0.2.11

Add install for Gentoo

.gitignore

@@ -4,4 +4,4 @@ build
 dist/
 *.egg-info
 .python-version
-
+.DS_Store

.travis.yml

@@ -1,15 +1,17 @@
 os:
     - linux
-    - os x
 
 language: python
 python:
     - 2.7
     - 2.6
+    - 3.3
+    - 3.4
+    - 3.5.2
 
 install:
     - python setup.py install
 
 script:
-    - nhentai --search umaru
+    - NHENTAI=https://nhentai.net nhentai --search umaru
-    - nhentai --ids=152503,146134 -t 10 --download --path=/tmp/
+    - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/

MANIFEST.in

@@ -1,2 +1,3 @@
 include README.md
 include requirements.txt
+include nhentai/doujinshi.html

README.md

@@ -7,45 +7,62 @@ nhentai
     |_| |_|_| |_|\___|_| |_|\__\__,_|_|
 
 あなたも変態。 いいね?  
+[![Build Status](https://travis-ci.org/RicterZ/nhentai.svg?branch=master)](https://travis-ci.org/RicterZ/nhentai)  
+
+🎉🎉 nhentai 现在支持 Windows 啦！
 
 由于 [http://nhentai.net](http://nhentai.net) 下载下来的种子速度很慢，而且官方也提供在线观看本子的功能，所以可以利用本脚本下载本子。
-### 安装
+
+### Installation
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
     python setup.py install
     
+### Gentoo
 
-### 用法
+    layman -fa glicOne
-+ 下载指定 id 的本子：
+    sudo emerge net-misc/nhentai
 
+### Usage
+下载指定 id 列表的本子：
+```bash
+nhentai --id=123855,123866
+```
 
-    nhentai --id=123855 --download
+下载某关键词第一页的本子：
+```bash
+nhentai --search="tomori" --page=1 --download
+```
 
+下载用户 favorites 内容：
+```bash
+nhentai --login "username:password" --download
+```
 
-+ 下载指定 id 列表的本子：
+### Options
 
+`-t, --thread`：指定下载的线程数，最多为 10 线程。  
+`--path`：指定下载文件的输出路径，默认为当前目录。  
+`--timeout`：指定下载图片的超时时间，默认为 30 秒。  
+`--proxy`：指定下载的代理，例如: http://127.0.0.1:8080/
+`--login`：nhentai 账号的“用户名:密码”组合
 
-    nhentai --ids=123855,123866 --download
+### nHentai Mirror
-    
+如果想用自建镜像下载 nhentai 的本子，需要搭建 nhentai.net 和 i.nhentai.net 的反向代理。  
-
+例如用 h.loli.club 来做反向代理的话，需要 h.loli.club 反代 nhentai.net，i.h.loli.club 反带 i.nhentai.net。  
-+ 下载某关键词第一页的本子（不推荐）：
+然后利用环境变量来下载：  
-
-
-    nhentai --search="tomori" --page=1 --download
-
-
-`-t, --thread` 指定下载的线程数，最多为 10 线程。  
-`--path` 指定下载文件的输出路径，默认为当前目录。  
-`--timeout` 指定下载图片的超时时间，默认为 30 秒。  
-`--proxy` 指定下载的代理，例如: http://127.0.0.1:8080/
 
+```bash
+NHENTAI=http://h.loli.club nhentai --id 123456
+```
 
 ![](./images/search.png)  
 ![](./images/download.png)  
+![](./images/viewer.png)  
 
 ### License  
 MIT
 
 ### あなたも変態
-![](./images/image.jpg)
+![](./images/image.jpg)

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.1.3'
+__version__ = '0.2.11'
 __author__ = 'Ricter'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,18 +1,26 @@
 # coding: utf-8
 from __future__ import print_function
+import sys
 from optparse import OptionParser
-from logger import logger
 try:
     from itertools import ifilter as filter
 except ImportError:
     pass
 
+import nhentai.constant as constant
+from nhentai.utils import urlparse, generate_html
+from nhentai.logger import logger
 
