update requirements

Pull/221

.gitignore

@@ -7,3 +7,4 @@ dist/
 .DS_Store
 output/
 venv/
+.vscode/

MANIFEST.in

@@ -1,8 +1,5 @@
 include README.md
 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

@@ -51,10 +51,17 @@ Installation (Gentoo)
     layman -fa glicOne
     sudo emerge net-misc/nhentai
     
+=====================
+Installation (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).*
 
@@ -63,15 +70,32 @@ 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"`
+**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:: ./images/usage.png?raw=true
+    :alt: nhentai
+    :align: center
 
 Download specified doujinshi:
 
 .. code-block:: bash
 
-    nhentai --id=123855,123866
+    nhentai --id 123855 123866 123877
 
 Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
@@ -112,30 +136,41 @@ Supported doujinshi folder formatter:
 - %t: Doujinshi name
 - %s: Doujinshi subtitle (translated name)
 - %a: Doujinshi authors' name
+- %p: Doujinshi pretty 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
+      # Operation options, control the program behaviors
       -h, --help            show this help message and exit
       -D, --download        download doujinshi (for search results)
       -S, --show            just show the doujinshi information
 
-      # Doujinshi options
+      # Doujinshi options, specify id, keyword, etc.
-      --id=ID               doujinshi ids set, e.g. 1,2,3
+      --id                  doujinshi ids set, e.g. 167680 167681 167682
       -s KEYWORD, --search=KEYWORD
                             search doujinshi by keyword
-      --tag=TAG             download doujinshi by tag
+      -F, --favorites       list or download your favorites
-      -F, --favorites       list or download your favorites.
 
-      # Multi-page options
+      # Page options, control the page to fetch / download
-      --page=PAGE           page number of search results
+      --page-all            all search results
-      --max-page=MAX_PAGE   The max page when recursive download tagged doujinshi
+      --page=PAGE, --page-range=PAGE
+                            page number of search results. e.g. 1,2-5,14
+      --sorting=SORTING     sorting of doujinshi (recent / popular /
+                            popular-[today|week])
 
-      # Download options
+      # Download options, the output directory, threads, timeout, delay, etc.
       -o OUTPUT_DIR, --output=OUTPUT_DIR
                             output dir
       -t THREADS, --threads=THREADS
@@ -144,23 +179,37 @@ 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
+      # Generate options, for generate html viewer, cbz file, pdf file, etc
       --html                generate a html viewer at current directory
       --no-html             don't generate HTML after downloading
-      --gen-main            generate a main viewer contain all the doujin in the folder
+      --gen-main            generate a main viewer contain all the doujin in the
+                            folder
       -C, --cbz             generate Comic Book CBZ File
-      -P --pdf              generate PDF file
+      -P, --pdf             generate PDF file
-      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ
+      --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ or
-                            or PDF file.
+                            PDF file
-
+      --meta                generate a metadata file in doujinshi format
-      # nHentai options
+      --regenerate-cbz      regenerate the cbz file if exists
-      --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
 
+      # nhentai options, set cookie, user-agent, language, remove caches, histories, etc
+      --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
+      --useragent=USERAGENT, --user-agent=USERAGENT
+                            set useragent to bypass Cloudflare captcha
+      --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
@@ -177,7 +226,7 @@ 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
@@ -190,14 +239,6 @@ Set `NHENTAI` env var to your nhentai mirror.
     :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

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.2'
+__version__ = '0.5.0'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,8 +1,10 @@
 # coding: utf-8
-from __future__ import print_function
+
 import os
 import sys
+import json
 from optparse import OptionParser
+
 try:
     from itertools import ifilter as filter
 except ImportError:
@@ -13,31 +15,52 @@ from nhentai import __version__
 from nhentai.utils import urlparse, 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\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
@@ -47,23 +70,24 @@ def cmd_parser():
     parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
 
     # doujinshi options
-    parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
+    parser.add_option('--id', dest='id', action='callback', callback=callback,
+                      help='doujinshi ids set, e.g. 167680 167681 167682')
     parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
                       help='search doujinshi by keyword')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
-                      help='list or download your favorites.')
+                      help='list or download your favorites')
 
