modify tests #54

Add viewer arrow support, add README license badge.

.gitignore

@@ -5,3 +5,4 @@ dist/
 *.egg-info
 .python-version
 .DS_Store
+output/

.travis.yml

@@ -4,14 +4,18 @@ os:
 language: python
 python:
     - 2.7
-    - 2.6
     - 3.6
+    - 3.5
+    - 3.4
 
 install:
     - python setup.py install
 
 script:
+    - echo 268642 > /tmp/test.txt
+    - NHENTAI=https://nhentai.net nhentai --cookie '__cfduid=da09f237ceb0f51c75980b0b3fda3ce571558179357; _ga=GA1.2.2000087053.1558179358; _gid=GA1.2.717818542.1558179358; csrftoken=iSxrTFOjrujJqauhAqWvTTI9dl3sfWnxdEFoMuqgmlBrbMin5Gj9wJW4r61cmH1X; sessionid=ewuaayfewbzpiukrarx9d52oxwlz2esd'
     - NHENTAI=https://nhentai.net nhentai --search umaru
-    - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/
+    - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - NHENTAI=https://nhentai.net nhentai -l nhentai_test:nhentai --output=/tmp/
     - NHENTAI=https://nhentai.net nhentai --tag lolicon
+    - NHENTAI=https://nhentai.net nhentai -F
+    - NHENTAI=https://nhentai.net nhentai --file /tmp/test.txt

README.md

@@ -7,7 +7,7 @@ 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 PyPI Downloads](https://pypistats.com/badge/nhentai.svg)  
+[![Build Status](https://travis-ci.org/RicterZ/nhentai.svg?branch=master)](https://travis-ci.org/RicterZ/nhentai) ![nhentai PyPI Downloads](https://img.shields.io/pypi/dm/nhentai.svg) [![license](https://img.shields.io/cocoapods/l/AFNetworking.svg)](https://github.com/RicterZ/nhentai/blob/master/LICENSE)
 
 
 nHentai is a CLI tool for downloading doujinshi from [nhentai.net](http://nhentai.net).
@@ -18,17 +18,26 @@ nHentai is a CLI tool for downloading doujinshi from [nhentai.net](http://nhenta
     cd nhentai
     python setup.py install
     
-### Gentoo
+### Installation (Gentoo)
 
     layman -fa glicOne
     sudo emerge net-misc/nhentai
 
 ### Usage
+**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--login` option to log into nhentai.net.
+
+*The default download folder will be the path where you run the command (CLI path).*
+
 Download specified doujinshi:
 ```bash
 nhentai --id=123855,123866
 ```
 
