NussNougate/nhentai
4
0
Fork 0
mirror of https://github.com/RicterZ/nhentai.git synced 2025-04-20 11:01:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:RicterZ/nhentai

Browse Source
This commit is contained in:
Ricter Z 2018-08-11 09:19:31 +08:00
commit de157ccb7f
11 changed files with 697 additions and 626 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
MANIFEST.in
View File

@ -1,3 +1,5 @@
include README.md include README.md
include requirements.txt include requirements.txt
include nhentai/doujinshi.html include nhentai/viewer/index.html
include nhentai/viewer/styles.css
include nhentai/viewer/scripts.js

136
README.md
View File

@ -1,68 +1,70 @@
nhentai nhentai
======= =======
_ _ _ _ _ _ _ _
_ __ | | | | ___ _ __ | |_ __ _(_) _ __ | | | | ___ _ __ | |_ __ _(_)
| '_ \| |_| |/ _ \ '_ \| __/ _` | | | '_ \| |_| |/ _ \ '_ \| __/ _` | |
| | | | _ | __/ | | | || (_| | | | | | | _ | __/ | | | || (_| | |
|_| |_|_| |_|\___|_| |_|\__\__,_|_| |_| |_|_| |_|\___|_| |_|\__\__,_|_|
あなたも変態。 いいね? 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) [![Build Status](https://travis-ci.org/RicterZ/nhentai.svg?branch=master)](https://travis-ci.org/RicterZ/nhentai)
🎉🎉 nhentai 现在支持 Windows 啦！ 🎉🎉 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。 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。
### Installation ### Installation
git clone https://github.com/RicterZ/nhentai git clone https://github.com/RicterZ/nhentai
cd nhentai cd nhentai
python setup.py install python setup.py install
### Gentoo ### Gentoo
layman -fa glicOne layman -fa glicOne
sudo emerge net-misc/nhentai sudo emerge net-misc/nhentai
### Usage ### Usage
下载指定 id 列表的本子： 下载指定 id 列表的本子：
```bash ```bash
nhentai --id=123855,123866 nhentai --id=123855,123866
``` ```
下载某关键词第一页的本子： 下载某关键词第一页的本子：
```bash ```bash
nhentai --search="tomori" --page=1 --download nhentai --search="tomori" --page=1 --download
``` ```
下载用户 favorites 内容： 下载用户 favorites 内容：
```bash ```bash
nhentai --login "username:password" --download nhentai --login "username:password" --download
``` ```
### Options ### Options
`-t, --thread`：指定下载的线程数，最多为 10 线程。 `-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。 `--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。 `--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/ `--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 `--login`：nhentai 账号的“用户名:密码”组合
`--nohtml`：nhentai Don't generate HTML
### nHentai Mirror `--cbz`：nhentai Generate Comic Book CBZ file
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。 ### nHentai Mirror
然后利用环境变量来下载： 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。
```bash 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)
![](./images/viewer.png) ![](./images/search.png)
![](./images/download.png)
### License ![](./images/viewer.png)
MIT
### License
### あなたも変態 MIT
### あなたも変態
![](./images/image.jpg) ![](./images/image.jpg)

6
nhentai/__init__.py
View File

@ -1,3 +1,3 @@
__version__ = '0.2.12' __version__ = '0.2.14'
__author__ = 'Ricter' __author__ = 'RicterZ'
__email__ = 'ricterzheng@gmail.com' __email__ = 'ricterzheng@gmail.com'

233
nhentai/cmdline.py
View File

@ -1,113 +1,120 @@
# coding: utf-8 # coding: utf-8
from __future__ import print_function from __future__ import print_function
import sys import sys
from optparse import OptionParser from optparse import OptionParser
try: from nhentai import __version__
from itertools import ifilter as filter try:
except ImportError: from itertools import ifilter as filter
pass except ImportError:
pass
import nhentai.constant as constant
from nhentai.utils import urlparse, generate_html import nhentai.constant as constant
from nhentai.logger import logger from nhentai.utils import urlparse, generate_html
from nhentai.logger import logger
try:
reload(sys) try:
sys.setdefaultencoding(sys.stdin.encoding) reload(sys)
except NameError: sys.setdefaultencoding(sys.stdin.encoding)
# python3 except NameError:
pass # python3
pass
def banner():
logger.info(u'''nHentai: あなたも変態。 いいね? def banner():
_ _ _ _ logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
_ __ | | | | ___ _ __ | |_ __ _(_) _ _ _ _
| '_ \| |_| |/ _ \ '_ \| __/ _` | | _ __ | | | | ___ _ __ | |_ __ _(_)
| | | | _ | __/ | | | || (_| | | | '_ \| |_| |/ _ \ '_ \| __/ _` | |
|_| |_|_| |_|\___|_| |_|\__\__,_|_| | | | | _ | __/ | | | || (_| | |
''') |_| |_|_| |_|\___|_| |_|\__\__,_|_|
''' % __version__)
def cmd_parser():
parser = OptionParser('\n nhentai --search [keyword] --download' def cmd_parser():
'\n NHENTAI=http://h.loli.club nhentai --id [ID ...]' parser = OptionParser('\n nhentai --search [keyword] --download'
'\n\nEnvironment Variable:\n' '\n NHENTAI=http://h.loli.club nhentai --id [ID ...]'