     # 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('--page-range', type='string', dest='page_range', action='store',
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='',
-                      help='page range of favorites.  e.g. 1,2-5,14')
+                      help='page number of search results. e.g. 1,2-5,14')
-    parser.add_option('--sorting', dest='sorting', action='store', default='recent',
+    parser.add_option('--sorting', dest='sorting', action='store', default='popular',
                       help='sorting of doujinshi (recent / popular / popular-[today|week])',
-                      choices=['recent', 'popular', 'popular-today', 'popular-week'])
+                      choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
-    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='',
+    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')
@@ -71,11 +95,12 @@ 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('--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',
@@ -89,30 +114,34 @@ def cmd_parser():
     parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
                       help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
-                      help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
+                      help='remove downloaded doujinshi dir when generated CBZ or PDF file')
+    parser.add_option('--meta', dest='generate_metadata', action='store_true',
+                      help='generate a metadata file in doujinshi format')
+    parser.add_option('--regenerate-cbz', dest='regenerate_cbz', action='store_true', default=False,
+                      help='regenerate the cbz 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)
 
     if args.main_viewer and not args.id and not args.keyword and not args.favorites:
@@ -126,76 +155,58 @@ def cmd_parser():
         logger.info('Download history cleaned.')
         exit(0)
 
-    if os.path.exists(constant.NHENTAI_COOKIE):
+    # --- set config ---
-        with open(constant.NHENTAI_COOKIE, 'r') as f:
+    if args.cookie is not None:
-            constant.COOKIE = f.read()
+        constant.CONFIG['cookie'] = args.cookie
-
+        write_config()
-    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)
-
         logger.info('Cookie saved.')
         exit(0)
-
+    elif args.useragent is not None:
-    if os.path.exists(constant.NHENTAI_LANGUAGE) and not args.language:
+        constant.CONFIG['useragent'] = args.useragent
-        with open(constant.NHENTAI_LANGUAGE, 'r') as f:
+        write_config()
-            constant.LANGUAGE = f.read()
+        logger.info('User-Agent saved.')
-            args.language = f.read()
-
-    if args.language:
-        try:
-            if not os.path.exists(constant.NHENTAI_HOME):
-                os.mkdir(constant.NHENTAI_HOME)
-
-            with open(constant.NHENTAI_LANGUAGE, 'w') as f:
-                f.write(args.language)
-        except Exception as e:
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
-
-        logger.info('Default language now is {}.'.format(args.language))
         exit(0)
+    elif args.language is not None:
+        constant.CONFIG['language'] = args.language
+        write_config()
+        logger.info(f'Default language now set to "{args.language}"')
+        exit(0)
+        # 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:
-            link = f.read()
-            constant.PROXY = {'http': link, 'https': link}
-
-    if args.proxy:
-        try:
-            if not os.path.exists(constant.NHENTAI_HOME):
-                os.mkdir(constant.NHENTAI_HOME)
-
         proxy_url = urlparse(args.proxy)
-            if proxy_url.scheme not in ('http', 'https'):
+        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h',
-                logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
+                                                             'socks4', 'socks4a'):
-            else:
+            logger.error(f'Invalid protocol "{proxy_url.scheme}" of proxy, ignored')
-                with open(constant.NHENTAI_PROXY, 'w') as f:
-                    f.write(args.proxy)
-
-        except Exception as e:
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
-
-        logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
             exit(0)
+        else:
+            constant.CONFIG['proxy'] = {
+                'http': args.proxy,
+                'https': args.proxy,
+            }
+            logger.info(f'Proxy now set to "{args.proxy}"')
+            write_config()
+            exit(0)
+
+    if args.viewer_template is not None:
+        if not args.viewer_template:
+            args.viewer_template = 'default'
+
+        if not os.path.exists(os.path.join(os.path.dirname(__file__),
+                                           f'viewer/{args.viewer_template}/index.html')):
+            logger.error(f'Template "{args.viewer_template}" does not exists')
+            exit(1)
+        else:
+            constant.CONFIG['template'] = args.viewer_template
+            write_config()
+
+    # --- end set config ---
 
