diff --git a/.travis.yml b/.travis.yml index e8a0921..b0b5eef 100644 --- a/.travis.yml +++ b/.travis.yml @@ -13,9 +13,9 @@ 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 -l nhentai_test:nhentai --download --output=/tmp/ + - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz - NHENTAI=https://nhentai.net nhentai --tag lolicon - - NHENTAI=https://nhentai.net nhentai --id 92066 --output=/tmp/ --cbz + - NHENTAI=https://nhentai.net nhentai -F - NHENTAI=https://nhentai.net nhentai --file /tmp/test.txt diff --git a/README.md b/README.md deleted file mode 100644 index ac8aefc..0000000 --- a/README.md +++ /dev/null @@ -1,84 +0,0 @@ -nhentai -======= - _ _ _ _ - _ __ | | | | ___ _ __ | |_ __ _(_) - | '_ \| |_| |/ _ \ '_ \| __/ _` | | - | | | | _ | __/ | | | || (_| | | - |_| |_|_| |_|\___|_| |_|\__\__,_|_| - -あなたも変態。 いいね? -[](https://travis-ci.org/RicterZ/nhentai)  [](https://github.com/RicterZ/nhentai/blob/master/LICENSE) - - -nHentai is a CLI tool for downloading doujinshi from [nhentai.net](http://nhentai.net). - -### Installation - - git clone https://github.com/RicterZ/nhentai - cd nhentai - python setup.py install - -### 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 -``` - -Download your favourite doujinshi (login required): -```bash -nhentai --login "username:password" --download -``` - -Download by tag name: -```bash -nhentai --tag lolicon --download -``` - -### Options - -+ `-t, --thread`: Download threads, max: 10 -+ `--output`:Output dir of saving doujinshi -+ `--tag`:Download by tag name -+ `--timeout`: Timeout of downloading each image -+ `--proxy`: Use proxy, example: http://127.0.0.1:8080/ -+ `--login`: username:password pair of your nhentai account -+ `--nohtml`: Do not generate HTML -+ `--cbz`: Generate Comic Book CBZ File - -### nHentai Mirror -If you want to use a mirror, you should set up a reverse proxy of `nhentai.net` and `i.nhentai.net`. -For example: - - i.h.loli.club -> i.nhentai.net - h.loli.club -> nhentai.net - -Set `NHENTAI` env var to your nhentai mirror. -```bash -NHENTAI=http://h.loli.club nhentai --id 123456 -``` - - - - - -### あなたも変態 - diff --git a/README.rst b/README.rst new file mode 100644 index 0000000..5369190 --- /dev/null +++ b/README.rst @@ -0,0 +1,187 @@ +nhentai +======= + +.. code-block:: + + _ _ _ _ + _ __ | | | | ___ _ __ | |_ __ _(_) + | '_ \| |_| |/ _ \ '_ \| __/ _` | | + | | | | _ | __/ | | | || (_| | | + |_| |_|_| |_|\___|_| |_|\__\__,_|_| + + +あなたも変態。 いいね? + +|travis| +|pypi| +|license| + + +nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net> + +============ +Installation +============ +.. code-block:: + + git clone https://github.com/RicterZ/nhentai + cd nhentai + python setup.py install + +===================== +Installation (Gentoo) +===================== +.. code-block:: + + layman -fa glicOne + sudo emerge net-misc/nhentai + +===== +Usage +===== +**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--cookie` option to store your cookie. + +*The default download folder will be the path where you run the command (CLI path).* + + +Set your nhentai cookie against captcha: + +.. code-block:: bash + + nhentai --cookie 'YOUR COOKIE FROM nhentai.net' + +Download specified doujinshi: + +.. code-block:: bash + + nhentai --id=123855,123866 + +Download doujinshi with ids specified in a file (doujinshi ids split by line): + +.. code-block:: bash + + nhentai --file=doujinshi.txt + +Search a keyword and download the first page: + +.. code-block:: bash + + nhentai --search="tomori" --page=1 --download + +Download by tag name: + +.. code-block:: bash + + nhentai --tag lolicon --download --page=2 + +Download your favorites with delay: + +.. code-block:: bash + + nhentai --favorites --download --delay 1 + +Format output doujinshi folder name: + +.. code-block:: bash + + nhentai --id 261100 --format '[%i]%s' + +Supported doujinshi folder formatter: + +- %i: Doujinshi id +- %t: Doujinshi name +- %s: Doujinshi subtitle (translated name) +- %a: Doujinshi authors' name + + +Other options: + +.. code-block:: + + Options: + # Operation options + -h, --help show this help message and exit + -D, --download download doujinshi (for search results) + -S, --show just show the doujinshi