' NHENTAI nhentai mirror url') '\n\nEnvironment Variable:\n'
parser.add_option('--download', dest='is_download', action='store_true', ' NHENTAI nhentai mirror url')
help='download doujinshi (for search result)') parser.add_option('--download', dest='is_download', action='store_true',
parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information') help='download doujinshi (for search result)')
parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3') parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information')
parser.add_option('--search', type='string', dest='keyword', action='store', help='search doujinshi by keyword') parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--page', type='int', dest='page', action='store', default=1, parser.add_option('--search', type='string', dest='keyword', action='store', help='search doujinshi by keyword')
help='page number of search result') parser.add_option('--page', type='int', dest='page', action='store', default=1,
parser.add_option('--tags', type='string', dest='tags', action='store', help='download doujinshi by tags') help='page number of search result')
parser.add_option('--output', type='string', dest='output_dir', action='store', default='', parser.add_option('--tags', type='string', dest='tags', action='store', help='download doujinshi by tags')
help='output dir') parser.add_option('--output', type='string', dest='output_dir', action='store', default='',
parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5, help='output dir')
help='thread count of download doujinshi') parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30, help='thread count of download doujinshi')
help='timeout of download doujinshi') parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
parser.add_option('--proxy', type='string', dest='proxy', action='store', default='', help='timeout of download doujinshi')
help='use proxy, example: http://127.0.0.1:1080') parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
parser.add_option('--html', dest='html_viewer', action='store_true', help='use proxy, example: http://127.0.0.1:1080')
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') 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)) parser.add_option('--nohtml', dest='is_nohtml', action='store_true',
except (NameError, TypeError): help='Don\'t generate HTML')
pass
except UnicodeDecodeError: parser.add_option('--cbz', dest='is_cbz', action='store_true',
exit(0) help='Generate Comic Book CBZ File')
args, _ = parser.parse_args(sys.argv[1:]) try:
sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
if args.html_viewer: except (NameError, TypeError):
generate_html() pass
exit(0) except UnicodeDecodeError:
exit(0)
if args.login:
try: args, _ = parser.parse_args(sys.argv[1:])
_, _ = args.login.split(':', 1)
except ValueError: if args.html_viewer:
logger.error('Invalid `username:password` pair.') generate_html()
exit(1) exit(0)
if not args.is_download: if args.login:
logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!') try:
_, _ = args.login.split(':', 1)
if args.tags: except ValueError:
logger.warning('`--tags` is under construction') logger.error('Invalid `username:password` pair.')