     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)
 
-    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()]
@@ -217,4 +228,8 @@ def cmd_parser():
         logger.critical('Maximum number of used threads is 15')
         exit(1)
 
+    if args.dryrun and (args.is_cbz or args.is_pdf):
+        logger.critical('Cannot generate PDF or CBZ during dry-run')
+        exit(1)
+
     return args

nhentai/command.py

@@ -1,28 +1,38 @@
-#!/usr/bin/env python2.7
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+import sys
 import signal
 import platform
-import time
+import urllib3.exceptions
 
+from nhentai import constant
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser
+from nhentai.parser import doujinshi_parser, search_parser, legacy_search_parser, print_doujinshi, favorites_parser
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, check_cookie, signal_handler, DB
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
+    paging, check_cookie, signal_handler, DB
 
 
 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:
+        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()
@@ -31,18 +41,22 @@ def main():
     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(page=page_list)
 
     elif options.keyword:
-        from nhentai.constant import LANGUAGE
+        if constant.CONFIG['language']:
-        if LANGUAGE:
+            logger.info(f'Using default language: {constant.CONFIG["language"]}')
-            logger.info('Using deafult language: {0}'.format(LANGUAGE))
+            options.keyword += f' language:{constant.CONFIG["language"]}'
-            options.keyword += ', language:{}'.format(LANGUAGE)
+
-        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
+        _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 not doujinshi_ids:
         doujinshi_ids = options.id
@@ -53,37 +67,35 @@ def main():
 
     if options.is_save_download_history:
         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,
                                 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
-            doujinshi.download()
+                doujinshi.download(regenerate_cbz=options.regenerate_cbz)
+
+            if options.generate_metadata:
+                table = doujinshi.table
+                generate_metadata_file(options.output_dir, table, doujinshi)
+
             if options.is_save_download_history:
                 with DB() as db:
                     db.add_one(doujinshi.id)
 
             if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
-                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)
             elif options.is_pdf:
@@ -93,14 +105,21 @@ def main():
             generate_main_html(options.output_dir)
 
         if not platform.system() == 'Windows':
-            logger.log(15, '🍻 All done.')
+            logger.log(16, '🍻 All done.')
         else:
-            logger.log(15, 'All done.')
+            logger.log(16, 'All done.')
 
     else:
-        [doujinshi.show() for doujinshi in doujinshi_list]
+        for doujinshi_id in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(doujinshi_id)
+            if doujinshi_info:
+                doujinshi = Doujinshi(name_format=options.name_format, **doujinshi_info)
+            else:
+                continue
+            doujinshi.show()
 
 
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 signal.signal(signal.SIGINT, signal_handler)
 
 if __name__ == '__main__':

nhentai/constant.py

@@ -1,37 +1,40 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 import os
 import tempfile
 
-try:
+from urllib.parse import urlparse
-    from urlparse import urlparse
-except ImportError:
-    from urllib.parse import urlparse
 
 
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-__api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
+DETAIL_URL = f'{BASE_URL}/g'
+LEGACY_SEARCH_URL = f'{BASE_URL}/search/'
+SEARCH_URL = f'{BASE_URL}/api/galleries/search'
 
-DETAIL_URL = '%s/g' % BASE_URL
+TAG_API_URL = f'{BASE_URL}/api/galleries/tagged'
-SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+LOGIN_URL = f'{BASE_URL}/login/'
+CHALLENGE_URL = f'{BASE_URL}/challenge'
+FAV_URL = f'{BASE_URL}/favorites/'
 
-
+IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
-TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
-LOGIN_URL = '%s/login/' % BASE_URL
-CHALLENGE_URL = '%s/challenge' % BASE_URL
-FAV_URL = '%s/favorites/' % BASE_URL
-
-u = urlparse(BASE_URL)
-IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
 
 NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
-NHENTAI_PROXY = os.path.join(NHENTAI_HOME, 'proxy')
-NHENTAI_COOKIE = os.path.join(NHENTAI_HOME, 'cookie')
-NHENTAI_LANGUAGE = os.path.join(NHENTAI_HOME, 'language')
 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 = {
-LANGUAGE = ''
+    'proxy': {'http': '', 'https': ''},
+    'cookie': '',
+    'language': '',
+    'template': '',
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
+}
+
+LANGUAGE_ISO = {
+    'english': 'en',
+    'chinese': 'zh',
+    'japanese': 'ja',
+    'translated': 'translated'
+}

nhentai/doujinshi.py

@@ -1,7 +1,6 @@
 # coding: utf-8
-from __future__ import print_function, unicode_literals
+
 from tabulate import tabulate
-from future.builtins import range
 
 from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
@@ -27,27 +26,28 @@ class DoujinshiInfo(dict):
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
+    def __init__(self, name=None, pretty_name=None, id=None, img_id=None,
+                 ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
+        self.pretty_name = pretty_name
         self.id = id
         self.img_id = img_id
         self.ext = ext
         self.pages = pages
         self.downloader = None
-        self.url = '%s/%d' % (DETAIL_URL, self.id)
+        self.url = f'{DETAIL_URL}/{self.id}'
         self.info = DoujinshiInfo(**kwargs)
 
-        name_format = name_format.replace('%i', str(self.id))
+        name_format = name_format.replace('%i', format_filename(str(self.id)))
-        name_format = name_format.replace('%a', self.info.artists)
+        name_format = name_format.replace('%a', format_filename(self.info.artists))
-        name_format = name_format.replace('%t', self.name)
-        name_format = name_format.replace('%s', self.info.subtitle)
-        self.filename = format_filename(name_format)
 
-    def __repr__(self):
+        name_format = name_format.replace('%t', format_filename(self.name))
-        return '<Doujinshi: {0}>'.format(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)
 
-    def show(self):
+        self.table = [
-        table = [
+            ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
             ["Characters", self.info.characters],
@@ -57,26 +57,24 @@ class Doujinshi(object):
             ["URL", self.url],
             ["Pages", self.pages],
         ]
-        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
 
-    def download(self):
+    def __repr__(self):
-        logger.info('Starting to download doujinshi: %s' % self.name)
+        return f'<Doujinshi: {self.name}>'
+
+    def show(self):
+        logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
+
+    def download(self, regenerate_cbz=False):
+        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]]))
-            '''
 
+            self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
         else:
             logger.critical('Downloader has not been loaded')
 
@@ -88,4 +86,4 @@ if __name__ == '__main__':
     try:
         test.download()
     except Exception as e:
-        print('Exception: %s' % str(e))
+        print(f'Exception: {e}')

nhentai/downloader.py

@@ -1,25 +1,22 @@
 # coding: utf-
-from __future__ import unicode_literals, print_function
 
 import multiprocessing
 import signal
 
-from future.builtins import str as text
 import sys
 import os
 import requests
 import time
+import urllib3.exceptions
 
-try:
+from urllib.parse import urlparse
-    from urllib.parse import urlparse
+from nhentai import constant
-except ImportError:
-    from urlparse import urlparse
-
 from nhentai.logger import logger
 from nhentai.parser import request
 from nhentai.utils import Singleton
 
-requests.packages.urllib3.disable_warnings()
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 semaphore = multiprocessing.Semaphore(1)
 
 
@@ -27,6 +24,21 @@ class NHentaiImageNotExistException(Exception):
     pass
 
 
+def download_callback(result):
+    result, data = result
+    if result == 0:
+        logger.warning('fatal errors occurred, ignored')
+    elif result == -1:
+        logger.warning(f'url {data} return status code 404')
+    elif result == -2:
+        logger.warning('Ctrl-C pressed, exiting sub processes ...')
+    elif result == -3:
+        # workers won't be run, just pass
+        pass
+    else:
+        logger.log(16, f'{data} downloaded successfully')
+
+
 class Downloader(Singleton):
 
     def __init__(self, path='', size=5, timeout=30, delay=0):
@@ -35,24 +47,25 @@ class Downloader(Singleton):
         self.timeout = timeout
         self.delay = delay
 