information + + # Doujinshi options + --id=ID doujinshi ids set, e.g. 1,2,3 + -s KEYWORD, --search=KEYWORD + search doujinshi by keyword + --tag=TAG download doujinshi by tag + -F, --favorites list or download your favorites. + + # Multi-page options + --page=PAGE page number of search results + --max-page=MAX_PAGE The max page when recursive download tagged doujinshi + + # Download options + -o OUTPUT_DIR, --output=OUTPUT_DIR + output dir + -t THREADS, --threads=THREADS + thread count for downloading doujinshi + -T TIMEOUT, --timeout=TIMEOUT + timeout for downloading doujinshi + -d DELAY, --delay=DELAY + slow down between downloading every doujinshi + -p PROXY, --proxy=PROXY + uses a proxy, for example: http://127.0.0.1:1080 + -f FILE, --file=FILE read gallery IDs from file. + --format=NAME_FORMAT format the saved folder name + + # Generating options + --html generate a html viewer at current directory + --no-html don't generate HTML after downloading + -C, --cbz generate Comic Book CBZ File + --rm-origin-dir remove downloaded doujinshi dir when generated CBZ + file. + + # nHentai options + --cookie=COOKIE set cookie of nhentai to bypass Google recaptcha + + +============== +nHentai Mirror +============== +If you want to use a mirror, you should set up a reverse proxy of `nhentai.net` and `i.nhentai.net`. +For example: + +.. code-block:: + + i.h.loli.club -> i.nhentai.net + h.loli.club -> nhentai.net + +Set `NHENTAI` env var to your nhentai mirror. + +.. code-block:: bash + + NHENTAI=http://h.loli.club nhentai --id 123456 + + +.. image:: ./images/search.png?raw=true + :alt: nhentai + :align: center +.. image:: ./images/download.png?raw=true + :alt: nhentai + :align: center +.. image:: ./images/viewer.png?raw=true + :alt: nhentai + :align: center + +============ +あなたも変態 +============ +.. image:: ./images/image.jpg?raw=true + :alt: nhentai + :align: center + + + +.. |travis| image:: https://travis-ci.org/RicterZ/nhentai.svg?branch=master + :target: https://travis-ci.org/RicterZ/nhentai + +.. |pypi| image:: https://img.shields.io/pypi/dm/nhentai.svg + :target: https://pypi.org/project/nhentai/ + +.. |license| image:: https://img.shields.io/github/license/ricterz/nhentai.svg + :target: https://github.com/RicterZ/nhentai/blob/master/LICENSE diff --git a/nhentai/__init__.py b/nhentai/__init__.py index b6f0dc4..42ea186 100644 --- a/nhentai/__init__.py +++ b/nhentai/__init__.py @@ -1,3 +1,3 @@ -__version__ = '0.3.1' +__version__ = '0.3.4' __author__ = 'RicterZ' __email__ = 'ricterzheng@gmail.com' diff --git a/nhentai/cmdline.py b/nhentai/cmdline.py index 7e199b4..de6455c 100644 --- a/nhentai/cmdline.py +++ b/nhentai/cmdline.py @@ -1,14 +1,15 @@ # 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, generate_main_html from nhentai.logger import logger @@ -40,40 +41,54 @@ def cmd_parser(): '\n nhentai --file [filename]' '\n\nEnvironment Variable:\n' ' NHENTAI nhentai mirror url') - parser.add_option('--download', dest='is_download', action='store_true', + # operation options + parser.add_option('--download', '-D', dest='is_download', action='store_true', 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', '-S', 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('--search', '-s', type='string', dest='keyword', action='store', help='search doujinshi by keyword') + 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('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag') parser.add_option('--max-page', type='int', dest='max_page', action='store', default=1, help='The max page when recursive download tagged doujinshi') - parser.add_option('--output', type='string', dest='output_dir', action='store', default='', + + # download options + parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='', help='output dir') parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5, help='thread count for downloading doujinshi') - parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30, + parser.add_option('--timeout', '-T', type='int', dest='timeout', action='store', default=30, help='timeout for downloading doujinshi') - parser.add_option('--proxy', type='string', dest='proxy', action='store', default='', - help='uses a proxy, for example: --proxy "http://127.0.0.1:1080" or its alias "default"') + parser.add_option('--delay', '-d', type='int', dest='delay', action='store', default=0, + help='slow down between downloading every doujinshi') + parser.add_option('--proxy', '-p', type='string', dest='proxy', action='store', default='', + 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.') + parser.add_option('--format', type='string', dest='name_format', action='store', + help='format the saved folder name', default='[%i][%a][%t]') + + # generate options parser.add_option('--html', dest='html_viewer', action='store_true', help='generate a html viewer at current directory') + parser.add_option('--no-html', dest='is_nohtml', action='store_true', + help='don\'t generate HTML after downloading') parser.add_option('--gen-main', dest='main_viewer', action='store_true', help='generate a main viewer contain all the doujin in the folder') - - 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') - - parser.add_option('--cbz', dest='is_cbz', action='store_true', - help='Generate Comic Book CBZ File') + parser.add_option('--cbz', '-C', dest='is_cbz', action='store_true', + 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.') - parser.add_option('--file', '-f', type='string', dest='file', action='store', help='Read gallery IDs from file.') + 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)) @@ -92,6 +107,25 @@ def cmd_parser(): generate_main_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) @@ -101,6 +135,12 @@ 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(',')) @@ -112,12 +152,12 @@ def cmd_parser(): 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) diff --git a/nhentai/command.py b/nhentai/command.py index 4175bd1..71d0669 100644 --- a/nhentai/command.py +++ b/nhentai/command.py @@ -3,9 +3,10 @@ from __future__ import unicode_literals, print_function import signal import platform +import time from nhentai.cmdline import cmd_parser, banner -from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_parser, tag_parser, login +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 @@ -21,43 +22,37 @@ def main(): doujinshi_ids = [] doujinshi_list = [] - if options.login: - username, password = options.login.split(':', 1) - logger.info('Logging in to nhentai using credential pair \'%s:%s\'' % (username, '*' * len(password))) - login(username, password) + if options.favorites: + if not options.is_download: + logger.warning('You do not specify --download option') - if options.is_download or options.is_show: - for doujinshi_info in login_parser(): - doujinshi_list.append(Doujinshi(**doujinshi_info)) + doujinshi_ids = favorites_parser() - if options.is_show and not options.is_download: - print_doujinshi([{'id': i.id, 'title': i.name} for i in doujinshi_list]) - exit(0) - - if options.tag: + elif options.tag: doujinshis = tag_parser(options.tag, max_page=options.max_page) print_doujinshi(doujinshis) - if options.is_download: + if options.is_download and doujinshis: doujinshi_ids = map(lambda d: d['id'], doujinshis) - if options.keyword: + elif options.keyword: doujinshis = search_parser(options.keyword, options.page) - print(doujinshis) print_doujinshi(doujinshis) if options.is_download: doujinshi_ids = map(lambda d: d['id'], doujinshis) - if not doujinshi_ids: + elif not doujinshi_ids: doujinshi_ids = options.id if doujinshi_ids: for id_ in doujinshi_ids: + if options.delay: + time.sleep(options.delay) doujinshi_info = doujinshi_parser(id_) - doujinshi_list.append(Doujinshi(**doujinshi_info)) + doujinshi_list.append(Doujinshi(name_format=options.name_format, **doujinshi_info)) if not options.is_show: downloader = Downloader(path=options.output_dir, - thread=options.threads, timeout=options.timeout) + thread=options.threads, timeout=options.timeout, delay=options.delay) for doujinshi in doujinshi_list: doujinshi.downloader = downloader diff --git a/nhentai/constant.py b/nhentai/constant.py index 6eb3dee..11c0d02 100644 --- a/nhentai/constant.py +++ b/nhentai/constant.py @@ -1,6 +1,7 @@ # 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') @@ -20,4 +21,8 @@ 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 = '' diff --git a/nhentai/doujinshi.py