fix bug of proxy while downloading doujinshi

Changed write_comic_info from False to True

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

@@ -67,6 +67,15 @@ Set your nhentai cookie against captcha:
 
 **NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
 
+| 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
+
 Download specified doujinshi:
 
 .. code-block:: bash

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.5'
+__version__ = '0.4.15'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-from __future__ import print_function
+
 import os
 import sys
 import json
@@ -15,17 +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?
@@ -43,7 +32,7 @@ def load_config():
 
     try:
         with open(constant.NHENTAI_CONFIG_FILE, 'r') as f:
-            constant.CONFIG = json.load(f)
+            constant.CONFIG.update(json.load(f))
     except json.JSONDecodeError:
         logger.error('Failed to load config file.')
         write_config()
@@ -87,7 +76,7 @@ def cmd_parser():
                       choices=['recent', 'popular', 'popular-today', 'popular-week'])
 
     # 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')
@@ -95,7 +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', 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\'')
     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',
@@ -126,10 +115,11 @@ def cmd_parser():
                       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]
-        print()
     except (NameError, TypeError):
         pass
     except UnicodeDecodeError:
@@ -179,6 +169,19 @@ def cmd_parser():
             logger.info('Proxy now set to \'{0}\'.'.format(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__),
+                                           '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()
+
     # --- end set config ---
 
     if args.favorites:

nhentai/command.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+
-import json
+import sys
-import os
 import signal
 import platform
 import time
@@ -13,19 +12,29 @@ from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, fav
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
-from nhentai.constant import NHENTAI_CONFIG_FILE, BASE_URL
+from nhentai.constant import BASE_URL
 from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
     paging, check_cookie, signal_handler, DB
 
 
 def main():
     banner()
+
+    if sys.version_info < (3, 0, 0):
+        logger.error('nhentai now only support Python 3.x')
+        exit(1)
+
     options = cmd_parser()
     logger.info('Using mirror: {0}'.format(BASE_URL))
 
     # CONFIG['proxy'] will be changed after cmd_parser()
-    if constant.CONFIG['proxy']:
+    if constant.CONFIG['proxy']['http']:
-        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']))
+        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']['http']))
+
+    if not constant.CONFIG['template']:
+        constant.CONFIG['template'] = 'default'
+
+    logger.info('Using viewer template "{}"'.format(constant.CONFIG['template']))
 
     # check your cookie
     check_cookie()
@@ -56,11 +65,11 @@ def main():
     if options.is_download and doujinshis:
         doujinshi_ids = [i['id'] for i in doujinshis]
 
-        if options.is_save_download_history:
+    if options.is_save_download_history:
-            with DB() as db:
+        with DB() as db:
-                data = set(db.get_all())
+            data = map(int, db.get_all())
 
-            doujinshi_ids = list(set(doujinshi_ids) - data)
+        doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
 
     if doujinshi_ids:
         for i, id_ in enumerate(doujinshi_ids):
@@ -88,7 +97,7 @@ def main():
                     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:
@@ -108,5 +117,6 @@ def main():
 
 signal.signal(signal.SIGINT, signal_handler)
 
+
 if __name__ == '__main__':
     main()

nhentai/constant.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
+
 import os
 import tempfile
 
@@ -30,8 +30,15 @@ NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
 NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
 CONFIG = {
-    'proxy': {},
+    'proxy': {'http': '', 'https': ''},
     'cookie': '',
     'language': '',
+    'template': '',
 }
 
+LANGUAGEISO ={
+    '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

nhentai/downloader.py

@@ -1,5 +1,4 @@
 # coding: utf-
-from __future__ import unicode_literals, print_function
 
 import multiprocessing
 import signal
@@ -15,6 +14,7 @@ try:
 except ImportError:
     from urlparse import urlparse
 
+from nhentai import constant
 from nhentai.logger import logger
 from nhentai.parser import request
 from nhentai.utils import Singleton
@@ -35,7 +35,7 @@ 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))
@@ -52,7 +52,7 @@ class Downloader(Singleton):
                 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
 
@@ -78,7 +78,8 @@ class Downloader(Singleton):
         except (requests.HTTPError, requests.Timeout) as e:
             if retried < 3:
                 logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), 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
 