+Download doujinshi with ids specified in a file:
+```bash
+nhentai --file=doujinshi.txt
+```
+
 Search a keyword and download the first page:
 ```bash
 nhentai --search="tomori" --page=1 --download
@@ -71,8 +80,5 @@ NHENTAI=http://h.loli.club nhentai --id 123456
 ![](./images/download.png)  
 ![](./images/viewer.png)  
 
-### License  
-MIT
-
 ### あなたも変態
 ![](./images/image.jpg)

doujinshi.txt

@@ -0,0 +1,5 @@
+184212
+204944
+222460
+244502
+261909

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.2.15'
+__version__ = '0.3.1'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,20 +1,25 @@
 # coding: utf-8
 from __future__ import print_function
+import os
 import sys
 from optparse import OptionParser
-from nhentai import __version__
 try:
     from itertools import ifilter as filter
 except ImportError:
     pass
 
 import nhentai.constant as constant
+from nhentai import __version__
 from nhentai.utils import urlparse, generate_html
 from nhentai.logger import logger
 
 try:
-    reload(sys)
+    if sys.version_info < (3, 0, 0):
-    sys.setdefaultencoding(sys.stdin.encoding)
+        import codecs
+        import locale
+        sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
+        sys.stderr = codecs.getwriter(locale.getpreferredencoding())(sys.stderr)
+
 except NameError:
     # python3
     pass
@@ -33,35 +38,51 @@ def banner():
 def cmd_parser():
     parser = OptionParser('\n  nhentai --search [keyword] --download'
                           '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n  nhentai --file [filename]'    
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
+    # operation options
     parser.add_option('--download', dest='is_download', action='store_true',
-                      help='download doujinshi (for search result)')
+                      help='download doujinshi (for search results)')
-    parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information')
+    parser.add_option('--show', dest='is_show', action='store_true', help='just show the doujinshi information')
+
+    # doujinshi options
     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('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
+    parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
+                      help='list or download your favorites.')
+
+    # page options
+    parser.add_option('--page', type='int', dest='page', action='store', default=1,
+                      help='page number of search results')
+    parser.add_option('--max-page', type='int', dest='max_page', action='store', default=1,
+                      help='The max page when recursive download tagged doujinshi')
+
+    # download options
     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')
+                      help='thread count for downloading doujinshi')
     parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
-                      help='timeout of download doujinshi')
+                      help='timeout for downloading doujinshi')
     parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
-                      help='use proxy, example: http://127.0.0.1:1080')
+                      help='uses a proxy, for example: http://127.0.0.1:1080')
+    parser.add_option('--file',  '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+
+    # generate options
     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')
-
     parser.add_option('--nohtml', dest='is_nohtml', action='store_true',
-                      help='Don\'t generate HTML')
+                      help='don\'t generate HTML')
-
     parser.add_option('--cbz', dest='is_cbz', action='store_true',
-                      help='Generate Comic Book CBZ File')                      
+                      help='generate Comic Book CBZ File')
+    parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
+                      help='remove downloaded doujinshi dir when generated CBZ file.')
+
+    # nhentai options
+    parser.add_option('--cookie', type='str', dest='cookie', action='store',
+                      help='set cookie of nhentai to bypass Google recaptcha')
 
     try:
         sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
@@ -76,6 +97,25 @@ def cmd_parser():
         generate_html()
         exit(0)
 
+    if os.path.exists(os.path.join(constant.NHENTAI_HOME, 'cookie')):
+        with open(os.path.join(constant.NHENTAI_HOME, 'cookie'), 'r') as f:
+            constant.COOKIE = f.read()
+
+    if args.cookie:
+        try:
+            if not os.path.exists(constant.NHENTAI_HOME):
+                os.mkdir(constant.NHENTAI_HOME)
+
+            with open(os.path.join(constant.NHENTAI_HOME, 'cookie'), 'w') as f:
+                f.write(args.cookie)
+        except Exception as e:
+            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
+            exit(1)
+
+        logger.info('Cookie saved.')
+        exit(0)
+
+    '''
     if args.login:
         try:
             _, _ = args.login.split(':', 1)
@@ -85,18 +125,29 @@ def cmd_parser():
 
         if not args.is_download:
             logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
+    '''
+
+    if args.favorites:
+        if not constant.COOKIE:
+            logger.warning('Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.')
+            exit(1)
 
     if args.id:
