0.2.12

Add install for Gentoo

README.md

@@ -12,38 +12,50 @@ 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
+```
 
-    nhentai --id=123855,123866
+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
+```
 
-+ 下载某关键词第一页的本子（不推荐）：
-
-
-    nhentai --search="tomori" --page=1 --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：  
 
-    NHENTAI=http://h.loli.club nhentai --id 123456
-
+```bash
+NHENTAI=http://h.loli.club nhentai --id 123456
+```
 
 ![](./images/search.png)  
 ![](./images/download.png)  

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.2.10'
+__version__ = '0.2.12'
 __author__ = 'Ricter'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -34,7 +34,8 @@ def cmd_parser():
                           '\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('--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')
@@ -49,7 +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('--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))
@@ -64,35 +69,45 @@ def cmd_parser():
         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 > 15:
         logger.critical('Maximum number of used threads is 15')
-        exit(0)
+        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

@@ -1,12 +1,11 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
 from __future__ import unicode_literals, print_function
-import os
 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
@@ -22,6 +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)
@@ -31,11 +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,

nhentai/constant.py

@@ -5,8 +5,10 @@ from nhentai.utils import urlparse
 
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-DETAIL_URL = '%s/g' % BASE_URL
-SEARCH_URL = '%s/search/' % BASE_URL
+DETAIL_URL = '%s/api/gallery' % BASE_URL
+SEARCH_URL = '%s/api/galleries/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.py

@@ -5,6 +5,13 @@ from future.builtins import range
 
 from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
+from nhentai.utils import format_filename
+
+
+EXT_MAP = {
+    'j': 'jpg',
+    'p': 'png',
+}
 
 
 class DoujinshiInfo(dict):
@@ -19,7 +26,7 @@ class DoujinshiInfo(dict):
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='jpg', pages=0, **kwargs):
+    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, **kwargs):
         self.name = name
         self.id = id
         self.img_id = img_id
@@ -49,9 +56,10 @@ class Doujinshi(object):
         logger.info('Start download doujinshi: %s' % self.name)
         if self.downloader:
             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)
+            for i in range(len(self.ext)):
+                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i+1, EXT_MAP[self.ext[i]]))
+
+            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

@@ -36,6 +36,11 @@ class Downloader(Singleton):
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
         try:
+            if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
+                logger.warning('File: {0} existed, ignore.'.format(os.path.join(folder, base_filename.zfill(3) +
+                                                                                extension)))
+                return 1, url
+
             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:
@@ -75,7 +80,7 @@ class Downloader(Singleton):
             logger.log(15, '{0} download successfully'.format(data))
 
     def download(self, queue, folder=''):
-        if not isinstance(folder, (text)):
+        if not isinstance(folder, text):
             folder = str(folder)
 
         if self.path:

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
@@ -17,6 +19,66 @@ def request(method, url, **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({0}) is not valid'.format(id_))
@@ -25,49 +87,29 @@ def doujinshi_parser(id_):
     logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
+    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
 
     try:
-        response = request('get', url).content
+        response = request('get', url).json()
     except Exception as e:
         logger.critical(str(e))
         exit(1)
 
-    html = BeautifulSoup(response, 'html.parser')
-    doujinshi_info = html.find('div', attrs={'id': 'info'})
-
-    title = doujinshi_info.find('h1').text
-    subtitle = doujinshi_info.find('h2')
-
-    doujinshi['name'] = title
-    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.attrs['data-src'])
-    if not img_id:
-        logger.critical('Tried yo get image id failed')
-        exit(1)
-
-    doujinshi['img_id'] = img_id.group(1)
-    doujinshi['ext'] = img_id.group(2)
-
-    pages = 0
-    for _ in doujinshi_info.find_all('div', class_=''):
-        pages = re.search('([\d]+) pages', _.text)
-        if pages:
-            pages = pages.group(1)
-            break
-    doujinshi['pages'] = int(pages)
+    doujinshi['name'] = response['title']['english']
+    doujinshi['subtitle'] = response['title']['japanese']
+    doujinshi['img_id'] = response['media_id']
+    doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))
+    doujinshi['pages'] = len(response['images']['pages'])
 
     # gain information of the doujinshi
-    information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
-    needed_fields = ['Characters', 'Artists', 'Language', 'Tags']
-    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
-                    field.find_all('a', attrs={'class': 'tag'})]
-            doujinshi[field_name.lower()] = ', '.join(data)
+    needed_fields = ['character', 'artist', 'language']
+    for tag in response['tags']:
+        tag_type = tag['type']
+        if tag_type in needed_fields:
+            if tag_type not in doujinshi:
+                doujinshi[tag_type] = tag['name']
+            else:
+                doujinshi[tag_type] += tag['name']
 
     return doujinshi
 
@@ -76,20 +118,19 @@ def search_parser(keyword, page):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     result = []
     try:
-        response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page}).content
+        response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json()
+        if 'result' not in response:
+            raise Exception('No result in response')
     except requests.ConnectionError as e:
         logger.critical(e)
         logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
         exit(1)
 
-    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'})
-        title = doujinshi_container.text.strip()
-        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})
+    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('Not found anything of keyword {}'.format(keyword))
 
@@ -104,5 +145,6 @@ 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

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals, print_function
 
 import os
+import string
 from nhentai.logger import logger
 
 
@@ -33,7 +34,8 @@ def generate_html(output_dir='.', doujinshi_obj=None):
     previous = ''
 
     if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, str(doujinshi_obj.id))
+        doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
+                                                                            doujinshi_obj.name[:200])))
     else:
         doujinshi_dir = '.'
 
@@ -66,3 +68,20 @@ def generate_html(output_dir='.', doujinshi_obj=None):
         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', 'r') as f:
+    with codecs.open('README.md', 'rb') as f:
+        if sys.version_info >= (3, 0, 0):
             return str(f.read())
 
 setup(