujinshi_dir)
+        serialize_json(doujinshi_obj, doujinshi_dir)
         name = doujinshi_obj.name
-        if sys.version_info < (3, 0):
-            name = doujinshi_obj.name.encode('utf-8')
     else:
         name = {'title': 'nHentai HTML Viewer'}
 
     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(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(16, f'HTML Viewer has been written to "{os.path.join(doujinshi_dir, "index.html")}"')
     except Exception as e:
-        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing HTML Viewer failed ({e})')
+
+
+def move_to_folder(output_dir='.', doujinshi_obj=None, file_type=None):
+    if not file_type:
+        raise RuntimeError('no file_type specified')
+
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
+
+    for fn in os.listdir(doujinshi_dir):
+        file_path = os.path.join(doujinshi_dir, fn)
+        _, ext = os.path.splitext(file_path)
+        if ext in ['.pdf', '.cbz']:
+            continue
+
+        if os.path.isfile(file_path):
+            try:
+                os.remove(file_path)
+            except Exception as e:
+                print(f"Error deleting file: {e}")
+
+    shutil.move(filename, os.path.join(doujinshi_dir, os.path.basename(filename)))
 
 
 def generate_main_html(output_dir='./'):
     """
-    Generate a main html to show all the contain doujinshi.
+    Generate a main html to show all the contains doujinshi.
     With a link to their `index.html`.
     Default output folder will be the CLI path.
     """
@@ -138,7 +206,7 @@ def generate_main_html(output_dir='./'):
         files.sort()
 
         if 'index.html' in files:
-            logger.info('Add doujinshi \'{}\''.format(folder))
+            logger.info(f'Add doujinshi "{folder}"')
         else:
             continue
 
@@ -148,64 +216,84 @@ 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('None index.html found, --gen-main paused.')
+        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', 'wb') as f:
-            with open('./main.html', 'w') as f:
+            f.write(data.encode('utf-8'))
-                f.write(data)
+        shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
-        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(
+        output_dir = output_dir[:-1] if output_dir.endswith('/') else output_dir
-            15, 'Main Viewer has been write to \'{0}main.html\''.format(output_dir))
+        logger.log(16, f'Main Viewer has been written to "{output_dir}/main.html"')
     except Exception as e:
-        logger.warning('Writen Main Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing Main Viewer failed ({e})')
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
-    if doujinshi_obj is not None:
+
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
+
+    if os.path.exists(f'{doujinshi_dir}.{file_type}') and not regenerate:
+        logger.info(f'Skipped {file_type} file generation: {doujinshi_dir}.{file_type} already exists')
+        return
+
+    if file_type == 'cbz':
+        file_list = os.listdir(doujinshi_dir)
+        file_list.sort()
+
+        logger.info(f'Writing CBZ file to path: {filename}')
+        with zipfile.ZipFile(filename, 'w') as cbz_pf:
+            for image in file_list:
+                image_path = os.path.join(doujinshi_dir, image)
+                cbz_pf.write(image_path, image)
+
+        logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
+    elif file_type == 'pdf':
+        try:
+            import img2pdf
+
+            """Write images to a PDF file using img2pdf."""
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.webp'))]
+            file_list.sort()
+
+            logger.info(f'Writing PDF file to path: {filename}')
+            with open(filename, 'wb') as pdf_f:
+                full_path_list = (
+                    [os.path.join(doujinshi_dir, image) for image in file_list]
+                )
+                pdf_f.write(img2pdf.convert(full_path_list, rotation=img2pdf.Rotation.ifvalid))
+
+            logger.log(16, f'PDF file has been written to "{filename}"')
+
+        except ImportError:
+            logger.error("Please install img2pdf package by using pip.")
+
+
+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(' '). 
+    """
+    # maybe you can use `--format` to select a suitable filename
+
+    if not _truncate_only:
+        ban_chars = '\\\'/:,;*?"<>|\t\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b'
+        filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
+        filename = ' '.join(filename.split())
+
+        while filename.endswith('.'):
+            filename = filename[:-1]
     else:
-        cbz_filename = './doujinshi.cbz'
+        filename = s
-        doujinshi_dir = '.'
 