-import constant
+try:
+    reload(sys)
+    sys.setdefaultencoding(sys.stdin.encoding)
+except NameError:
+    # python3
+    pass
 
 
 def banner():
-    logger.info('''nHentai: あなたも変態。 いいね?
+    logger.info(u'''nHentai: あなたも変態。 いいね?
        _   _            _        _
  _ __ | | | | ___ _ __ | |_ __ _(_)
 | '_ \| |_| |/ _ \ '_ \| __/ _` | |
@@ -22,51 +30,84 @@ def banner():
 
 
 def cmd_parser():
-    parser = OptionParser()
+    parser = OptionParser('\n  nhentai --search [keyword] --download'
-    parser.add_option('--download', dest='is_download', action='store_true', help='download doujinshi or not')
+                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
-    parser.add_option('--id', type='int', dest='id', action='store', help='doujinshi id of nhentai')
+                          '\n\nEnvironment Variable:\n'
-    parser.add_option('--ids', type='str', dest='ids', action='store', help='doujinshi id set, e.g. 1,2,3')
+                          '  NHENTAI                 nhentai mirror url')
-    parser.add_option('--search', type='string', dest='keyword', action='store', help='keyword searched')
+    parser.add_option('--download', dest='is_download', action='store_true',
+                      help='download doujinshi (for search result)')
+    parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information')
+    parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
+    parser.add_option('--search', type='string', dest='keyword', action='store', help='search doujinshi by keyword')
     parser.add_option('--page', type='int', dest='page', action='store', default=1,
                       help='page number of search result')
-    parser.add_option('--path', type='string', dest='saved_path', action='store', default='',
+    parser.add_option('--tags', type='string', dest='tags', action='store', help='download doujinshi by tags')
-                      help='path which save the doujinshi')
+    parser.add_option('--output', 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 of download doujinshi')
     parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
                       help='timeout of download doujinshi')
     parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
                       help='use proxy, example: http://127.0.0.1:1080')
-    args, _ = parser.parse_args()
+    parser.add_option('--html', dest='html_viewer', action='store_true',
+                      help='generate a html viewer at current directory')
 
-    if args.ids:
+    parser.add_option('--login', '-l', type='str', dest='login', action='store',
-        _ = map(lambda id: id.strip(), args.ids.split(','))
+                      help='username:password pair of nhentai account')
-        args.ids = set(map(int, filter(lambda id: id.isdigit(), _)))
 
-    if args.is_download and not args.id and not args.ids and not args.keyword:
+    try:
-        logger.critical('Doujinshi id/ids is required for downloading')
+        sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
-        parser.print_help()
+    except (NameError, TypeError):
-        raise SystemExit
+        pass
+    except UnicodeDecodeError:
+        exit(0)
+
+    args, _ = parser.parse_args(sys.argv[1:])
+
+    if args.html_viewer:
+        generate_html()
+        exit(0)
+
+    if args.login:
+        try:
+            _, _ = args.login.split(':', 1)
+        except ValueError:
+            logger.error('Invalid `username:password` pair.')
+            exit(1)
+
+        if not args.is_download:
+            logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
+
+    if args.tags:
+        logger.warning('`--tags` is under construction')
+        exit(1)
 
     if args.id:
-        args.ids = (args.id, ) if not args.ids else args.ids
+        _ = map(lambda id: id.strip(), args.id.split(','))
+        args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
 
-    if not args.keyword and not args.ids:
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.login:
+        logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
-        raise SystemExit
+        exit(1)
+
+    if not args.keyword and not args.id and not args.login:
+        parser.print_help()
+        exit(1)
 
     if args.threads <= 0:
         args.threads = 1
-    elif args.threads > 10:
+
-        logger.critical('Maximum number of used threads is 10')
+    elif args.threads > 15:
-        raise SystemExit
+        logger.critical('Maximum number of used threads is 15')
+        exit(1)
 
     if args.proxy:
-        import urlparse
+        proxy_url = urlparse(args.proxy)
-        proxy_url = urlparse.urlparse(args.proxy)
         if proxy_url.scheme not in ('http', 'https'):
-            logger.error('Invalid protocol \'{}\' of proxy, ignored'.format(proxy_url.scheme))
+            logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
         else:
-            constant.PROXY = {proxy_url.scheme: args.proxy}
+            constant.PROXY = {'http': args.proxy, 'https': args.proxy}
 