-    def download_(self, url, folder='', filename='', retried=0):
+    def download(self, url, folder='', filename='', retried=0, proxy=None):
         if self.delay:
             time.sleep(self.delay)
-        logger.info('Starting to download {0} ...'.format(url))
+        logger.info(f'Starting to download {url} ...')
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
+
+        save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
         try:
-            if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
+            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'Ignored exists file: {save_file_path}')
-                                                                                extension)))
                 return 1, url
 
             response = None
-            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
+            with open(save_file_path, "wb") as f:
                 i = 0
                 while i < 10:
                     try:
-                        response = request('get', url, stream=True, timeout=self.timeout)
+                        response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
                         if response.status_code != 200:
                             raise NHentaiImageNotExistException
 
@@ -77,13 +90,14 @@ class Downloader(Singleton):
 
         except (requests.HTTPError, requests.Timeout) as e:
             if retried < 3:
-                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
+                logger.warning(f'Warning: {e}, retrying({retried}) ...')
-                return 0, self.download_(url=url, folder=folder, filename=filename, retried=retried+1)
+                return 0, self.download(url=url, folder=folder, filename=filename,
+                                        retried=retried+1, proxy=proxy)
             else:
                 return 0, None
 
         except NHentaiImageNotExistException as e:
-            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            os.remove(save_file_path)
             return -1, url
 
         except Exception as e:
@@ -97,39 +111,28 @@ class Downloader(Singleton):
 
         return 1, url
 
-    def _download_callback(self, result):
+    def start_download(self, queue, folder='', regenerate_cbz=False):
-        result, data = result
+        if not isinstance(folder, (str, )):
-        if result == 0:
-            logger.warning('fatal errors occurred, ignored')
-            # exit(1)
-        elif result == -1:
-            logger.warning('url {} return status code 404'.format(data))
-        elif result == -2:
-            logger.warning('Ctrl-C pressed, exiting sub processes ...')
-        elif result == -3:
-            # workers wont be run, just pass
-            pass
-        else:
-            logger.log(15, '{0} downloaded successfully'.format(data))
-
-    def download(self, queue, folder=''):
-        if not isinstance(folder, text):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
+        if os.path.exists(folder + '.cbz'):
+            if not regenerate_cbz:
+                logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
+                return
+
         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))
 
         else:
-            logger.warn('Path \'{0}\' already exist.'.format(folder))
+            logger.warning(f'Path "{folder}" already exist.')
 
-        queue = [(self, url, folder) for url in queue]
+        queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
 
         pool = multiprocessing.Pool(self.size, init_worker)
         [pool.apply_async(download_wrapper, args=item) for item in queue]
@@ -138,9 +141,9 @@ class Downloader(Singleton):
         pool.join()
 
 
-def download_wrapper(obj, url, folder=''):
+def download_wrapper(obj, url, folder='', proxy=None):
     if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download_(obj, url=url, folder=folder)
+        return Downloader.download(obj, url=url, folder=folder, proxy=proxy)
     else:
         return -3, None
 
@@ -149,7 +152,7 @@ def init_worker():
     signal.signal(signal.SIGINT, subprocess_signal)
 
 
-def subprocess_signal(signal, frame):
+def subprocess_signal(sig, frame):
     if semaphore.acquire(timeout=1):
         logger.warning('Ctrl-C pressed, exiting sub processes ...')
 

nhentai/logger.py

@@ -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

@@ -1,7 +1,5 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
-import sys
 import os
 import re
 import time
@@ -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,
@@ -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 +76,73 @@ def favorites_parser(page_range=''):
         return []
     pages = int(count / 25)
 
+    if page:
+        page_range_list = page
+    else:
         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'):
             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):
-    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,):
+        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_))
+            logger.debug(f'Slow down and retry ({id_}) ...')
             time.sleep(1)
             return doujinshi_parser(str(id_))
 
     except Exception as e:
-        logger.warn('Error: {}, ignored'.format(str(e)))
+        logger.warning(f'Error: {e}, ignored')
         return None
 
     html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
+    pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
     subtitle = doujinshi_info.find('h2')
 
     doujinshi['name'] = title
+    doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+                       doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
@@ -178,6 +156,7 @@ def doujinshi_parser(id_):
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
 