exit(1) exit(1)
if args.id: if not args.is_download:
_ = map(lambda id: id.strip(), args.id.split(',')) logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
if args.tags:
if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.login: logger.warning('`--tags` is under construction')
logger.critical('Doujinshi id(s) are required for downloading') exit(1)
parser.print_help()
exit(1) if args.id:
_ = map(lambda id: id.strip(), args.id.split(','))
if not args.keyword and not args.id and not args.login: args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
parser.print_help()
exit(1) 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')
if args.threads <= 0: parser.print_help()
args.threads = 1 exit(1)
elif args.threads > 15: if not args.keyword and not args.id and not args.login:
logger.critical('Maximum number of used threads is 15') parser.print_help()
exit(1) exit(1)
if args.proxy: if args.threads <= 0:
proxy_url = urlparse(args.proxy) args.threads = 1
if proxy_url.scheme not in ('http', 'https'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme)) elif args.threads > 15:
else: logger.critical('Maximum number of used threads is 15')
constant.PROXY = {'http': args.proxy, 'https': args.proxy} exit(1)
return args 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 = {'http': args.proxy, 'https': args.proxy}
return args

141
nhentai/command.py
View File

@ -1,69 +1,72 @@
#!/usr/bin/env python2.7 #!/usr/bin/env python2.7
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals, print_function from __future__ import unicode_literals, print_function
import signal import signal
import platform import platform
from nhentai.cmdline import cmd_parser, banner from nhentai.cmdline import cmd_parser, banner
from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_parser from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_parser
from nhentai.doujinshi import Doujinshi from nhentai.doujinshi import Doujinshi
from nhentai.downloader import Downloader from nhentai.downloader import Downloader
from nhentai.logger import logger from nhentai.logger import logger
from nhentai.constant import BASE_URL from nhentai.constant import BASE_URL
from nhentai.utils import generate_html from nhentai.utils import generate_html, generate_cbz
def main(): def main():
banner() banner()
logger.info('Using mirror: {0}'.format(BASE_URL)) logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser() options = cmd_parser()
doujinshi_ids = [] doujinshi_ids = []
doujinshi_list = [] doujinshi_list = []
if options.login: if options.login:
username, password = options.login.split(':', 1) username, password = options.login.split(':', 1)
logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password))) logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password)))
for doujinshi_info in login_parser(username=username, password=password): for doujinshi_info in login_parser(username=username, password=password):
doujinshi_list.append(Doujinshi(**doujinshi_info)) doujinshi_list.append(Doujinshi(**doujinshi_info))
if options.keyword: if options.keyword:
doujinshis = search_parser(options.keyword, options.page) doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis) print_doujinshi(doujinshis)
if options.is_download: if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis) doujinshi_ids = map(lambda d: d['id'], doujinshis)
else: else:
doujinshi_ids = options.id doujinshi_ids = options.id
if doujinshi_ids: if doujinshi_ids:
for id_ in doujinshi_ids: for id_ in doujinshi_ids:
doujinshi_info = doujinshi_parser(id_) doujinshi_info = doujinshi_parser(id_)
doujinshi_list.append(Doujinshi(**doujinshi_info)) doujinshi_list.append(Doujinshi(**doujinshi_info))
if not options.is_show: if not options.is_show:
downloader = Downloader(path=options.output_dir, downloader = Downloader(path=options.output_dir,
thread=options.threads, timeout=options.timeout) thread=options.threads, timeout=options.timeout)
for doujinshi in doujinshi_list: for doujinshi in doujinshi_list:
doujinshi.downloader = downloader doujinshi.downloader = downloader
doujinshi.download() doujinshi.download()
generate_html(options.output_dir, doujinshi) if not options.is_nohtml and not options.is_cbz:
generate_html(options.output_dir, doujinshi)
if not platform.system() == 'Windows': elif options.is_cbz:
logger.log(15, '🍺 All done.') generate_cbz(options.output_dir, doujinshi)
else:
logger.log(15, 'All done.') if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else: else:
[doujinshi.show() for doujinshi in doujinshi_list] logger.log(15, 'All done.')
else:
def signal_handler(signal, frame): [doujinshi.show() for doujinshi in doujinshi_list]
logger.error('Ctrl-C signal received. Quit.')
exit(1)
def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Quit.')