     return args

nhentai/command.py

@@ -1,50 +1,66 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
+from __future__ import unicode_literals, print_function
 import signal
-from cmdline import cmd_parser, banner
+import platform
-from parser import doujinshi_parser, search_parser, print_doujinshi
+
-from doujinshi import Doujinshi
+from nhentai.cmdline import cmd_parser, banner
-from downloader import Downloader
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_parser
-from logger import logger
+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
 
 
 def main():
     banner()
+    logger.info('Using mirror: {0}'.format(BASE_URL))
     options = cmd_parser()
 
     doujinshi_ids = []
     doujinshi_list = []
 
+    if options.login:
+        username, password = options.login.split(':', 1)
+        logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password)))
+        for doujinshi_info in login_parser(username=username, password=password):
+            doujinshi_list.append(Doujinshi(**doujinshi_info))
+
     if options.keyword:
         doujinshis = search_parser(options.keyword, options.page)
         print_doujinshi(doujinshis)
         if options.is_download:
             doujinshi_ids = map(lambda d: d['id'], doujinshis)
     else:
-        doujinshi_ids = options.ids
+        doujinshi_ids = options.id
 
     if doujinshi_ids:
-        for id in doujinshi_ids:
+        for id_ in doujinshi_ids:
-            doujinshi_info = doujinshi_parser(id)
+            doujinshi_info = doujinshi_parser(id_)
             doujinshi_list.append(Doujinshi(**doujinshi_info))
-    else:
-        raise SystemExit
 
-    if options.is_download:
+    if not options.is_show:
-        downloader = Downloader(path=options.saved_path,
+        downloader = Downloader(path=options.output_dir,
                                 thread=options.threads, timeout=options.timeout)
+
         for doujinshi in doujinshi_list:
             doujinshi.downloader = downloader
             doujinshi.download()
-    else:
+            generate_html(options.output_dir, doujinshi)
-        map(lambda doujinshi: doujinshi.show(), doujinshi_list)
 
-    logger.log(15, u'🍺 All done.')
+        if not platform.system() == 'Windows':
+            logger.log(15, '🍺 All done.')
+        else:
+            logger.log(15, 'All done.')
+
+    else:
+        [doujinshi.show() for doujinshi in doujinshi_list]
 
 
 def signal_handler(signal, frame):
     logger.error('Ctrl-C signal received. Quit.')
-    raise SystemExit
+    exit(1)
 
 
 signal.signal(signal.SIGINT, signal_handler)

nhentai/constant.py

@@ -1,6 +1,16 @@
-SCHEMA = 'http://'
+# coding: utf-8
-URL = '%snhentai.net' % SCHEMA
+from __future__ import unicode_literals, print_function
-DETAIL_URL = '%s/g' % URL
+import os
-SEARCH_URL = '%s/search/' % URL
+from nhentai.utils import urlparse
-IMAGE_URL = '%si.nhentai.net/galleries' % SCHEMA
+
+BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
+
+DETAIL_URL = '%s/g' % BASE_URL
+SEARCH_URL = '%s/search/' % BASE_URL
+LOGIN_URL = '%s/login/' % BASE_URL
+FAV_URL = '%s/favorites/' % BASE_URL
+
+u = urlparse(BASE_URL)
+IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
+
 PROXY = {}