@@ -120,16 +121,16 @@ class Downloader(Singleton):
             folder = os.path.join(self.path, folder)
 
         if not os.path.exists(folder):
-            logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
+            logger.warning('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
                 logger.critical('{0}'.format(str(e)))
 
         else:
-            logger.warn('Path \'{0}\' already exist.'.format(folder))
+            logger.warning('Path \'{0}\' already exist.'.format(folder))
 
-        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 +139,9 @@ 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
 

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
@@ -174,7 +173,7 @@ logger.setLevel(logging.DEBUG)
 if __name__ == '__main__':
     logger.log(15, 'nhentai')
     logger.info('info')
-    logger.warn('warn')
+    logger.warning('warning')
     logger.debug('debug')
     logger.error('error')
     logger.critical('critical')

nhentai/parser.py

@@ -1,5 +1,4 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import os
 import re
@@ -116,15 +115,18 @@ def doujinshi_parser(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("Doujinshi with id {0} cannot be found".format(id_))
+            return []
         else:
             logger.debug('Slow down and retry ({}) ...'.format(id_))
             time.sleep(1)
             return doujinshi_parser(str(id_))
 
     except Exception as e:
-        logger.warn('Error: {}, ignored'.format(str(e)))
+        logger.warning('Error: {}, ignored'.format(str(e)))
         return None
 
     html = BeautifulSoup(response, 'html.parser')
@@ -178,7 +180,7 @@ def old_search_parser(keyword, sorting='date', page=1):
 
     result = _get_title_and_id(response)
     if not result:
-        logger.warn('Not found anything of keyword {}'.format(keyword))
+        logger.warning('Not found anything of keyword {}'.format(keyword))
 
     return result
 
@@ -219,7 +221,7 @@ def search_parser(keyword, sorting, page, is_page_all=False):
             break
 
         if 'result' not in response:
-            logger.warn('No result in response in page {}'.format(p))
+            logger.warning('No result in response in page {}'.format(p))
             break
 
         for row in response['result']:
@@ -228,7 +230,7 @@ def search_parser(keyword, sorting, page, is_page_all=False):
             result.append({'id': row['id'], 'title': title})
 
         if not result:
-            logger.warn('No results for keywords {}'.format(keyword))
+            logger.warning('No results for keywords {}'.format(keyword))
 
     return result
 

nhentai/serializer.py

@@ -2,7 +2,7 @@
 import json
 import os
 from xml.sax.saxutils import escape
-
+from nhentai.constant import LANGUAGEISO
 
 def serialize_json(doujinshi, dir):
     metadata = {'title': doujinshi.name,
@@ -65,7 +65,8 @@ def serialize_comicxml(doujinshi, dir):
         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', LANGUAGEISO[i]) for i in languages \
+                if (i != 'translated' and i in LANGUAGEISO)]
 
         f.write('</ComicInfo>')
 

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
@@ -22,7 +20,11 @@ def request(method, url, **kwargs):
         'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
         'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.CONFIG['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():
@@ -64,7 +66,7 @@ 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:
@@ -81,9 +83,9 @@ 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_json(doujinshi_obj, doujinshi_dir)
@@ -168,7 +170,7 @@ def generate_main_html(output_dir='./'):
         logger.warning('Writing Main Viewer failed ({})'.format(str(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:
@@ -196,52 +198,61 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
 def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     try:
         import img2pdf
+        
+        """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))
+        
     except ImportError:
         logger.error("Please install img2pdf package by using pip.")
 
-    """Write images to a PDF file using img2pdf."""
+def unicode_truncate(s, length, encoding='utf-8'):
-    if doujinshi_obj is not None:
+    """https://stackoverflow.com/questions/1809531/truncating-unicode-so-it-fits-a-maximum-size-when-encoded-for-wire-transfer
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    """
-        pdf_filename = os.path.join(
+    encoded = s.encode(encoding)[:length]
-            os.path.join(doujinshi_dir, '..'),
+    return encoded.decode(encoding, 'ignore')
-            '{}.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 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.
-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)
+    ban_chars = '\\\'/:,;*?"<>|\t'
-    filename = ''.join(c for c in s if c in valid_chars)
+    filename = s.translate(str.maketrans(ban_chars, ' '*len(ban_chars))).strip()
+    filename = ' '.join(filename.split())
+    print(repr(filename))
+
+    while filename.endswith('.'):
+        filename = filename[:-1]
+
     if len(filename) > 100:
-        filename = filename[:100] + '...]'
+        filename = filename[:100] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()

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