signal.signal(signal.SIGINT, signal_handler) exit(1)
if __name__ == '__main__':
main() signal.signal(signal.SIGINT, signal_handler)
if __name__ == '__main__':
main()

126
nhentai/doujinshi.html
View File

@ -1,126 +0,0 @@
<!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>

316
nhentai/parser.py
View File

@ -1,158 +1,158 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals, print_function from __future__ import unicode_literals, print_function
import os import os
import re import re
import threadpool import threadpool
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from tabulate import tabulate from tabulate import tabulate
import nhentai.constant as constant import nhentai.constant as constant
from nhentai.logger import logger from nhentai.logger import logger
def request(method, url, **kwargs): def request(method, url, **kwargs):
if not hasattr(requests, method): if not hasattr(requests, method):
raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method)) raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))
return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs) return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)
def login_parser(username, password): def login_parser(username, password):
s = requests.Session() s = requests.Session()
s.proxies = constant.PROXY s.proxies = constant.PROXY
s.verify = False s.verify = False
s.headers.update({'Referer': constant.LOGIN_URL}) s.headers.update({'Referer': constant.LOGIN_URL})
s.get(constant.LOGIN_URL) s.get(constant.LOGIN_URL)
content = s.get(constant.LOGIN_URL).content content = s.get(constant.LOGIN_URL).content
html = BeautifulSoup(content, 'html.parser') html = BeautifulSoup(content, 'html.parser').encode("ascii")
csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'}) csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
if not csrf_token_elem: if not csrf_token_elem:
raise Exception('Cannot find csrf token to login') raise Exception('Cannot find csrf token to login')
csrf_token = csrf_token_elem.attrs['value'] csrf_token = csrf_token_elem.attrs['value']
login_dict = { login_dict = {
'csrfmiddlewaretoken': csrf_token, 'csrfmiddlewaretoken': csrf_token,
'username_or_email': username, 'username_or_email': username,
'password': password, 'password': password,
} }
resp = s.post(constant.LOGIN_URL, data=login_dict) resp = s.post(constant.LOGIN_URL, data=login_dict)
if 'Invalid username (or email) or password' in resp.text: if 'Invalid username (or email) or password' in resp.text:
logger.error('Login failed, please check your username and password') logger.error('Login failed, please check your username and password')
exit(1) exit(1)
html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser') html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser').encode("ascii")
count = html.find('span', attrs={'class': 'count'}) count = html.find('span', attrs={'class': 'count'})
if not count: if not count:
logger.error('Cannot get count of your favorites, maybe login failed.') logger.error('Cannot get count of your favorites, maybe login failed.')
count = int(count.text.strip('(').strip(')')) count = int(count.text.strip('(').strip(')'))
if count == 0: if count == 0:
logger.warning('No favorites found') logger.warning('No favorites found')
return [] return []
pages = int(count / 25) pages = int(count / 25)
if pages: if pages:
pages += 1 if count % (25 * pages) else 0 pages += 1 if count % (25 * pages) else 0
else: else:
pages = 1 pages = 1
logger.info('Your have %d favorites in %d pages.' % (count, pages)) logger.info('Your have %d favorites in %d pages.' % (count, pages))
if os.getenv('DEBUG'): if os.getenv('DEBUG'):
pages = 1 pages = 1
ret = [] ret = []
doujinshi_id = re.compile('data-id="([\d]+)"') doujinshi_id = re.compile('data-id="([\d]+)"')
def _callback(request, result): def _callback(request, result):
ret.append(result) ret.append(result)
thread_pool = threadpool.ThreadPool(5) thread_pool = threadpool.ThreadPool(5)
for page in range(1, pages+1): for page in range(1, pages+1):
try: try:
logger.info('Getting doujinshi id of page %d' % page) logger.info('Getting doujinshi id of page %d' % page)
resp = s.get(constant.FAV_URL + '?page=%d' % page).text resp = s.get(constant.FAV_URL + '?page=%d' % page).text
ids = doujinshi_id.findall(resp) ids = doujinshi_id.findall(resp)
requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback) requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
[thread_pool.putRequest(req) for req in requests_] [thread_pool.putRequest(req) for req in requests_]
thread_pool.wait() thread_pool.wait()
except Exception as e: except Exception as e:
logger.error('Error: %s, continue', str(e)) logger.error('Error: %s, continue', str(e))
return ret return ret
def doujinshi_parser(id_): def doujinshi_parser(id_):
if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()): if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
raise Exception('Doujinshi id({0}) is not valid'.format(id_)) raise Exception('Doujinshi id({0}) is not valid'.format(id_))
id_ = int(id_) id_ = int(id_)
logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_)) logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
doujinshi = dict() doujinshi = dict()
doujinshi['id'] = id_ doujinshi['id'] = id_