nhentai/doujinshi.html

@@ -0,0 +1,126 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>{TITLE}</title>
+    <style>
+        html, body {{
+            background-color: #e8e6e6;
+            height: 100%;
+            padding: 0;
+            margin: 0;
+            overflow: hidden;
+        }}
+
+        .container img {{
+            display: block;
+            width: 100%;
+            margin: 30px 0;
+            padding:  10px;
+            cursor: pointer;
+        }}
+
+        .container {{
+            height: 100%;
+            overflow: scroll;
+            background: #e8e6e6;
+            width: 200px;
+            padding: 30px;
+            float: left;
+        }}
+
+        .image {{
+            margin-left: 260px;
+            height: 100%;
+            background: #222;
+            text-align: center;
+        }}
+
+        .image img {{
+            height: 100%;
+        }}
+
+        .i a {{
+            display: block;
+            position: absolute;
+            top: 0;
+            width: 50%;
+            height: 100%;
+        }}
+
+        .i {{
+            position: relative;
+            height: 100%;
+        }}
+
+        .current {{
+            background: #BBB;
+            border-radius: 10px;
+        }}
+    </style>
+
+    <script>
+        function cursorfocus(elem) {{
+            var container = document.getElementsByClassName('container')[0];
+            container.scrollTop = elem.offsetTop - 500;
+        }}
+
+        function getImage(type) {{
+            var current = document.getElementsByClassName("current")[0];
+            current.className = "image-item";
+            var img_src = type == 1 ? current.getAttribute('attr-next') : current.getAttribute('attr-prev');
+            if (img_src === "") {{
+                img_src = current.src;
+            }}
+
+            var img_list = document.getElementsByClassName("image-item");
+            for (i=0; i<img_list.length; i++) {{
+                if (img_list[i].src.endsWith(img_src)) {{
+                    img_list[i].className = "image-item current";
+                    cursorfocus(img_list[i]);
+                    break;
+                }}
+            }}
+            var display = document.getElementById("dest");
+            display.src = img_src;
+            display.focus();
+        }}
+    </script>
+</head>
+<body>
+
+<div class="container">
+{IMAGES}</div>
+<div class="image">
+    <div class="i">
+        <img src="" id="dest">
+        <a href="javascript:getImage(-1)" style="left: 0;"></a>
+        <a href="javascript:getImage(1)" style="left: 50%;"></a>
+    </div>
+</div>
+</body>
+
+<script>
+    var img_list = document.getElementsByClassName("image-item");
+
+    var display = document.getElementById("dest");
+    display.src = img_list[0].src;
+
+    for (var i = 0; i < img_list.length; i++) {{
+        img_list[i].addEventListener('click', function() {{
+            var current = document.getElementsByClassName("current")[0];
+            current.className = "image-item";
+            this.className = "image-item current";
+            var display = document.getElementById("dest");
+            display.src = this.src;
+            display.focus();
+        }}, false);
+    }}
+
+    document.onkeypress = function(e) {{
+        if (e.keyCode == 32) {{
+            getImage(1);
+        }}
+    }}
+</script>
+</html>

nhentai/doujinshi.py

@@ -1,8 +1,11 @@
 # coding: utf-8
-from __future__ import print_function
+from __future__ import print_function, unicode_literals
 from tabulate import tabulate
-from constant import DETAIL_URL, IMAGE_URL
+from future.builtins import range
-from logger import logger
+
+from nhentai.constant import DETAIL_URL, IMAGE_URL
+from nhentai.logger import logger
+from nhentai.utils import format_filename
 
 
 class DoujinshiInfo(dict):
@@ -28,7 +31,7 @@ class Doujinshi(object):
         self.info = DoujinshiInfo(**kwargs)
 
     def __repr__(self):
-        return '<Doujinshi: {}>'.format(self.name)
+        return '<Doujinshi: {0}>'.format(self.name)
 
     def show(self):
         table = [
@@ -41,15 +44,15 @@ class Doujinshi(object):
             ["URL", self.url],
             ["Pages", self.pages],
         ]
-        logger.info(u'Print doujinshi information\n{}'.format(tabulate(table)))
+        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
 
     def download(self):
         logger.info('Start download doujinshi: %s' % self.name)
         if self.downloader:
             download_queue = []
-            for i in xrange(1, self.pages + 1):
+            for i in range(1, self.pages + 1):
                 download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext))
-            self.downloader.download(download_queue, self.id)
+            self.downloader.download(download_queue, format_filename('%s-%s' % (self.id, self.name[:200])))
         else:
             logger.critical('Downloader has not be loaded')
 

nhentai/downloader.py

@@ -1,73 +1,95 @@
-# coding: utf-8
+# coding: utf-
+from __future__ import unicode_literals, print_function
+from future.builtins import str as text
 import os
 import requests
 import threadpool
-from urlparse import urlparse
+try:
-from logger import logger
+    from urllib.parse import urlparse
-from parser import request
+except ImportError:
+    from urlparse import urlparse
+
+from nhentai.logger import logger
+from nhentai.parser import request
+from nhentai.utils import Singleton
 
