0.4.10

fix issue #186

.gitignore

@@ -6,3 +6,4 @@ dist/
 .python-version
 .DS_Store
 output/
+venv/

.travis.yml

@@ -3,18 +3,17 @@ os:
 
 language: python
 python:
-    - 2.7
     - 3.7
+    - 3.8
 
 install:
     - python setup.py install
 
 script:
     - echo 268642 > /tmp/test.txt
-    - nhentai --cookie "csrftoken=xIh7s9d4NB8qSLN7eJZG9064zsV84aHEYFoAU49Ib9anqmoT0pZRw6TIdayLzQuT; sessionid=un101zfgpglsyffdnsm72le4euuisp7t"
+    - nhentai --cookie "_ga=GA1.2.1651446371.1545407218; __cfduid=d0ed34dfb81167d2a51a1d6392c1768a81601380350; csrftoken=KRN0GR1ft86m3HTefpQA99pp6R1Bo7hUs5QxNGOAIuwB5g4EcJj04fwMB8QKgLaB; sessionid=7hzoowox78c90wi5ud5ibphm4axcck7c"
     - nhentai --search umaru
     - nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - nhentai --tag lolicon --sorting popular
     - nhentai -F
     - nhentai --file /tmp/test.txt
     - nhentai --id=152503,146134 --gen-main --output=/tmp/

MANIFEST.in

@@ -1,8 +1,4 @@
 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/main.html
-include nhentai/viewer/main.css
-include nhentai/viewer/main.js

README.rst

@@ -19,15 +19,30 @@ nhentai
 
 nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
 
-============
+===================
-Installation
+Manual Installation
-============
+===================
 .. code-block::
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
     python setup.py install
-    
+
+==================
+Installation (pip)
+==================
+Alternatively, install 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
+
 =====================
 Installation (Gentoo)
 =====================
@@ -50,6 +65,8 @@ Set your nhentai cookie against captcha:
 
     nhentai --cookie "YOUR COOKIE FROM nhentai.net"
 
+**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
+
 Download specified doujinshi:
 
 .. code-block:: bash
@@ -62,53 +79,20 @@ 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:
 
@@ -170,8 +154,9 @@ Other options:
       --no-html             don't generate HTML after downloading
       --gen-main            generate a main viewer contain all the doujin in the folder
       -C, --cbz             generate Comic Book CBZ File
+      -P --pdf              generate PDF file
       --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ
-                            file.
+                            or PDF file.
 
       # nHentai options
       --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
@@ -183,7 +168,7 @@ 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
     h.loli.club -> nhentai.net

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.3.8'
+__version__ = '0.4.10'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -2,7 +2,9 @@
 from __future__ import print_function
 import os
 import sys
+import json
 from optparse import OptionParser
+
 try:
     from itertools import ifilter as filter
 except ImportError:
@@ -13,17 +15,6 @@ 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?
@@ -35,10 +26,32 @@ def banner():
 ''' % __version__)
 
 
+def load_config():
+    if not os.path.exists(constant.NHENTAI_CONFIG_FILE):
+        return
+
+    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 cmd_parser():
+    load_config()
+
     parser = OptionParser('\n  nhentai --search [keyword] --download'
                           '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
-                          '\n  nhentai --file [filename]'    
+                          '\n  nhentai --file [filename]'
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
     # operation options
@@ -50,29 +63,20 @@ def cmd_parser():
     parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
     parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
                       help='search doujinshi by keyword')
-    parser.add_option('--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.')
 
     # 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='',
-                      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', dest='sorting', action='store', default='recent',
-                      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'])
-                      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')
@@ -80,7 +84,7 @@ 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', default='',
                       help='store a proxy, for example: -p \'http://127.0.0.1:1080\'')
     parser.add_option('--file',  '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
@@ -95,16 +99,24 @@ 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.')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
                       help='set cookie of nhentai to bypass Google recaptcha')
+    parser.add_option('--language', type='str', dest='language', action='store',
+                      help='set default language to parse doujinshis')
+    parser.add_option('--clean-language', dest='clean_language', action='store_true', default=False,
+                      help='set DEFAULT as language to parse doujinshis')
     parser.add_option('--save-download-history', dest='is_save_download_history', action='store_true',
                       default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
     parser.add_option('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
                       help='clean download history')
+    parser.add_option('--template', dest='viewer_template', action='store',
+                      help='set viewer template', default='')
 
     try:
         sys.argv = [unicode(i.decode(sys.stdin.encoding)) for i in sys.argv]
@@ -120,9 +132,7 @@ def cmd_parser():
         generate_html()
         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)
 
@@ -133,50 +143,50 @@ 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
-
-    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.')
+        write_config()
         exit(0)
 