-    file_list = os.listdir(doujinshi_dir)
+    # limit `length` chars
-    file_list.sort()
+    if len(filename) >= length:
-
+        filename = filename[:length - 1] + u'…'
-    logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
-    with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
-        for image in file_list:
-            image_path = os.path.join(doujinshi_dir, image)
-            cbz_pf.write(image_path, image)
-
-    if rm_origin_dir:
-        shutil.rmtree(doujinshi_dir, ignore_errors=True)
-
-    logger.log(15, 'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir))
-
-
-def format_filename(s):
-    """Take a string and return a valid filename constructed from the string.
-Uses a whitelist approach: any characters not present in valid_chars are
-removed. Also spaces are replaced with underscores.
-
-Note: this method may produce invalid filenames such as ``, `.` or `..`
-When I use this method I prepend a date string like '2009_01_15_19_46_32_'
-and append a file extension like '.txt', so I avoid the potential of using
-an invalid filename.
-
-"""
-    valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
-    filename = ''.join(c for c in s if c in valid_chars)
-    if len(filename) > 100:
-        filename = filename[:100] + '...]'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
@@ -214,7 +302,50 @@ an invalid filename.
 
 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 []
+
+    page_list = []
+    for i in page_string.split(','):
+        if '-' in i:
+            start, end = i.split('-')
+            if not (start.isdigit() and end.isdigit()):
+                raise Exception('Invalid page number')
+            page_list.extend(list(range(int(start), int(end) + 1)))
+        else:
+            if not i.isdigit():
+                raise Exception('Invalid page number')
+            page_list.append(int(i))
+
+    return page_list
+
+
+def generate_metadata_file(output_dir, doujinshi_obj):
+
+    info_txt_path = os.path.join(output_dir, doujinshi_obj.filename, 'info.txt')
+
+    f = open(info_txt_path, 'w', encoding='utf-8')
+
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
+              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
+              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'DATE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
+                      'LANGUAGE', 'TAGS', 'URL', 'PAGES']
+
+    for i in range(len(fields)):
+        f.write(f'{fields[i]}: ')
+        if fields[i] in special_fields:
+            f.write(str(doujinshi_obj.table[special_fields.index(fields[i])][1]))
+        f.write('\n')
+
+    f.close()
+    logger.log(16, f'Metadata Info has been written to "{info_txt_path}"')
 
 
 class DB(object):

nhentai/viewer/main.css

@@ -148,7 +148,7 @@ blockquote {
   -webkit-user-select: none; /* Safari */
   -khtml-user-select: none; /* Konqueror HTML */
   -moz-user-select: none; /* Old versions of Firefox */
-  ms-user-select: none; /* Internet Explorer/Edge */
+  -ms-user-select: none; /* Internet Explorer/Edge */
   user-select: none;
 }
 
@@ -157,7 +157,7 @@ blockquote {
   padding: 5px 0px 5px 15px;
   text-decoration: none;
   font-size: 15px;
-  color: #0d0d0d9;
+  color: #0d0d0d;
   display: block;
   text-align: left;
 }
@@ -329,4 +329,4 @@ html.theme-black .gallery:hover .caption {
 html.theme-black .caption {
     background-color: #404040;
     color: #d9d9d9
-}
+}

nhentai/viewer/main.js

@@ -139,7 +139,7 @@ function filter_searcher(){
 					break
 			}
 		}
-		if (verifier){doujinshi_id.push(data[i].Folder);}
+		if (verifier){doujinshi_id.push(data[i].Folder.replace("_", " "));}
 	}
 	var gallery = document.getElementsByClassName("gallery-favorite");
 	for (var i = 0; i < gallery.length; i++){
@@ -174,4 +174,4 @@ function tag_maker(data){
 			document.getElementById("tags").appendChild(node);
 		}
 	}
-}
+}