+    pages = 0
     for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
         if re.search('Pages:', _.text):
             pages = _.find('span', class_='name').string
@@ -199,13 +178,38 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def old_search_parser(keyword, sorting='date', page=1):
+def legacy_search_parser(keyword, sorting, page, is_page_all=False):
-    logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
+    logger.debug(f'Searching doujinshis of keyword {keyword}')
-    response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
+
+    response = None
+    result = []
+
+    if is_page_all and len(page) != 1:
+        # `--page-all` option will override the `--page` option
+        page = [1]
+
+    for p in page:
+        logger.debug(f'Fetching page {p} ...')
+        response = request('get', url=constant.LEGACY_SEARCH_URL,
+                           params={'q': keyword, 'page': p, 'sort': sorting}).content
+        result.extend(_get_title_and_id(response))
 
-    result = _get_title_and_id(response)
     if not result:
-        logger.warn('Not found anything of keyword {}'.format(keyword))
+        logger.warning(f'Not found anything of keyword {keyword} on page {page[0]}')
+        return result
+
+    if is_page_all:
+        html = BeautifulSoup(response, 'lxml')
+        pagination = html.find(attrs={'class': 'pagination'})
+        next_page = pagination.find(attrs={'class': 'next'})
+
+        if next_page is None:
+            logger.warning('Reached the last page')
+            return result
+        else:
+            next_page = re.findall('page=([0-9]+)', next_page.attrs['href'])[0]
+            result.extend(legacy_search_parser(keyword, sorting, [next_page], is_page_all))
+            return result
 
     return result
 
@@ -215,47 +219,64 @@ def print_doujinshi(doujinshi_list):
         return
     doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
-    logger.info('Search Result\n' +
+    logger.info(f'Search Result || Found {doujinshi_list.__len__()} doujinshis')
-                tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+    print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def search_parser(keyword, sorting, page):
+def search_parser(keyword, sorting, page, is_page_all=False):
-    logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
-    # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     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
-    while i < 5:
+
+        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': page, 'sort': sorting}).url
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+                                                                      'page': p, 'sort': sorting}).url
                 response = request('get', url.replace('%2B', '+')).json()
             except Exception as e:
                 logger.critical(str(e))
-
+                response = None
             break
 
-    if 'result' not in response:
+        if response is None or 'result' not in response:
-        raise Exception('No result in response')
+            logger.warning(f'No result in response in page {p}')
+            if not_exists_persist is True:
+                break
+            continue
 
         for row in response['result']:
             title = row['title']['english']
             title = title[:85] + '..' if len(title) > 85 else title
             result.append({'id': row['id'], 'title': title})
 
+        not_exists_persist = False
         if not result:
-        logger.warn('No results for keywords {}'.format(keyword))
+            logger.warning(f'No results for keywords {keyword}')
 
     return result
 
 
 def __api_suspended_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
+        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:

nhentai/serializer.py

@@ -2,9 +2,10 @@
 import json
 import os
 from xml.sax.saxutils import escape
+from nhentai.constant import LANGUAGE_ISO
 
 
-def serialize_json(doujinshi, dir):
+def serialize_json(doujinshi, output_dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
     if doujinshi.info.date:
@@ -25,13 +26,13 @@ def serialize_json(doujinshi, dir):
     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_comicxml(doujinshi, dir):
+def serialize_comic_xml(doujinshi, output_dir):
     from iso8601 import parse_date
-    with open(os.path.join(dir, 'ComicInfo.xml'), 'w') as f:
+    with open(os.path.join(output_dir, 'ComicInfo.xml'), 'w', encoding="utf-8") as f:
         f.write('<?xml version="1.0" encoding="utf-8"?>\n')
         f.write('<ComicInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" '
                 'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">\n')
@@ -45,7 +46,8 @@ def serialize_comicxml(doujinshi, dir):
         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
         xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
 