-    if os.path.exists(constant.NHENTAI_PROXY):
+    if args.language is not None:
-        with open(constant.NHENTAI_PROXY, 'r') as f:
+        constant.CONFIG['language'] = args.language
-            link = f.read()
+        logger.info('Default language now set to \'{0}\''.format(args.language))
-            constant.PROXY = {'http': link, 'https': link}
+        write_config()
+        exit(0)
+        # TODO: search without language
 
     if args.proxy:
-        try:
+        proxy_url = urlparse(args.proxy)
-            if not os.path.exists(constant.NHENTAI_HOME):
+        if not args.proxy == '' and proxy_url.scheme not in ('http', 'https'):
-                os.mkdir(constant.NHENTAI_HOME)
+            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
+            exit(0)
+        else:
+            constant.CONFIG['proxy'] = {
+                'http': args.proxy,
+                'https': args.proxy,
+            }
+            logger.info('Proxy now set to \'{0}\'.'.format(args.proxy))
+            write_config()
+            exit(0)
 
-            proxy_url = urlparse(args.proxy)
+    if args.viewer_template:
-            if proxy_url.scheme not in ('http', 'https'):
+        if not args.viewer_template:
-                logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
+            args.viewer_template = 'default'
-            else:
-                with open(constant.NHENTAI_PROXY, 'w') as f:
-                    f.write(args.proxy)
 
-        except Exception as e:
+        if not os.path.exists(os.path.join(os.path.dirname(__file__),
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
+                                           'viewer/{}/index.html'.format(args.viewer_template))):
+            logger.error('Template \'{}\' does not exists'.format(args.viewer_template))
             exit(1)
+        else:
+            constant.CONFIG['template'] = args.viewer_template
+            write_config()
 
-        logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
+    # --- end set config ---
-        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)
 
@@ -189,15 +199,12 @@ def cmd_parser():
             _ = [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:
-            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)
 
-    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:
-            not args.character and not args.parody and not args.group and not args.language and not args.favorites:
         parser.print_help()
         exit(1)
 

nhentai/command.py

@@ -1,17 +1,20 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
 from __future__ import unicode_literals, print_function
+import sys
 import signal
 import platform
 import time
 
+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, 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_cbz, generate_main_html, generate_pdf, \
+    paging, check_cookie, signal_handler, DB
 
 
 def main():
@@ -19,61 +22,49 @@ def main():
     options = cmd_parser()
     logger.info('Using mirror: {0}'.format(BASE_URL))
 
-    from nhentai.constant import PROXY
+    # CONFIG['proxy'] will be changed after cmd_parser()
-    # constant.PROXY will be changed after cmd_parser()
+    if constant.CONFIG['proxy']['http']:
-    if PROXY != {}:
+        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']['http']))
-        logger.info('Using proxy: {0}'.format(PROXY))
+
+    if not constant.CONFIG['template']:
+        constant.CONFIG['template'] = 'default'
+
+    logger.info('Using viewer template "{}"'.format(constant.CONFIG['template']))
 
     # check your cookie
     check_cookie()
 
-    index = 0
     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(page=page_list)
-
-    elif options.tag:
-        doujinshis = tag_parser(options.tag, sorting=options.sorting, max_page=options.max_page)
-
-    elif options.artist:
-        index = 1
-
-    elif options.character:
-        index = 2
-
-    elif options.parody:
-        index = 3
-
-    elif options.group:
-        index = 4
-
-    elif options.language:
-        index = 5
 
     elif options.keyword:
-        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
+        if constant.CONFIG['language']:
+            logger.info('Using default language: {0}'.format(constant.CONFIG['language']))
+            options.keyword += ' language:{}'.format(constant.CONFIG['language'])
+        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=page_list,
+                                   is_page_all=options.page_all)
 
     elif not doujinshi_ids:
         doujinshi_ids = options.id
 
-    if index:
-        doujinshis = tag_parser(options.language, max_page=options.max_page, index=index)
-
     print_doujinshi(doujinshis)
     if options.is_download and doujinshis:
         doujinshi_ids = [i['id'] for i in doujinshis]
 
         if options.is_save_download_history:
             with DB() as db:
-                data = set(db.get_all())
+                data = map(int, db.get_all())
 
-            doujinshi_ids = list(set(doujinshi_ids) - data)
+            doujinshi_ids = list(set(doujinshi_ids) - set(data))
 
     if doujinshi_ids:
         for i, id_ in enumerate(doujinshi_ids):
@@ -100,10 +91,12 @@ def main():
                 with DB() as db:
                     db.add_one(doujinshi.id)
 