 
-class Downloader(object):
+requests.packages.urllib3.disable_warnings()
-    _instance = None
 
-    def __new__(cls, *args, **kwargs):
+
-        if not cls._instance:
+class NhentaiImageNotExistException(Exception):
-            cls._instance = super(Downloader, cls).__new__(cls, *args, **kwargs)
+    pass
-        return cls._instance
+
+
+class Downloader(Singleton):
 
     def __init__(self, path='', thread=1, timeout=30):
-        if not isinstance(thread, (int, )) or thread < 1 or thread > 10:
+        if not isinstance(thread, (int, )) or thread < 1 or thread > 15:
             raise ValueError('Invalid threads count')
         self.path = str(path)
         self.thread_count = thread
         self.threads = []
         self.timeout = timeout
 
-    def _download(self, url, folder='', filename='', retried=False):
+    def _download(self, url, folder='', filename='', retried=0):
-        logger.info('Start downloading: {} ...'.format(url))
+        logger.info('Start downloading: {0} ...'.format(url))
         filename = filename if filename else os.path.basename(urlparse(url).path)
+        base_filename, extension = os.path.splitext(filename)
         try:
-            with open(os.path.join(folder, filename), "wb") as f:
+            with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
                 response = request('get', url, stream=True, timeout=self.timeout)
+                if response.status_code != 200:
+                    raise NhentaiImageNotExistException
                 length = response.headers.get('content-length')
                 if length is None:
                     f.write(response.content)
                 else:
                     for chunk in response.iter_content(2048):
                         f.write(chunk)
-        except requests.HTTPError as e:
+
-            if not retried:
+        except (requests.HTTPError, requests.Timeout) as e:
-                logger.error('Error: {}, retrying'.format(str(e)))
+            if retried < 3:
-                return self._download(url=url, folder=folder, filename=filename, retried=True)
+                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
+                return 0, self._download(url=url, folder=folder, filename=filename, retried=retried+1)
             else:
-                return None
+                return 0, None
+
+        except NhentaiImageNotExistException as e:
+            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            return -1, url
+
         except Exception as e:
             logger.critical(str(e))
-            return None
+            return 0, None
-        return url
+
+        return 1, url
 
     def _download_callback(self, request, result):
-        if not result:
+        result, data = result
-            logger.critical('Too many errors occurred, quit.')
+        if result == 0:
-            raise SystemExit
+            logger.warning('fatal errors occurred, ignored')
-        logger.log(15, '{} download successfully'.format(result))
+            # exit(1)
+        elif result == -1:
+            logger.warning('url {} return status code 404'.format(data))
+        else:
+            logger.log(15, '{0} download successfully'.format(data))
 
     def download(self, queue, folder=''):
-        if not isinstance(folder, (str, unicode)):
+        if not isinstance(folder, (text)):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
         if not os.path.exists(folder):
-            logger.warn('Path \'{}\' not exist.'.format(folder))
+            logger.warn('Path \'{0}\' not exist.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
-                logger.critical('Error: {}'.format(str(e)))
+                logger.critical('{0}'.format(str(e)))
-                raise SystemExit
+                exit(1)
         else:
-            logger.warn('Path \'{}\' already exist.'.format(folder))
+            logger.warn('Path \'{0}\' already exist.'.format(folder))
 
         queue = [([url], {'folder': folder}) for url in queue]
 

nhentai/logger.py

@@ -1,13 +1,24 @@
-import logging
 #
 # 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 os
 import re
+import platform
 import sys
 