-        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and 'full color' in doujinshi.info.tags else 'Yes')
+        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and
+                             'full color' in doujinshi.info.tags else 'Yes')
 
         if doujinshi.info.date:
             dt = parse_date(doujinshi.info.date)
@@ -59,19 +61,20 @@ def serialize_comicxml(doujinshi, dir):
         if doujinshi.info.tags:
             xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
         if doujinshi.info.artists:
-            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in doujinshi.info.artists.split(',')]))
+            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in
-        # if doujinshi.info.groups:
+                                                          doujinshi.info.artists.split(',')]))
-        #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
+
         if doujinshi.info.languages:
             languages = [i.strip() for i in doujinshi.info.languages.split(',')]
             xml_write_simple_tag(f, 'Translated', 'Yes' if 'translated' in languages else 'No')
-            [xml_write_simple_tag(f, 'Language', i) for i in languages if i != 'translated']
+            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGE_ISO[i]) for i in languages
+             if (i != 'translated' and i in LANGUAGE_ISO)]
 
         f.write('</ComicInfo>')
 
 
 def xml_write_simple_tag(f, name, val, indent=1):
-    f.write('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
+    f.write(f'{" "*indent}<{name}>{escape(str(val))}</{name}>\n')
 
 
 def merge_json():
@@ -120,7 +123,7 @@ def serialize_unique(lst):
 def set_js_database():
     with open('data.js', 'w') as f:
         indexed_json = merge_json()
-        unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
+        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

@@ -1,10 +1,8 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import sys
 import re
 import os
-import string
 import zipfile
 import shutil
 import requests
@@ -12,26 +10,37 @@ import sqlite3
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
+from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
+
+
+MAX_FIELD_LENGTH = 100
 
 
 def request(method, url, **kwargs):
     session = requests.Session()
     session.headers.update({
         'Referer': constant.LOGIN_URL,
-        'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+        'User-Agent': constant.CONFIG['useragent'],
-        'Cookie': constant.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)
 
 
 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 == 503 and 'cf-browser-verification' in response.text:
+        logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
+        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):
@@ -64,7 +73,7 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None):
+def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     image_html = ''
 
     if doujinshi_obj is not None:
@@ -72,24 +81,28 @@ def generate_html(output_dir='.', doujinshi_obj=None):
     else:
         doujinshi_dir = '.'
 
+    if not os.path.exists(doujinshi_dir):
+        logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
+        try:
+            os.makedirs(doujinshi_dir)
+        except EnvironmentError as e:
+            logger.critical(e)
+
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
     for image in file_list:
         if not os.path.splitext(image)[1] in ('.jpg', '.png'):
             continue
+        image_html += f'<img src="{image}" class="image-item"/>\n'
 
-        image_html += '<img src="{0}" class="image-item"/>\n'\
+    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_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'}
 
@@ -102,14 +115,14 @@ def generate_html(output_dir='.', doujinshi_obj=None):
             with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
                 f.write(data.encode('utf-8'))
 
-        logger.log(15, 'HTML Viewer has been written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(16, f'HTML Viewer has been written to "{os.path.join(doujinshi_dir, "index.html")}"')
     except Exception as e:
-        logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing HTML Viewer failed ({e})')
 
 
 def generate_main_html(output_dir='./'):
     """
-    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 +151,7 @@ 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
 
@@ -160,20 +173,19 @@ def generate_main_html(output_dir='./'):
         else:
             with open('./main.html', 'wb') as f:
                 f.write(data.encode('utf-8'))
-        shutil.copy(os.path.dirname(__file__)+'/viewer/logo.png', './')
+        shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
         set_js_database()
-        logger.log(
+        logger.log(16, f'Main Viewer has been written to "{output_dir}main.html"')
-            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
     except Exception as e:
-        logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
+        logger.warning(f'Writing Main Viewer failed ({e})')
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=False):
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True):
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
         if write_comic_info:
-            serialize_comicxml(doujinshi_obj, doujinshi_dir)
+            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
+        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), f'{doujinshi_obj.filename}.cbz')
     else:
         cbz_filename = './doujinshi.cbz'
         doujinshi_dir = '.'
@@ -181,7 +193,7 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
-    logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
+    logger.info(f'Writing CBZ file to path: {cbz_filename}')
     with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
         for image in file_list:
             image_path = os.path.join(doujinshi_dir, image)
@@ -190,21 +202,19 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
-    logger.log(15, 'Comic Book CBZ file has been written to \'{0}\''.format(doujinshi_dir))
+    logger.log(16, f'Comic Book CBZ file has been written to "{doujinshi_dir}"')
 
 
 def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     try:
         import img2pdf
-    except ImportError:
-        logger.error("Please install img2pdf package by using pip.")
 