nhentai/viewer/minimal/index.html

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

nhentai/viewer/minimal/scripts.js

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

nhentai/viewer/minimal/styles.css

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

poetry.lock

@@ -0,0 +1,331 @@
+# This file is automatically @generated by Poetry 1.8.4 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 = "4.11.2"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.6.0"
+files = [
+    {file = "beautifulsoup4-4.11.2-py3-none-any.whl", hash = "sha256:0e79446b10b3ecb499c1556f7e228a53e64a2bfcebd455f370d8927cb5b59e39"},
+    {file = "beautifulsoup4-4.11.2.tar.gz", hash = "sha256:bc4bdda6717de5a2987436fb8d72f45dc90dd856bdfd512a1314ce90349a0106"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "certifi"
+version = "2024.7.4"
+description = "Python package for providing Mozilla's CA Bundle."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"},
+    {file = "certifi-2024.7.4.tar.gz", hash = "sha256:5a1e7645bc0ec61a09e26c36f6106dd4cf40c6db3a1fb6352b0244e7fb057c7b"},
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.0.1"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+optional = false
+python-versions = "*"
+files = [
+    {file = "charset-normalizer-3.0.1.tar.gz", hash = "sha256:ebea339af930f8ca5d7a699b921106c6e29c617fe9606fa7baa043c1cdae326f"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:88600c72ef7587fe1708fd242b385b6ed4b8904976d5da0893e31df8b3480cb6"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c75ffc45f25324e68ab238cb4b5c0a38cd1c3d7f1fb1f72b5541de469e2247db"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db72b07027db150f468fbada4d85b3b2729a3db39178abf5c543b784c1254539"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62595ab75873d50d57323a91dd03e6966eb79c41fa834b7a1661ed043b2d404d"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ff6f3db31555657f3163b15a6b7c6938d08df7adbfc9dd13d9d19edad678f1e8"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:772b87914ff1152b92a197ef4ea40efe27a378606c39446ded52c8f80f79702e"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70990b9c51340e4044cfc394a81f614f3f90d41397104d226f21e66de668730d"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:292d5e8ba896bbfd6334b096e34bffb56161c81408d6d036a7dfa6929cff8783"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:2edb64ee7bf1ed524a1da60cdcd2e1f6e2b4f66ef7c077680739f1641f62f555"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:31a9ddf4718d10ae04d9b18801bd776693487cbb57d74cc3458a7673f6f34639"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:44ba614de5361b3e5278e1241fda3dc1838deed864b50a10d7ce92983797fa76"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:12db3b2c533c23ab812c2b25934f60383361f8a376ae272665f8e48b88e8e1c6"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c512accbd6ff0270939b9ac214b84fb5ada5f0409c44298361b2f5e13f9aed9e"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-win32.whl", hash = "sha256:502218f52498a36d6bf5ea77081844017bf7982cdbe521ad85e64cabee1b608b"},
+    {file = "charset_normalizer-3.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:601f36512f9e28f029d9481bdaf8e89e5148ac5d89cffd3b05cd533eeb423b59"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0298eafff88c99982a4cf66ba2efa1128e4ddaca0b05eec4c456bbc7db691d8d"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a8d0fc946c784ff7f7c3742310cc8a57c5c6dc31631269876a88b809dbeff3d3"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:87701167f2a5c930b403e9756fab1d31d4d4da52856143b609e30a1ce7160f3c"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14e76c0f23218b8f46c4d87018ca2e441535aed3632ca134b10239dfb6dadd6b"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c0a590235ccd933d9892c627dec5bc7511ce6ad6c1011fdf5b11363022746c1"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c7fe7afa480e3e82eed58e0ca89f751cd14d767638e2550c77a92a9e749c317"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79909e27e8e4fcc9db4addea88aa63f6423ebb171db091fb4373e3312cb6d603"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ac7b6a045b814cf0c47f3623d21ebd88b3e8cf216a14790b455ea7ff0135d18"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:72966d1b297c741541ca8cf1223ff262a6febe52481af742036a0b296e35fa5a"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f9d0c5c045a3ca9bedfc35dca8526798eb91a07aa7a2c0fee134c6c6f321cbd7"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:5995f0164fa7df59db4746112fec3f49c461dd6b31b841873443bdb077c13cfc"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4a8fcf28c05c1f6d7e177a9a46a1c52798bfe2ad80681d275b10dcf317deaf0b"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:761e8904c07ad053d285670f36dd94e1b6ab7f16ce62b9805c475b7aa1cffde6"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-win32.whl", hash = "sha256:71140351489970dfe5e60fc621ada3e0f41104a5eddaca47a7acb3c1b851d6d3"},
+    {file = "charset_normalizer-3.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:9ab77acb98eba3fd2a85cd160851816bfce6871d944d885febf012713f06659c"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:84c3990934bae40ea69a82034912ffe5a62c60bbf6ec5bc9691419641d7d5c9a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74292fc76c905c0ef095fe11e188a32ebd03bc38f3f3e9bcb85e4e6db177b7ea"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c95a03c79bbe30eec3ec2b7f076074f4281526724c8685a42872974ef4d36b72"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f4c39b0e3eac288fedc2b43055cfc2ca7a60362d0e5e87a637beac5d801ef478"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df2c707231459e8a4028eabcd3cfc827befd635b3ef72eada84ab13b52e1574d"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93ad6d87ac18e2a90b0fe89df7c65263b9a99a0eb98f0a3d2e079f12a0735837"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:59e5686dd847347e55dffcc191a96622f016bc0ad89105e24c14e0d6305acbc6"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:cd6056167405314a4dc3c173943f11249fa0f1b204f8b51ed4bde1a9cd1834dc"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:083c8d17153ecb403e5e1eb76a7ef4babfc2c48d58899c98fcaa04833e7a2f9a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:f5057856d21e7586765171eac8b9fc3f7d44ef39425f85dbcccb13b3ebea806c"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:7eb33a30d75562222b64f569c642ff3dc6689e09adda43a082208397f016c39a"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-win32.whl", hash = "sha256:95dea361dd73757c6f1c0a1480ac499952c16ac83f7f5f4f84f0658a01b8ef41"},