 
+if platform.system() == 'Windows':
+    import ctypes
+    import ctypes.wintypes
+
+    # Reference: https://gist.github.com/vsajip/758430
+    #            https://github.com/ipython/ipython/issues/4252
+    #            https://msdn.microsoft.com/en-us/library/windows/desktop/ms686047%28v=vs.85%29.aspx
+    ctypes.windll.kernel32.SetConsoleTextAttribute.argtypes = [ctypes.wintypes.HANDLE, ctypes.wintypes.WORD]
+    ctypes.windll.kernel32.SetConsoleTextAttribute.restype = ctypes.wintypes.BOOL
+
+
 class ColorizingStreamHandler(logging.StreamHandler):
     # color names to indices
     color_map = {
@@ -22,22 +33,13 @@ class ColorizingStreamHandler(logging.StreamHandler):
     }
 
     # levels to (background, foreground, bold/intense)
-    if os.name == 'nt':
+    level_map = {
-        level_map = {
+        logging.DEBUG: (None, 'blue', False),
-            logging.DEBUG: (None, 'white', False),
+        logging.INFO: (None, 'green', False),
-            logging.INFO: (None, 'green', False),
+        logging.WARNING: (None, 'yellow', False),
-            logging.WARNING: (None, 'yellow', False),
+        logging.ERROR: (None, 'red', False),
-            logging.ERROR: (None, 'red', False),
+        logging.CRITICAL: ('red', 'white', False)
-            logging.CRITICAL: ('red', 'white', False)
+    }
-        }
-    else:
-        level_map = {
-            logging.DEBUG: (None, 'white', False),
-            logging.INFO: (None, 'green', False),
-            logging.WARNING: (None, 'yellow', False),
-            logging.ERROR: (None, 'red', False),
-            logging.CRITICAL: ('red', 'white', False)
-        }
     csi = '\x1b['
     reset = '\x1b[0m'
     disable_coloring = False
@@ -47,7 +49,29 @@ class ColorizingStreamHandler(logging.StreamHandler):
         isatty = getattr(self.stream, 'isatty', None)
         return isatty and isatty() and not self.disable_coloring
 
-    if os.name != 'nt':
+    def emit(self, record):
+        try:
+            message = self.format(record)
+            stream = self.stream
+
+            if not self.is_tty:
+                if message and message[0] == "\r":
+                    message = message[1:]
+                stream.write(message)
+            else:
+                self.output_colorized(message)
+            stream.write(getattr(self, 'terminator', '\n'))
+
+            self.flush()
+        except (KeyboardInterrupt, SystemExit):
+            raise
+        except IOError:
+            pass
+        except:
+            self.handleError(record)
+
+
+    if not platform.system() == 'Windows':
         def output_colorized(self, message):
             self.stream.write(message)
     else:
@@ -65,8 +89,6 @@ class ColorizingStreamHandler(logging.StreamHandler):
         }
 
         def output_colorized(self, message):
-            import ctypes
-
             parts = self.ansi_esc.split(message)
             write = self.stream.write
             h = None
@@ -75,7 +97,7 @@ class ColorizingStreamHandler(logging.StreamHandler):
             if fd is not None:
                 fd = fd()
 
-                if fd in (1, 2):  # stdout or stderr
+                if fd in (1, 2): # stdout or stderr
                     h = ctypes.windll.kernel32.GetStdHandle(-10 - fd)
 
             while parts:
@@ -97,11 +119,11 @@ class ColorizingStreamHandler(logging.StreamHandler):
                             elif 30 <= p <= 37:
                                 color |= self.nt_color_map[p - 30]
                             elif p == 1:
-                                color |= 0x08  # foreground intensity on
+                                color |= 0x08 # foreground intensity on
-                            elif p == 0:  # reset to default color
+                            elif p == 0: # reset to default color
                                 color = 0x07
                             else:
-                                pass  # error condition ignored
+                                pass # error condition ignored
 
                         ctypes.windll.kernel32.SetConsoleTextAttribute(h, color)
 
@@ -135,6 +157,7 @@ class ColorizingStreamHandler(logging.StreamHandler):
         message = logging.StreamHandler.format(self, record)
         return self.colorize(message, record)
 