-            if not options.is_nohtml and not options.is_cbz:
+            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:
+                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)
@@ -121,4 +114,8 @@ signal.signal(signal.SIGINT, signal_handler)
 
 
 if __name__ == '__main__':
+    if sys.version_info < (3, 0, 0):
+        logger.error('nhentai now only support Python 3.x')
+        exit(1)
+
     main()

nhentai/constant.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 import os
+import copy
 import tempfile
 
 try:
@@ -12,17 +13,10 @@ except ImportError:
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
 __api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
-__api_suspended_SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
 DETAIL_URL = '%s/g' % BASE_URL
-SEARCH_URL = '%s/search/' % BASE_URL
+SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
-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
 LOGIN_URL = '%s/login/' % BASE_URL
@@ -33,10 +27,13 @@ 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_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
+NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
-PROXY = {}
 
-COOKIE = ''
+CONFIG = {
+    'proxy': {'http': '', 'https': ''},
+    'cookie': '',
+    'language': '',
+    'template': '',
+}

nhentai/doujinshi.py

@@ -48,6 +48,7 @@ class Doujinshi(object):
 
     def show(self):
         table = [
+            ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
             ["Characters", self.info.characters],

nhentai/downloader.py

@@ -5,11 +5,10 @@ import multiprocessing
 import signal
 
 from future.builtins import str as text
+import sys
 import os
 import requests
-import threadpool
 import time
-import multiprocessing as mp
 
 try:
     from urllib.parse import urlparse
@@ -18,10 +17,10 @@ except ImportError:
 
 from nhentai.logger import logger
 from nhentai.parser import request
-from nhentai.utils import Singleton, signal_handler
+from nhentai.utils import Singleton
 
 requests.packages.urllib3.disable_warnings()
-semaphore = mp.Semaphore()
+semaphore = multiprocessing.Semaphore(1)
 
 
 class NHentaiImageNotExistException(Exception):
@@ -133,16 +132,14 @@ class Downloader(Singleton):
         queue = [(self, url, folder) for url in queue]
 
         pool = multiprocessing.Pool(self.size, init_worker)
-
+        [pool.apply_async(download_wrapper, args=item) for item in queue]
-        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=''):
-    if semaphore.get_value():
+    if sys.platform == 'darwin' or semaphore.get_value():
         return Downloader.download_(obj, url=url, folder=folder)
     else:
         return -3, None

nhentai/parser.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 
-import sys
 import os
 import re
 import time
@@ -64,7 +63,7 @@ def _get_title_and_id(response):
     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'})
@@ -78,20 +77,20 @@ 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('You have %d favorites in %d pages.' % (count, 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:
@@ -105,32 +104,6 @@ def favorites_parser(page_range=''):
     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_))
@@ -143,7 +116,7 @@ def doujinshi_parser(id_):
 
     try:
         response = request('get', url)
-        if response.status_code in (200, ):
+        if response.status_code in (200,):
             response = response.content
         else:
             logger.debug('Slow down and retry ({}) ...'.format(id_))
@@ -178,12 +151,9 @@ 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'):
-    for _ in doujinshi_info.find_all('div', class_=''):
+        if re.search('Pages:', _.text):
-        pages = re.search('([\d]+) pages', _.text)
+            pages = _.find('span', class_='name').string
-        if pages:
-            pages = pages.group(1)
-            break
     doujinshi['pages'] = int(pages)
 
     # gain information of the doujinshi
@@ -192,7 +162,7 @@ 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)
 
@@ -202,7 +172,7 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def search_parser(keyword, sorting='date', page=1):
+def old_search_parser(keyword, sorting='date', page=1):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
 
@@ -218,96 +188,47 @@ 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('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def tag_parser(tag_name, sorting='date', max_page=1, index=0):
+def search_parser(keyword, sorting, page, is_page_all=False):
+    # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     result = []
-    tag_name = tag_name.lower()
+    if not page:
-    if ',' in tag_name:
+        page = [1]
-        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 is_page_all:
-        if sys.version_info >= (3, 0, 0):
+        url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
-            unicode_ = str
+        init_response = request('get', url.replace('%2B', '+')).json()
-        else:
+        page = range(1, init_response['num_pages']+1)
-            unicode_ = unicode
 
-        if isinstance(tag_name, (str, unicode_)):
+    total = '/{0}'.format(page[-1]) if is_page_all else ''
-            logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
+    for p in page:
-            response = request('get', url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], tag_name, sorting, p)).content
+        i = 0
-            result += _get_title_and_id(response)
+
-        else:
+        logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
-            for i in tag_name:
+        while i < 3:
-                logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, i))
+            try:
-                response = request('get',
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
-                                   url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], i, sorting, p)).content
+                                                                      'page': p, 'sort': sorting}).url
-                result += _get_title_and_id(response)
+                response = request('get', url.replace('%2B', '+')).json()
+            except Exception as e:
+                logger.critical(str(e))
+
+            break
+
+        if 'result' not in response:
+            logger.warn('No result in response in page {}'.format(p))
+            break
+
+        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.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
+            logger.warn('No results for keywords {}'.format(keyword))
-            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
 

nhentai/serializer.py

@@ -1,9 +1,10 @@
 # coding: utf-8
 import json
 import os
+from xml.sax.saxutils import escape
 