url = '{0}/{1}'.format(constant.DETAIL_URL, id_) url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
try: try:
response = request('get', url).json() response = request('get', url).json()
except Exception as e: except Exception as e:
logger.critical(str(e)) logger.critical(str(e))
exit(1) exit(1)
doujinshi['name'] = response['title']['english'] doujinshi['name'] = response['title']['english']
doujinshi['subtitle'] = response['title']['japanese'] doujinshi['subtitle'] = response['title']['japanese']
doujinshi['img_id'] = response['media_id'] doujinshi['img_id'] = response['media_id']
doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages'])) doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))
doujinshi['pages'] = len(response['images']['pages']) doujinshi['pages'] = len(response['images']['pages'])
# gain information of the doujinshi # gain information of the doujinshi
needed_fields = ['character', 'artist', 'language'] needed_fields = ['character', 'artist', 'language']
for tag in response['tags']: for tag in response['tags']:
tag_type = tag['type'] tag_type = tag['type']
if tag_type in needed_fields: if tag_type in needed_fields:
if tag_type not in doujinshi: if tag_type not in doujinshi:
doujinshi[tag_type] = tag['name'] doujinshi[tag_type] = tag['name']
else: else:
doujinshi[tag_type] += tag['name'] doujinshi[tag_type] += tag['name']
return doujinshi return doujinshi
def search_parser(keyword, page): def search_parser(keyword, page):
logger.debug('Searching doujinshis of keyword {0}'.format(keyword)) logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
result = [] result = []
try: try:
response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json() response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json()
if 'result' not in response: if 'result' not in response:
raise Exception('No result in response') raise Exception('No result in response')
except requests.ConnectionError as e: except requests.ConnectionError as e:
logger.critical(e) logger.critical(e)
logger.warn('If you are in China, please configure the proxy to fu*k GFW.') logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
exit(1) exit(1)
for row in response['result']: for row in response['result']:
title = row['title']['english'] title = row['title']['english']
title = title[:85] + '..' if len(title) > 85 else title title = title[:85] + '..' if len(title) > 85 else title
result.append({'id': row['id'], 'title': title}) result.append({'id': row['id'], 'title': title})
if not result: if not result:
logger.warn('Not found anything of keyword {}'.format(keyword)) logger.warn('Not found anything of keyword {}'.format(keyword))
return result return result
def print_doujinshi(doujinshi_list): def print_doujinshi(doujinshi_list):
if not doujinshi_list: if not doujinshi_list:
return return
doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list] doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
headers = ['id', 'doujinshi'] headers = ['id', 'doujinshi']
logger.info('Search Result\n' + logger.info('Search Result\n' +
tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst')) tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
if __name__ == '__main__': if __name__ == '__main__':
print(doujinshi_parser("32271")) print(doujinshi_parser("32271"))

202
nhentai/utils.py
View File

@ -1,87 +1,115 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals, print_function from __future__ import unicode_literals, print_function
import os import os
import string import string
from nhentai.logger import logger import zipfile
import shutil
from nhentai.logger import logger
class _Singleton(type):
""" A metaclass that creates a Singleton base class when called. """
_instances = {} class _Singleton(type):
""" A metaclass that creates a Singleton base class when called. """
def __call__(cls, *args, **kwargs): _instances = {}
if cls not in cls._instances:
cls._instances[cls] = super(_Singleton, cls).__call__(*args, **kwargs) def __call__(cls, *args, **kwargs):
return cls._instances[cls] if cls not in cls._instances:
cls._instances[cls] = super(_Singleton, cls).__call__(*args, **kwargs)
return cls._instances[cls]
class Singleton(_Singleton(str('SingletonMeta'), (object,), {})):
pass
class Singleton(_Singleton(str('SingletonMeta'), (object,), {})):
pass
def urlparse(url):
try:
from urlparse import urlparse def urlparse(url):
except ImportError: try:
from urllib.parse import urlparse from urlparse import urlparse
except ImportError:
return urlparse(url) from urllib.parse import urlparse
return urlparse(url)
def generate_html(output_dir='.', doujinshi_obj=None):
image_html = '' def readfile(path):
previous = '' loc = os.path.dirname(__file__)
if doujinshi_obj is not None: with open(os.path.join(loc, path), 'r') as file:
doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id, return file.read()
doujinshi_obj.name[:200])))
else: def generate_html(output_dir='.', doujinshi_obj=None):
doujinshi_dir = '.' image_html = ''
file_list = os.listdir(doujinshi_dir) if doujinshi_obj is not None:
file_list.sort() doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
str(doujinshi_obj.name[:200]))))
for index, image in enumerate(file_list): else:
if not os.path.splitext(image)[1] in ('.jpg', '.png'): doujinshi_dir = '.'