+
 logging.addLevelName(15, "INFO")
 logger = logging.getLogger('nhentai')
 LOGGER_HANDLER = ColorizingStreamHandler(sys.stdout)

nhentai/parser.py

@@ -1,38 +1,101 @@
 # coding: utf-8
-from __future__ import print_function
+from __future__ import unicode_literals, print_function
-import sys
+
+import os
 import re
+import threadpool
 import requests
 from bs4 import BeautifulSoup
-import constant
-from logger import logger
 from tabulate import tabulate
 
+import nhentai.constant as constant
+from nhentai.logger import logger
+
 
 def request(method, url, **kwargs):
     if not hasattr(requests, method):
-        raise AttributeError('\'requests\' object has no attribute \'{}\''.format(method))
+        raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))
 
-    return requests.__dict__[method](url, proxies=constant.PROXY, **kwargs)
+    return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)
+
+
+def login_parser(username, password):
+    s = requests.Session()
+    s.proxies = constant.PROXY
+    s.verify = False
+    s.headers.update({'Referer': constant.LOGIN_URL})
+
+    s.get(constant.LOGIN_URL)
+    content = s.get(constant.LOGIN_URL).content
+    html = BeautifulSoup(content, 'html.parser')
+    csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
+
+    if not csrf_token_elem:
+        raise Exception('Cannot find csrf token to login')
+    csrf_token = csrf_token_elem.attrs['value']
+
+    login_dict = {
+        'csrfmiddlewaretoken': csrf_token,
+        'username_or_email': username,
+        'password': password,
+    }
+    resp = s.post(constant.LOGIN_URL, data=login_dict)
+    if 'Invalid username (or email) or password' in resp.text:
+        logger.error('Login failed, please check your username and password')
+        exit(1)
+
+    html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser')
+    count = html.find('span', attrs={'class': 'count'})
+    if not count:
+        logger.error('Cannot get count of your favorites, maybe login failed.')
+
+    count = int(count.text.strip('(').strip(')'))
+    pages = count / 25
+    pages += 1 if count % (25 * pages) else 0
+    logger.info('Your have %d favorites in %d pages.' % (count, pages))
+
+    if os.getenv('DEBUG'):
+        pages = 1
+
+    ret = []
+    doujinshi_id = re.compile('data-id="([\d]+)"')
+
+    def _callback(request, result):
+        ret.append(result)
+
+    thread_pool = threadpool.ThreadPool(5)
+
+    for page in range(1, pages+1):
+        try:
+            logger.info('Getting doujinshi id of page %d' % page)
+            resp = s.get(constant.FAV_URL + '?page=%d' % page).content
+            ids = doujinshi_id.findall(resp)
+            requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
+            [thread_pool.putRequest(req) for req in requests_]
+            thread_pool.wait()
+        except Exception as e:
+            logger.error('Error: %s, continue', str(e))
+
+    return ret
 
 
 def doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
-        raise Exception('Doujinshi id({}) is not valid'.format(id_))
+        raise Exception('Doujinshi id({0}) is not valid'.format(id_))
 
     id_ = int(id_)
-    logger.log(15, 'Fetching doujinshi information of id {}'.format(id_))
+    logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{}/{}/'.format(constant.DETAIL_URL, id_)
+    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
 
     try:
         response = request('get', url).content
     except Exception as e:
         logger.critical(str(e))
-        sys.exit()
+        exit(1)
 
-    html = BeautifulSoup(response)
+    html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
@@ -42,10 +105,11 @@ def doujinshi_parser(id_):
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img['src'])
+    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
     if not img_id:
         logger.critical('Tried yo get image id failed')
-        sys.exit()
+        exit(1)
+
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = img_id.group(2)
 
@@ -71,16 +135,16 @@ def doujinshi_parser(id_):
 
 
 def search_parser(keyword, page):
-    logger.debug('Searching doujinshis of keyword {}'.format(keyword))
+    logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     result = []
     try:
         response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page}).content
     except requests.ConnectionError as e:
         logger.critical(e)
         logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
-        raise SystemExit
+        exit(1)
 