-        _ = map(lambda id: id.strip(), args.id.split(','))
+        _ = map(lambda id_: id_.strip(), args.id.split(','))
+        args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
+
+    if args.file:
+        with open(args.file, 'r') as f:
+            _ = map(lambda id: id.strip(), f.readlines())
             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 and \
-            not args.login and not args.tag:
+            not args.tag and not args.favorites:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
         exit(1)
 
-    if not args.keyword and not args.id and not args.login and not args.tag:
+    if not args.keyword and not args.id and not args.tag and not args.favorites:
         parser.print_help()
         exit(1)
 

nhentai/command.py

@@ -5,7 +5,7 @@ import signal
 import platform
 
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_parser, tag_guessing, tag_parser
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser, tag_parser, login
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
@@ -21,18 +21,21 @@ def main():
     doujinshi_ids = []
     doujinshi_list = []
 
-    if options.login:
+    if options.favorites:
-        username, password = options.login.split(':', 1)
+        if not options.is_download:
-        logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password)))
+            logger.warning('You do not specify --download option')
-        for doujinshi_info in login_parser(username=username, password=password):
+
+        for doujinshi_info in favorites_parser():
             doujinshi_list.append(Doujinshi(**doujinshi_info))
 
+        if not options.is_download:
+            print_doujinshi([{'id': i.id, 'title': i.name} for i in doujinshi_list])
+            exit(0)
+
     if options.tag:
-        tag_id = tag_guessing(options.tag)
+        doujinshis = tag_parser(options.tag, max_page=options.max_page)
-        if tag_id:
-            doujinshis = tag_parser(tag_id)
         print_doujinshi(doujinshis)
-            if options.is_download:
+        if options.is_download and doujinshis:
             doujinshi_ids = map(lambda d: d['id'], doujinshis)
 
     if options.keyword:
@@ -41,6 +44,9 @@ def main():
         if options.is_download:
             doujinshi_ids = map(lambda d: d['id'], doujinshis)
 
+    if not doujinshi_ids:
+        doujinshi_ids = options.id
+
     if doujinshi_ids:
         for id_ in doujinshi_ids:
             doujinshi_info = doujinshi_parser(id_)
@@ -56,7 +62,7 @@ def main():
             if not options.is_nohtml and not options.is_cbz:
                 generate_html(options.output_dir, doujinshi)
             elif options.is_cbz:
-                generate_cbz(options.output_dir, doujinshi)
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
 
         if not platform.system() == 'Windows':
             logger.log(15, '🍻 All done.')
@@ -68,7 +74,7 @@ def main():
 
 
 def signal_handler(signal, frame):
-    logger.error('Ctrl-C signal received. Quit.')
+    logger.error('Ctrl-C signal received. Stopping...')
     exit(1)
 
 

nhentai/constant.py

@@ -1,18 +1,28 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 import os
+import tempfile
 from nhentai.utils import urlparse
 
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-DETAIL_URL = '%s/api/gallery' % BASE_URL
+__api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
-SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+__api_suspended_SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+
+DETAIL_URL = '%s/g' % BASE_URL
+SEARCH_URL = '%s/search/' % BASE_URL
+
 TAG_URL = '%s/tag' % BASE_URL
 TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
 LOGIN_URL = '%s/login/' % BASE_URL
+CHALLENGE_URL = '%s/challenge' % BASE_URL
 FAV_URL = '%s/favorites/' % BASE_URL
 
 u = urlparse(BASE_URL)
 IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
 
+NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
+
 PROXY = {}
+
+COOKIE = ''

nhentai/doujinshi.py

@@ -11,6 +11,7 @@ from nhentai.utils import format_filename
 EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
+    'g': 'gif',
 }
 
 
@@ -35,6 +36,7 @@ class Doujinshi(object):
         self.downloader = None
         self.url = '%s/%d' % (DETAIL_URL, self.id)
         self.info = DoujinshiInfo(**kwargs)
+        self.filename = format_filename('[%s][%s][%s]' % (self.id, self.info.artist, self.name))
 
     def __repr__(self):
         return '<Doujinshi: {0}>'.format(self.name)
@@ -43,8 +45,8 @@ class Doujinshi(object):
         table = [
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
-            ["Characters", self.info.characters],
+            ["Characters", self.info.character],
-            ["Authors", self.info.artists],
+            ["Authors", self.info.artist],
             ["Language", self.info.language],
             ["Tags", self.info.tags],
             ["URL", self.url],
@@ -53,15 +55,25 @@ class Doujinshi(object):
         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)
+        logger.info('Starting to download doujinshi: %s' % self.name)
         if self.downloader:
             download_queue = []
+
+            if len(self.ext) != self.pages:
+                logger.warning('Page count and ext count do not equal')
+
+            for i in range(1, min(self.pages, len(self.ext)) + 1):
+                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))