+    {file = "charset_normalizer-3.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:eaa379fcd227ca235d04152ca6704c7cb55564116f8bc52545ff357628e10602"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3e45867f1f2ab0711d60c6c71746ac53537f1684baa699f4f668d4c6f6ce8e14"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cadaeaba78750d58d3cc6ac4d1fd867da6fc73c88156b7a3212a3cd4819d679d"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:911d8a40b2bef5b8bbae2e36a0b103f142ac53557ab421dc16ac4aafee6f53dc"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:503e65837c71b875ecdd733877d852adbc465bd82c768a067badd953bf1bc5a3"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a60332922359f920193b1d4826953c507a877b523b2395ad7bc716ddd386d866"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:16a8663d6e281208d78806dbe14ee9903715361cf81f6d4309944e4d1e59ac5b"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:a16418ecf1329f71df119e8a65f3aa68004a3f9383821edcb20f0702934d8087"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:9d9153257a3f70d5f69edf2325357251ed20f772b12e593f3b3377b5f78e7ef8"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:02a51034802cbf38db3f89c66fb5d2ec57e6fe7ef2f4a44d070a593c3688667b"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:2e396d70bc4ef5325b72b593a72c8979999aa52fb8bcf03f701c1b03e1166918"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:11b53acf2411c3b09e6af37e4b9005cba376c872503c8f28218c7243582df45d"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-win32.whl", hash = "sha256:0bf2dae5291758b6f84cf923bfaa285632816007db0330002fa1de38bfcb7154"},
+    {file = "charset_normalizer-3.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2c03cc56021a4bd59be889c2b9257dae13bf55041a3372d3295416f86b295fb5"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:024e606be3ed92216e2b6952ed859d86b4cfa52cd5bc5f050e7dc28f9b43ec42"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4b0d02d7102dd0f997580b51edc4cebcf2ab6397a7edf89f1c73b586c614272c"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:358a7c4cb8ba9b46c453b1dd8d9e431452d5249072e4f56cfda3149f6ab1405e"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81d6741ab457d14fdedc215516665050f3822d3e56508921cc7239f8c8e66a58"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8b8af03d2e37866d023ad0ddea594edefc31e827fee64f8de5611a1dbc373174"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9cf4e8ad252f7c38dd1f676b46514f92dc0ebeb0db5552f5f403509705e24753"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e696f0dd336161fca9adbb846875d40752e6eba585843c768935ba5c9960722b"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c22d3fe05ce11d3671297dc8973267daa0f938b93ec716e12e0f6dee81591dc1"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:109487860ef6a328f3eec66f2bf78b0b72400280d8f8ea05f69c51644ba6521a"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:37f8febc8ec50c14f3ec9637505f28e58d4f66752207ea177c1d67df25da5aed"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:f97e83fa6c25693c7a35de154681fcc257c1c41b38beb0304b9c4d2d9e164479"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a152f5f33d64a6be73f1d30c9cc82dfc73cec6477ec268e7c6e4c7d23c2d2291"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:39049da0ffb96c8cbb65cbf5c5f3ca3168990adf3551bd1dee10c48fce8ae820"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-win32.whl", hash = "sha256:4457ea6774b5611f4bed5eaa5df55f70abde42364d498c5134b7ef4c6958e20e"},
+    {file = "charset_normalizer-3.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:e62164b50f84e20601c1ff8eb55620d2ad25fb81b59e3cd776a1902527a788af"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8eade758719add78ec36dc13201483f8e9b5d940329285edcd5f70c0a9edbd7f"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8499ca8f4502af841f68135133d8258f7b32a53a1d594aa98cc52013fff55678"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3fc1c4a2ffd64890aebdb3f97e1278b0cc72579a08ca4de8cd2c04799a3a22be"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d3ffdaafe92a5dc603cb9bd5111aaa36dfa187c8285c543be562e61b755f6b"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c2ac1b08635a8cd4e0cbeaf6f5e922085908d48eb05d44c5ae9eabab148512ca"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6f45710b4459401609ebebdbcfb34515da4fc2aa886f95107f556ac69a9147e"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ae1de54a77dc0d6d5fcf623290af4266412a7c4be0b1ff7444394f03f5c54e3"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b590df687e3c5ee0deef9fc8c547d81986d9a1b56073d82de008744452d6541"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ab5de034a886f616a5668aa5d098af2b5385ed70142090e2a31bcbd0af0fdb3d"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9cb3032517f1627cc012dbc80a8ec976ae76d93ea2b5feaa9d2a5b8882597579"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:608862a7bf6957f2333fc54ab4399e405baad0163dc9f8d99cb236816db169d4"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0f438ae3532723fb6ead77e7c604be7c8374094ef4ee2c5e03a3a17f1fca256c"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:356541bf4381fa35856dafa6a965916e54bed415ad8a24ee6de6e37deccf2786"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-win32.whl", hash = "sha256:39cf9ed17fe3b1bc81f33c9ceb6ce67683ee7526e65fde1447c772afc54a1bb8"},
+    {file = "charset_normalizer-3.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:0a11e971ed097d24c534c037d298ad32c6ce81a45736d31e0ff0ad37ab437d59"},
+    {file = "charset_normalizer-3.0.1-py3-none-any.whl", hash = "sha256:7e189e2e1d3ed2f4aebabd2d5b0f931e883676e51c7624826e0a4e5fe8a0bf24"},
+]
+
+[[package]]
+name = "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 = "0.27.2"
+description = "The next generation HTTP client."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0"},
+    {file = "httpx-0.27.2.tar.gz", hash = "sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2"},
+]
+
+[package.dependencies]
+anyio = "*"
+certifi = "*"
+httpcore = "==1.*"
+idna = "*"
+sniffio = "*"
+
+[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 = "3.7"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"},
+    {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"},
+]
+
+[[package]]
+name = "iso8601"
+version = "1.1.0"
+description = "Simple module to parse ISO 8601 dates"
+optional = false
+python-versions = ">=3.6.2,<4.0"
+files = [
+    {file = "iso8601-1.1.0-py3-none-any.whl", hash = "sha256:8400e90141bf792bce2634df533dc57e3bee19ea120a87bebcd3da89a58ad73f"},
+    {file = "iso8601-1.1.0.tar.gz", hash = "sha256:32811e7b81deee2063ea6d2e94f8819a86d1f3811e49d23623a41fa832bef03f"},
+]
+
+[[package]]
+name = "requests"
+version = "2.32.0"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "requests-2.32.0-py3-none-any.whl", hash = "sha256:f2c3881dddb70d056c5bd7600a4fae312b2a300e39be6a118d30b90bd27262b5"},
+    {file = "requests-2.32.0.tar.gz", hash = "sha256:fa5490319474c82ef1d2c9bc459d3652e3ae4ef4c4ebdd18a21145a47ca4b6b8"},
+]
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "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 = "2.4"
+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 = "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 = "1.26.19"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
+files = [
+    {file = "urllib3-1.26.19-py2.py3-none-any.whl", hash = "sha256:37a0344459b199fce0e80b0d3569837ec6b6937435c5244e7fd73fa6006830f3"},
+    {file = "urllib3-1.26.19.tar.gz", hash = "sha256:3e3d753a8618b86d7de333b4223005f68720bcd6a7d2bcb9fbd2229ec7c1e429"},
+]
+
+[package.extras]
+brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.8"
+content-hash = "a69dbf5dcfd6dcc5afc0fd2de4ab153841f7d210d4be60c426e332e36a79d679"