b/nhentai/doujinshi.py index 88e0925..0ee0598 100644 --- a/nhentai/doujinshi.py +++ b/nhentai/doujinshi.py @@ -27,7 +27,7 @@ class DoujinshiInfo(dict): class Doujinshi(object): - def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, **kwargs): + def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs): self.name = name self.id = id self.img_id = img_id @@ -36,7 +36,12 @@ 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)) + + name_format = name_format.replace('%i', str(self.id)) + name_format = name_format.replace('%a', self.info.artists) + name_format = name_format.replace('%t', self.name) + name_format = name_format.replace('%s', self.info.subtitle) + self.filename = name_format def __repr__(self): return '<Doujinshi: {0}>'.format(self.name) @@ -46,7 +51,7 @@ class Doujinshi(object): ["Doujinshi", self.name], ["Subtitle", self.info.subtitle], ["Characters", self.info.character], - ["Authors", self.info.artist], + ["Authors", self.info.artists], ["Language", self.info.language], ["Tags", self.info.tags], ["URL", self.url], diff --git a/nhentai/downloader.py b/nhentai/downloader.py index 8095c5f..81037f8 100644 --- a/nhentai/downloader.py +++ b/nhentai/downloader.py @@ -4,6 +4,8 @@ from future.builtins import str as text import os import requests import threadpool +import time + try: from urllib.parse import urlparse except ImportError: @@ -23,7 +25,7 @@ class NhentaiImageNotExistException(Exception): class Downloader(Singleton): - def __init__(self, path='', thread=1, timeout=30): + def __init__(self, path='', thread=1, timeout=30, delay=0): if not isinstance(thread, (int, )) or thread < 1 or thread > 15: raise ValueError('Invalid threads count') self.path = str(path) @@ -31,8 +33,11 @@ class Downloader(Singleton): self.threads = [] self.thread_pool = None self.timeout = timeout + self.delay = delay def _download(self, url, folder='', filename='', retried=0): + if self.delay: + time.sleep(self.delay) 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) diff --git a/nhentai/parser.py b/nhentai/parser.py index 9feb89c..34555e0 100644 --- a/nhentai/parser.py +++ b/nhentai/parser.py @@ -25,6 +25,7 @@ def request(method, url, **kwargs): if not hasattr(session, method): raise AttributeError('\'requests.Session\' object has no attribute \'{0}\''.format(method)) + session.headers.update({'Cookie': constant.COOKIE}) return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs) @@ -37,6 +38,7 @@ def _get_csrf_token(content): 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 ...') @@ -51,7 +53,7 @@ def login(username, password): } resp = request('post', url=constant.LOGIN_URL, data=login_dict) - if 'You\'re loading pages way too quickly.' 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': '/'}) @@ -59,13 +61,12 @@ def login(username, password): logger.error('Login failed, please check your username and password') exit(1) - if 'You\'re loading pages way too quickly.' in resp.text: - logger.error('You meet challenge insistently, please submit a issue' - ' at https://github.com/RicterZ/nhentai/issues') + 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 login_parser(): +def favorites_parser(): html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser') count = html.find('span', attrs={'class': 'count'}) if not count: @@ -91,20 +92,13 @@ def login_parser(): ret = [] doujinshi_id = re.compile('data-id="([\d]+)"') - def _callback(request, result): - ret.append(result) - - # TODO: reduce threads number ... - thread_pool = threadpool.ThreadPool(1) - for page in range(1, pages + 1): try: logger.info('Getting doujinshi ids of page %d' % page) 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_] - thread_pool.wait() + ret.extend(ids) + except Exception as e: logger.error('Error: %s, continue', str(e)) diff --git a/setup.py b/setup.py index d0f6562..7b87d5c 100644 --- a/setup.py +++ b/setup.py @@ -11,9 +11,10 @@ with open('requirements.txt') as f: def long_description(): - with codecs.open('README.md', 'rb') as f: - if sys.version_info >= (3, 0, 0): - return str(f.read()) + with codecs.open('README.rst', 'rb') as readme: + if not sys.version_info < (3, 0, 0): + return readme.read().decode('utf-8') + setup( name='nhentai',