+
+            self.downloader.download(download_queue, self.filename)
+
+            '''
             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')
+            logger.critical('Downloader has not been loaded')
 
 
 if __name__ == '__main__':

nhentai/downloader.py

@@ -29,22 +29,40 @@ class Downloader(Singleton):
         self.path = str(path)
         self.thread_count = thread
         self.threads = []
+        self.thread_pool = None
         self.timeout = timeout
 
     def _download(self, url, folder='', filename='', retried=0):
-        logger.info('Start downloading: {0} ...'.format(url))
+        logger.info('Starting to download {0} ...'.format(url))
         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) +
+                logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
                                                                                 extension)))
                 return 1, url
 
+            response = None
             with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
+                i = 0
+                while i < 10:
+                    try:
                         response = request('get', url, stream=True, timeout=self.timeout)
                         if response.status_code != 200:
                             raise NhentaiImageNotExistException
+
+                    except NhentaiImageNotExistException as e:
+                        raise e
+
+                    except Exception as e:
+                        i += 1
+                        if not i < 10:
+                            logger.critical(str(e))
+                            return 0, None
+                        continue
+
+                    break
+
                 length = response.headers.get('content-length')
                 if length is None:
                     f.write(response.content)
@@ -77,7 +95,7 @@ class Downloader(Singleton):
         elif result == -1:
             logger.warning('url {} return status code 404'.format(data))
         else:
-            logger.log(15, '{0} download successfully'.format(data))
+            logger.log(15, '{0} downloaded successfully'.format(data))
 
     def download(self, queue, folder=''):
         if not isinstance(folder, text):
@@ -87,7 +105,7 @@ class Downloader(Singleton):
             folder = os.path.join(self.path, folder)
 
         if not os.path.exists(folder):
-            logger.warn('Path \'{0}\' not exist.'.format(folder))
+            logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:

nhentai/logger.py

@@ -104,6 +104,9 @@ class ColorizingStreamHandler(logging.StreamHandler):
                 text = parts.pop(0)
 
                 if text:
+                    if sys.version_info < (3, 0, 0):
+                        write(text.encode('utf-8'))
+                    else:
                         write(text)
 
                 if parts:

nhentai/parser.py

@@ -5,6 +5,7 @@ import os
 import re
 import threadpool
 import requests
+import time
 from bs4 import BeautifulSoup
 from tabulate import tabulate
 
@@ -12,44 +13,67 @@ import nhentai.constant as constant
 from nhentai.logger import logger
 
 
+session = requests.Session()
+session.headers.update({
+    'Referer': constant.LOGIN_URL,
+    'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+})
+
+
 def request(method, url, **kwargs):
-    if not hasattr(requests, method):
+    global session
-        raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))
+    if not hasattr(session, method):
+        raise AttributeError('\'requests.Session\' object has no attribute \'{0}\''.format(method))
 
-    return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)
+    session.headers.update({'Cookie': constant.COOKIE})
+    return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
 
 
-def login_parser(username, password):
+def _get_csrf_token(content):
-    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']
+    return csrf_token_elem.attrs['value']
+
+
+def login(username, password):
+    logger.warning('This feature is deprecated, please use --cookie to set your cookie.')
+    csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
+    if os.getenv('DEBUG'):
+        logger.info('Getting CSRF token ...')
+
+    if os.getenv('DEBUG'):
+        logger.info('CSRF token is {}'.format(csrf_token))
 
     login_dict = {
         'csrfmiddlewaretoken': csrf_token,
         'username_or_email': username,
         'password': password,
     }
-    resp = s.post(constant.LOGIN_URL, data=login_dict)
+    resp = request('post', url=constant.LOGIN_URL, data=login_dict)
-    if 'Invalid username (or email) or password' in resp.text:
+
+    if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+        csrf_token = _get_csrf_token(resp.text)
+        resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
+
+    if 'Invalid username/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')
+    if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+        logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
+        exit(2)
+
+
+def favorites_parser():
+    html = BeautifulSoup(request('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.')
+        logger.error("Can't get your number of favorited doujins. Did the login failed?")
+        return []
 
-    count = int(count.text.strip('(').strip(')'))
