0.4.12

fix bugs

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

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.5'
+__version__ = '0.4.12'
 __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')
@@ -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()
@@ -58,9 +67,9 @@ 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(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
 
@@ -29,9 +29,10 @@ NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai'
 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': '',
 }
-

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

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

nhentai/parser.py

@@ -1,5 +1,4 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import os
 import re
@@ -116,8 +115,11 @@ 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)

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
@@ -64,7 +62,7 @@ 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 +79,9 @@ 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)
@@ -226,22 +224,31 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     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.
-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()