0.2.11

Add install for Gentoo

.gitignore

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

MANIFEST.in

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

README.md

@@ -12,41 +12,54 @@ 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
-+ 下载指定 id 列表的本子：
-
+    layman -fa glicOne
+    sudo emerge net-misc/nhentai
 
+### Usage
+下载指定 id 列表的本子：
+```bash
 nhentai --id=123855,123866
+```
 
-
-+ 下载某关键词第一页的本子（不推荐）：
-
-
+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
+```
+
+### 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
 
-### 自建 nhentai 镜像
+### 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。  
 然后利用环境变量来下载：  
 
+```bash
 NHENTAI=http://h.loli.club nhentai --id 123456
-
+```
 
 ![](./images/search.png)  
 ![](./images/download.png)  
+![](./images/viewer.png)  
 
 ### License  
 MIT

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.2.2'
+__version__ = '0.2.11'
 __author__ = 'Ricter'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -8,7 +8,7 @@ except ImportError:
     pass
 
 import nhentai.constant as constant
-from nhentai.utils import urlparse
+from nhentai.utils import urlparse, generate_html
 from nhentai.logger import logger
 
 try:
@@ -30,9 +30,13 @@ def banner():
 
 
 def cmd_parser():
-    parser = OptionParser()
-    parser.add_option('--download', dest='is_download', action='store_true', help='download doujinshi or not')
-    parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information.')
+    parser = OptionParser('\n  nhentai --search [keyword] --download'
+                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n\nEnvironment Variable:\n'
+                          '  NHENTAI                 nhentai mirror url')
+    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,
@@ -46,6 +50,11 @@ def cmd_parser():
                       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')
+    parser.add_option('--html', dest='html_viewer', action='store_true',
+                      help='generate a html viewer at current directory')
+
+    parser.add_option('--login', '-l', type='str', dest='login', action='store',
+                      help='username:password pair of nhentai account')
 
     try:
         sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
@@ -56,35 +65,49 @@ def cmd_parser():
 
     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(0)
+        exit(1)
 
     if args.id:
         _ = map(lambda id: id.strip(), args.id.split(','))
-        args.id = set(map(int, filter(lambda id: id.isdigit(), _)))
+        args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
 
-    if (args.is_download or args.is_show) and not args.id and not args.keyword:
+    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()
-        exit(0)
+        exit(1)
 
-    if not args.keyword and not args.id:
+    if not args.keyword and not args.id and not args.login:
         parser.print_help()
-        exit(0)
+        exit(1)
 
     if args.threads <= 0:
         args.threads = 1
 
-    elif args.threads > 10:
-        logger.critical('Maximum number of used threads is 10')
-        exit(0)
+    elif args.threads > 15:
+        logger.critical('Maximum number of used threads is 15')
+        exit(1)
 
     if args.proxy:
         proxy_url = urlparse(args.proxy)
         if proxy_url.scheme not in ('http', 'https'):
             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

@@ -5,11 +5,12 @@ import signal
 import platform
 
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_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
 
 
 def main():
@@ -20,6 +21,12 @@ def main():
     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)
@@ -29,11 +36,9 @@ def main():
         doujinshi_ids = options.id
 
     if doujinshi_ids:
-        for id in doujinshi_ids:
-            doujinshi_info = doujinshi_parser(id)
+        for id_ in doujinshi_ids:
+            doujinshi_info = doujinshi_parser(id_)
             doujinshi_list.append(Doujinshi(**doujinshi_info))
-    else:
-        exit(0)
 
     if not options.is_show:
         downloader = Downloader(path=options.output_dir,
@@ -42,6 +47,7 @@ def main():
         for doujinshi in doujinshi_list:
             doujinshi.downloader = downloader
             doujinshi.download()
+            generate_html(options.output_dir, doujinshi)
 
         if not platform.system() == 'Windows':
             logger.log(15, '🍺 All done.')

nhentai/constant.py

@@ -7,6 +7,8 @@ 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)

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

@@ -5,6 +5,7 @@ from future.builtins import range
 
 from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
+from nhentai.utils import format_filename
 
 
 class DoujinshiInfo(dict):
@@ -51,7 +52,7 @@ class Doujinshi(object):
             download_queue = []
             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

@@ -14,45 +14,65 @@ from nhentai.parser import request
 from nhentai.utils import Singleton
 
 
+requests.packages.urllib3.disable_warnings()
+
+
+class NhentaiImageNotExistException(Exception):
+    pass
+
+
 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: {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, 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:
-                logger.error('Error: {0}, retrying'.format(str(e)))
-                return self._download(url=url, folder=folder, filename=filename, retried=True)
+
+        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)
             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 url
+            return 0, None
+
+        return 1, url
 
     def _download_callback(self, request, result):
-        if not result:
-            logger.critical('Too many errors occurred, quit.')
-            exit(1)
-        logger.log(15, '{0} download successfully'.format(result))
+        result, data = result
+        if result == 0:
+            logger.warning('fatal errors occurred, ignored')
+            # 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, (text)):
@@ -66,7 +86,7 @@ class Downloader(Singleton):
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
-                logger.critical('Error: {0}'.format(str(e)))
+                logger.critical('{0}'.format(str(e)))
                 exit(1)
         else:
             logger.warn('Path \'{0}\' already exist.'.format(folder))

nhentai/parser.py

@@ -1,9 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 
-from bs4 import BeautifulSoup
+import os
 import re
+import threadpool
 import requests
+from bs4 import BeautifulSoup
 from tabulate import tabulate
 
 import nhentai.constant as constant
@@ -14,7 +16,67 @@ def request(method, url, **kwargs):
     if not hasattr(requests, 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_):
@@ -43,7 +105,7 @@ 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')
         exit(1)
@@ -104,5 +166,6 @@ def print_doujinshi(doujinshi_list):
     logger.info('Search Result\n' +
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/utils.py

@@ -1,6 +1,10 @@
 # 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. """
@@ -23,3 +27,61 @@ def urlparse(url):
         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

setup.py

@@ -1,15 +1,18 @@
 # 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(