+    count = int(count.text.strip('(').strip(')').replace(',', ''))
     if count == 0:
         logger.warning('No favorites found')
         return []
@@ -60,7 +84,7 @@ def login_parser(username, password):
     else:
         pages = 1
 
-    logger.info('Your have %d favorites in %d pages.' % (count, pages))
+    logger.info('You have %d favorites in %d pages.' % (count, pages))
 
     if os.getenv('DEBUG'):
         pages = 1
@@ -68,19 +92,15 @@ def login_parser(username, password):
     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)
+            logger.info('Getting doujinshi ids of page %d' % page)
-            resp = s.get(constant.FAV_URL + '?page=%d' % page).text
+            resp = request('get', constant.FAV_URL + '?page=%d' % page).text
             ids = doujinshi_id.findall(resp)
-            requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
+
-            [thread_pool.putRequest(req) for req in requests_]
+            for i in ids:
-            thread_pool.wait()
+                ret.append(doujinshi_parser(i))
+
         except Exception as e:
             logger.error('Error: %s, continue', str(e))
 
@@ -95,13 +115,110 @@ 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)
+        if response.status_code in (200, ):
+            response = response.content
+        else:
+            logger.debug('Slow down and retry ({}) ...'.format(id_))
+            time.sleep(1)
+            return doujinshi_parser(str(id_))
+
+    except Exception as e:
+        logger.critical(str(e))
+        raise SystemExit
+
+    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'])
+
+    ext = []
+    for i in html.find_all('div', attrs={'class': 'thumb-container'}):
+        _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
+        ext.append(ext_name)
+
+    if not img_id:
+        logger.critical('Tried yo get image id failed')
+        exit(1)
+
+    doujinshi['img_id'] = img_id.group(1)
+    doujinshi['ext'] = ext
+
+    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)
+
+    # 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)
+
+    return doujinshi
+
+
+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
+    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
+
+    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 if len(title) < 85 else title[:82] + '...'
+        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 __api_suspended_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_))
+
+    id_ = int(id_)
+    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
+    doujinshi = dict()
+    doujinshi['id'] = id_
+    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    i = 0
+    while 5 > i:
         try:
             response = request('get', url).json()
         except Exception as e:
+            i += 1
+            if not i < 5:
                 logger.critical(str(e))
                 exit(1)
+            continue
+        break
 
     doujinshi['name'] = response['title']['english']
     doujinshi['subtitle'] = response['title']['japanese']
@@ -124,22 +241,29 @@ def doujinshi_parser(id_):
             elif tag_type not in doujinshi:
                 doujinshi[tag_type] = tag['name']
             else:
-                doujinshi[tag_type] += tag['name']
+                doujinshi[tag_type] += ', ' + tag['name']
 
     return doujinshi
 
 
-def search_parser(keyword, page):
+def __api_suspended_search_parser(keyword, page):
-    logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
+    logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
     result = []
+    i = 0
+    while i < 5:
         try:
             response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json()
-        if 'result' not in response:
+        except Exception as e:
-            raise Exception('No result in response')
+            i += 1
-    except requests.ConnectionError as e:
+            if not i < 5:
-        logger.critical(e)
+                logger.critical(str(e))
                 logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
                 exit(1)
+            continue
+        break
+
+    if 'result' not in response:
+        raise Exception('No result in response')
 
     for row in response['result']:
         title = row['title']['english']
@@ -147,7 +271,7 @@ def search_parser(keyword, page):
         result.append({'id': row['id'], 'title': title})
 
     if not result:
-        logger.warn('Not found anything of keyword {}'.format(keyword))
+        logger.warn('No results for keywords {}'.format(keyword))
 
     return result
 
@@ -161,47 +285,54 @@ def print_doujinshi(doujinshi_list):
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def tag_parser(tag_id):
+def __api_suspended_tag_parser(tag_id, max_page=1):
-    logger.info('Get doujinshi of tag id: {0}'.format(tag_id))
+    logger.info('Searching for doujinshi with tag id {0}'.format(tag_id))
     result = []
     response = request('get', url=constant.TAG_API_URL, params={'sort': 'popular', 'tag_id': tag_id}).json()
+    page = max_page if max_page <= response['num_pages'] else int(response['num_pages'])
 
+    for i in range(1, page + 1):
+        logger.info('Getting page {} ...'.format(i))
+
+        if page != 1:
+            response = request('get', url=constant.TAG_API_URL,
+                               params={'sort': 'popular', 'tag_id': tag_id}).json()