 
-def serialize(doujinshi, dir):
+def serialize_json(doujinshi, dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
     if doujinshi.info.date:
@@ -28,6 +29,51 @@ def serialize(doujinshi, dir):
         json.dump(metadata, f, separators=','':')
 
 
+def serialize_comicxml(doujinshi, dir):
+    from iso8601 import parse_date
+    with open(os.path.join(dir, 'ComicInfo.xml'), 'w') 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, '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.groups:
+        #     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']
+
+        f.write('</ComicInfo>')
+
+
+def xml_write_simple_tag(f, name, val, indent=1):
+    f.write('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
+
+
 def merge_json():
     lst = []
     output_dir = "./"

nhentai/utils.py

@@ -4,7 +4,6 @@ from __future__ import unicode_literals, print_function
 import sys
 import re
 import os
-import string
 import zipfile
 import shutil
 import requests
@@ -12,7 +11,7 @@ import sqlite3
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize, set_js_database
+from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
 
 
 def request(method, url, **kwargs):
@@ -20,9 +19,9 @@ def request(method, url, **kwargs):
     session.headers.update({
         'Referer': constant.LOGIN_URL,
         'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
-        'Cookie': constant.COOKIE
+        'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
+    return getattr(session, method)(url, proxies=constant.CONFIG['proxy'], verify=False, **kwargs)
 
 
 def check_cookie():
@@ -64,7 +63,7 @@ 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:
@@ -81,12 +80,12 @@ def generate_html(output_dir='.', doujinshi_obj=None):
 
         image_html += '<img src="{0}" class="image-item"/>\n'\
             .format(image)
-    html = readfile('viewer/index.html')
+    html = readfile('viewer/{}/index.html'.format(template))
-    css = readfile('viewer/styles.css')
+    css = readfile('viewer/{}/styles.css'.format(template))
-    js = readfile('viewer/scripts.js')
+    js = readfile('viewer/{}/scripts.js'.format(template))
 
     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')
@@ -102,9 +101,9 @@ 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 write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(15, 'HTML Viewer has been written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
     except Exception as e:
-        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
+        logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
 
 
 def generate_main_html(output_dir='./'):
@@ -150,7 +149,7 @@ def generate_main_html(output_dir='./'):
 
         image_html += element.format(FOLDER=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)
@@ -163,14 +162,16 @@ def generate_main_html(output_dir='./'):
         shutil.copy(os.path.dirname(__file__)+'/viewer/logo.png', './')
         set_js_database()
         logger.log(
-            15, 'Main Viewer has been write to \'{0}main.html\''.format(output_dir))
+            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
     except Exception as e:
-        logger.warning('Writen Main Viewer failed ({})'.format(str(e)))
+        logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=False):
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+        if write_comic_info:
+            serialize_comicxml(doujinshi_obj, doujinshi_dir)
         cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
     else:
         cbz_filename = './doujinshi.cbz'
@@ -188,24 +189,64 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     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))
+    logger.log(15, 'Comic Book CBZ file has been written to \'{0}\''.format(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)
+        )
+    else:
+        pdf_filename = './doujinshi.pdf'
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    logger.info('Writing PDF file to path: {}'.format(pdf_filename))
+    with open(pdf_filename, 'wb') as pdf_f:
+        full_path_list = (
+            [os.path.join(doujinshi_dir, image) for image in file_list]
+        )
+        pdf_f.write(img2pdf.convert(full_path_list))
+
+    if rm_origin_dir:
+        shutil.rmtree(doujinshi_dir, ignore_errors=True)
+
+    logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
+
+
+def unicode_truncate(s, length, encoding='utf-8'):
+    """https://stackoverflow.com/questions/1809531/truncating-unicode-so-it-fits-a-maximum-size-when-encoded-for-wire-transfer
+    """
+    encoded = s.encode(encoding)[:length]
+    return encoded.decode(encoding, 'ignore')
 
 
 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
+    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.
+    if filename include forbidden characters (\'/:,;*?"<>|) ,it replace space character(' '). 
+    """
+    # maybe you can use `--format` to select a suitable filename
+    ban_chars = '\\\'/:,;*?"<>|'
+    filename = s.translate(str.maketrans(ban_chars, ' '*len(ban_chars))).strip()
+    while filename.endswith('.'):
+        filename = filename[:-1]
 
-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] + '...]'
+        filename = filename[:100] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()
@@ -217,6 +258,26 @@ 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
+
+
 class DB(object):
     conn = None
     cur = None

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
-}
+}

requirements.txt

@@ -4,3 +4,4 @@ BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
 future>=0.15.2
+iso8601 >= 0.1

setup.py

@@ -23,7 +23,7 @@ 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',