-    html = BeautifulSoup(response)
+    html = BeautifulSoup(response, 'html.parser')
     doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
     for doujinshi in doujinshi_search_result:
         doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
@@ -88,16 +152,20 @@ def search_parser(keyword, page):
         title = (title[:85] + '..') if len(title) > 85 else title
         id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
         result.append({'id': id_, 'title': title})
+    if not result:
+        logger.warn('Not found anything of keyword {}'.format(keyword))
+
     return result
 
 
 def print_doujinshi(doujinshi_list):
     if not doujinshi_list:
         return
-    doujinshi_list = [i.values() for i in doujinshi_list]
+    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
     logger.info('Search Result\n' +
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/utils.py

@@ -0,0 +1,87 @@
+# coding: utf-8
+from __future__ import unicode_literals, print_function
+
+import os
+import string
+from nhentai.logger import logger
+
+
+class _Singleton(type):
+    """ A metaclass that creates a Singleton base class when called. """
+    _instances = {}
+
+    def __call__(cls, *args, **kwargs):
+        if cls not in cls._instances:
+            cls._instances[cls] = super(_Singleton, cls).__call__(*args, **kwargs)
+        return cls._instances[cls]
+
+
+class Singleton(_Singleton(str('SingletonMeta'), (object,), {})):
+    pass
+
+
+def urlparse(url):
+    try:
+        from urlparse import urlparse
+    except ImportError:
+        from urllib.parse import urlparse
+
+    return urlparse(url)
+
+
+def generate_html(output_dir='.', doujinshi_obj=None):
+    image_html = ''
+    previous = ''
+
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
+                                                                            doujinshi_obj.name[:200])))
+    else:
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    for index, image in enumerate(file_list):
+        if not os.path.splitext(image)[1] in ('.jpg', '.png'):
+            continue
+
+        try:
+            next_ = file_list[file_list.index(image) + 1]
+        except IndexError:
+            next_ = ''
+
+        image_html += '<img src="{0}" class="image-item {1}" attr-prev="{2}" attr-next="{3}">\n'\
+            .format(image, 'current' if index == 0 else '', previous, next_)
+        previous = image
+
+    with open(os.path.join(os.path.dirname(__file__), 'doujinshi.html'), 'r') as template:
+        html = template.read()
+
+    if doujinshi_obj is not None:
+        title = doujinshi_obj.name
+    else:
+        title = 'nHentai HTML Viewer'
+
+    data = html.format(TITLE=title, IMAGES=image_html)
+    with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
+        f.write(data)
+
+    logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+
+
+def format_filename(s):
+    """Take a string and return a valid filename constructed from the string.
+Uses a whitelist approach: any characters not present in valid_chars are
+removed. Also spaces are replaced with underscores.
+
+Note: this method may produce invalid filenames such as ``, `.` or `..`
+When I use this method I prepend a date string like '2009_01_15_19_46_32_'
+and append a file extension like '.txt', so I avoid the potential of using
+an invalid filename.
+
+"""
+    valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
+    filename = ''.join(c for c in s if c in valid_chars)
+    filename = filename.replace(' ', '_')  # I don't like spaces in filenames.
+    return filename

requirements.txt

@@ -2,3 +2,4 @@ requests>=2.5.0
 BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
+future>=0.15.2

setup.cfg

@@ -0,0 +1,3 @@
+[metadata]
+description-file = README.md
+

setup.py

@@ -1,9 +1,20 @@
+# 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__
 
+
 with open('requirements.txt') as f:
     requirements = [l for l in f.read().splitlines() if l]
 
+
+def long_description():
+    with codecs.open('README.md', 'rb') as f:
+        if sys.version_info >= (3, 0, 0):
+            return str(f.read())
+
 setup(
     name='nhentai',
     version=__version__,
@@ -13,7 +24,9 @@ setup(
     author_email=__email__,
     keywords='nhentai, doujinshi',
     description='nhentai.net doujinshis downloader',
+    long_description=long_description(),
     url='https://github.com/RicterZ/nhentai',
+    download_url='https://github.com/RicterZ/nhentai/tarball/master',
     include_package_data=True,
     zip_safe=False,