pyproject.toml

@@ -0,0 +1,22 @@
+[tool.poetry]
+name = "nhentai"
+version = "0.5.15"
+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"
+httpx = "0.27.2"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -1,5 +1,8 @@
-requests>=2.5.0
+httpx==0.27.2
-BeautifulSoup4>=4.0.0
+requests
-threadpool>=1.2.7
+soupsieve
-tabulate>=0.7.5
+setuptools
-future>=0.15.2
+BeautifulSoup4
+tabulate
+iso8601
+urllib3

setup.cfg

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

setup.py

@@ -1,6 +1,4 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
-import sys
 import codecs
 from setuptools import setup, find_packages
 from nhentai import __version__, __author__, __email__
@@ -12,8 +10,7 @@ with open('requirements.txt') as f:
 
 def long_description():
     with codecs.open('README.rst', 'rb') as readme:
-        if not sys.version_info < (3, 0, 0):
+        return readme.read().decode('utf-8')
-            return readme.read().decode('utf-8')
 
 
 setup(
@@ -23,7 +20,7 @@ setup(
 
     author=__author__,
     author_email=__email__,
-    keywords='nhentai, doujinshi',
+    keywords=['nhentai', 'doujinshi', 'downloader'],
     description='nhentai.net doujinshis downloader',
     long_description=long_description(),
     url='https://github.com/RicterZ/nhentai',

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', 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'))
+
+        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)