         """Write images to a PDF file using img2pdf."""
         if doujinshi_obj is not None:
             doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
             pdf_filename = os.path.join(
                 os.path.join(doujinshi_dir, '..'),
-            '{}.pdf'.format(doujinshi_obj.filename)
+                f'{doujinshi_obj.filename}.pdf'
             )
         else:
             pdf_filename = './doujinshi.pdf'
@@ -213,7 +223,7 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
         file_list = os.listdir(doujinshi_dir)
         file_list.sort()
 
-    logger.info('Writing PDF file to path: {}'.format(pdf_filename))
+        logger.info(f'Writing PDF file to path: {pdf_filename}')
         with open(pdf_filename, 'wb') as pdf_f:
             full_path_list = (
                 [os.path.join(doujinshi_dir, image) for image in file_list]
@@ -223,25 +233,34 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
         if rm_origin_dir:
             shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
-    logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
+        logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
+
+    except ImportError:
+        logger.error("Please install img2pdf package by using pip.")
 
 
-def format_filename(s):
+def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
-    """Take a string and return a valid filename constructed from the string.
+    """
-Uses a whitelist approach: any characters not present in valid_chars are
+    It used to be a whitelist approach allowed only alphabet and a part of symbols.
-removed. Also spaces are replaced with underscores.
+    but most doujinshi's names include Japanese 2-byte characters and these was rejected.
-
+    so it is using blacklist approach now.
-Note: this method may produce invalid filenames such as ``, `.` or `..`
+    if filename include forbidden characters (\'/:,;*?"<>|) ,it replace space character(' '). 
-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.
-
-"""
     # maybe you can use `--format` to select a suitable filename
-    valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
+
-    filename = ''.join(c for c in s if c in valid_chars)
+    if not _truncate_only:
-    if len(filename) > 100:
+        ban_chars = '\\\'/:,;*?"<>|\t'
-        filename = filename[:100] + '...]'
+        filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
+        filename = ' '.join(filename.split())
+
+        while filename.endswith('.'):
+            filename = filename[:-1]
+    else:
+        filename = s
+
+    # limit `length` chars
+    if len(filename) >= length:
+        filename = filename[:length - 1] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
@@ -253,6 +272,54 @@ def signal_handler(signal, frame):
     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, table, doujinshi_obj=None):
+    logger.info('Writing Metadata Info')
+
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    else:
+        doujinshi_dir = '.'
+
+    logger.info(doujinshi_dir)
+
+    f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
+
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'CIRCLE', 'SCANLATOR',
+              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
+              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR',
+                      'LANGUAGE', 'TAGS', 'URL', 'PAGES']
+
+    for i in range(len(fields)):
+        f.write(f'{fields[i]}: ')
+        if fields[i] in special_fields:
+            f.write(str(table[special_fields.index(fields[i])][1]))
+        f.write('\n')
+
+    f.close()
+
+
 class DB(object):
     conn = None
     cur = None

nhentai/viewer/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;
+}

requirements.txt

@@ -1,7 +1,6 @@
 requests>=2.5.0
-soupsieve<2.0
+soupsieve
 BeautifulSoup4>=4.0.0
-threadpool>=1.2.7
 tabulate>=0.7.5
-future>=0.15.2
 iso8601 >= 0.1
+urllib3

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__
@@ -11,9 +9,8 @@ with open('requirements.txt') as f:
 
 
 def long_description():
-    with codecs.open('README.rst', 'rb') as readme:
+    with codecs.open('README.rst', 'r') as readme:
-        if not sys.version_info < (3, 0, 0):
+        return readme.read()
-            return readme.read().decode('utf-8')
 
 
 setup(