     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 tag id {}'.format(tag_id))
+        logger.warn('No results for tag id {}'.format(tag_id))
 
     return result
 
 
-def tag_guessing(tag_name):
+def tag_parser(tag_name, max_page=1):
+    result = []
     tag_name = tag_name.lower()
     tag_name = tag_name.replace(' ', '-')
-    logger.info('Trying to get tag_id of tag \'{0}\''.format(tag_name))
+
-    response = request('get', url='%s/%s' % (constant.TAG_URL, tag_name)).content
+    for p in range(1, max_page + 1):
+        logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
+        response = request('get', url='%s/%s?page=%d' % (constant.TAG_URL, tag_name, p)).content
+
         html = BeautifulSoup(response, 'html.parser')
-    first_item = html.find('div', attrs={'class': 'gallery'})
+        doujinshi_items = html.find_all('div', attrs={'class': 'gallery'})
-    if not first_item:
+        if not doujinshi_items:
             logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
             return
 
-    doujinshi_id = re.findall('(\d+)', first_item.a.attrs['href'])
+        for i in doujinshi_items:
-    if not doujinshi_id:
+            doujinshi_id = i.a.attrs['href'].strip('/g')
-        logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
+            doujinshi_title = i.a.text.strip()
-        return
+            doujinshi_title = doujinshi_title if len(doujinshi_title) < 85 else doujinshi_title[:82] + '...'
+            result.append({'title': doujinshi_title, 'id': doujinshi_id})
 
-    ret = doujinshi_parser(doujinshi_id[0])
+    if not result:
-    if 'tag' in ret and tag_name in ret['tag']:
+        logger.warn('No results for tag \'{}\''.format(tag_name))
-        tag_id = ret['tag'][tag_name]
-        logger.info('Tag id of tag \'{0}\' is {1}'.format(tag_name, tag_id))
-    else:
-        logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
-        return
 
-    return tag_id
+    return result
 
 
 if __name__ == '__main__':

nhentai/utils.py

@@ -43,8 +43,7 @@ def generate_html(output_dir='.', doujinshi_obj=None):
     image_html = ''
 
     if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-                                                                            str(doujinshi_obj.name[:200]))))
     else:
         doujinshi_dir = '.'
 
@@ -64,6 +63,8 @@ def generate_html(output_dir='.', doujinshi_obj=None):
 
     if doujinshi_obj is not None:
         title = doujinshi_obj.name
+        if sys.version_info < (3, 0):
+            title = title.encode('utf-8')
     else:
         title = 'nHentai HTML Viewer'
 
@@ -81,12 +82,10 @@ def generate_html(output_dir='.', doujinshi_obj=None):
         logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None):
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-                                                                            str(doujinshi_obj.name[:200]))))    
+        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '%s.cbz' % doujinshi_obj.id)
-        cbz_filename = os.path.join(output_dir, format_filename('%s-%s.cbz' % (doujinshi_obj.id,
-                                                                            str(doujinshi_obj.name[:200]))))
     else:
         cbz_filename = './doujinshi.cbz'
         doujinshi_dir = '.'
@@ -94,20 +93,18 @@ def generate_cbz(output_dir='.', doujinshi_obj=None):
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
+    logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
     with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
         for image in file_list:
             image_path = os.path.join(doujinshi_dir, image)
             cbz_pf.write(image_path, image)
 
+    if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
+
     logger.log(15, 'Comic Book CBZ file has been write 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
@@ -119,7 +116,12 @@ 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)
+    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.
+    if len(filename) > 100:
+        filename = filename[:100] + '...]'
+
+    # Remove [] from filename
+    filename = filename.replace('[]', '')
     return filename

nhentai/viewer/scripts.js

@@ -46,17 +46,33 @@ document.getElementById('image-container').onclick = event => {
 document.onkeypress = event => {
     switch (event.key.toLowerCase()) {
         // Previous Image
-        case 'arrowleft':
         case 'a':
             changePage(currentPage - 1);
             break;
 
         // Next Image
         case ' ':
+        case 'esc': // future close page function
         case 'enter':
-        case 'arrowright':
         case 'd':
             changePage(currentPage + 1);
             break;
+    }// remove arrow cause it won't work
+};
+
+document.onkeydown = event =>{
+    switch (event.keyCode) {
+        case 37: //left
+            changePage(currentPage - 1);
+            break;
+        case 38: //up
+            changePage(currentPage - 1);
+            break;
+        case 39: //right
+            changePage(currentPage + 1);
+            break;
+        case 40: //down
+            changePage(currentPage + 1);
+            break;
     }
 };

requirements.txt

@@ -2,4 +2,4 @@ requests>=2.5.0
 BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
-future>=0.15.2threadpool==1.3.2
+future>=0.15.2