continue
file_list = os.listdir(doujinshi_dir)
try: file_list.sort()
next_ = file_list[file_list.index(image) + 1]
except IndexError: for image in file_list:
next_ = '' if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
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_) image_html += '<img src="{0}" class="image-item"/>\n'\
previous = image .format(image)
with open(os.path.join(os.path.dirname(__file__), 'doujinshi.html'), 'r') as template: html = readfile('viewer/index.html')
html = template.read() css = readfile('viewer/styles.css')
js = readfile('viewer/scripts.js')
if doujinshi_obj is not None:
title = doujinshi_obj.name if doujinshi_obj is not None:
else: title = doujinshi_obj.name
title = 'nHentai HTML Viewer' 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: data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
f.write(data) 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')))
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. def generate_cbz(output_dir='.', doujinshi_obj=None):
Uses a whitelist approach: any characters not present in valid_chars are if doujinshi_obj is not None:
removed. Also spaces are replaced with underscores. doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
str(doujinshi_obj.name[:200]))))
Note: this method may produce invalid filenames such as ``, `.` or `..` cbz_filename = os.path.join(output_dir, format_filename('%s-%s.cbz' % (doujinshi_obj.id,
When I use this method I prepend a date string like '2009_01_15_19_46_32_' str(doujinshi_obj.name[:200]))))
and append a file extension like '.txt', so I avoid the potential of using else:
an invalid filename. cbz_filename = './doujinshi.cbz'
doujinshi_dir = '.'
"""
valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits) file_list = os.listdir(doujinshi_dir)
filename = ''.join(c for c in s if c in valid_chars) file_list.sort()
filename = filename.replace(' ', '_') # I don't like spaces in filenames.
return 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)
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
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

24
nhentai/viewer/index.html Normal file
View File

@ -0,0 +1,24 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>{TITLE}</title>
<style>
{STYLES}
</style>
</head>
<body>
<nav id="list">
{IMAGES}</nav>
<div id="image-container">
<span id="page-num"></span>
<div id="dest"></div>
</div>
<script>
{SCRIPTS}
</script>
</body>
</html>

62
nhentai/viewer/scripts.js Normal file
View File

@ -0,0 +1,62 @@
const pages = Array.from(document.querySelectorAll('img.image-item'));
let currentPage = 0;
function changePage(pageNum) {
const previous = pages[currentPage];
const current = pages[pageNum];
if (current == null) {
return;
}
previous.classList.remove('current');
current.classList.add('current');
currentPage = pageNum;
const display = document.getElementById('dest');
display.style.backgroundImage = `url("${current.src}")`;
document.getElementById('page-num')
.innerText = [
(pageNum + 1).toLocaleString(),
pages.length.toLocaleString()
].join('\u200a/\u200a');
}
changePage(0);
document.getElementById('list').onclick = event => {
if (pages.includes(event.target)) {
changePage(pages.indexOf(event.target));
}
};
document.getElementById('image-container').onclick = event => {
const width = document.getElementById('image-container').clientWidth;
const clickPos = event.clientX / width;
if (clickPos < 0.5) {
changePage(currentPage - 1);
} else {
changePage(currentPage + 1);
}
};
document.onkeypress = event => {
switch (event.key.toLowerCase()) {
// Previous Image
case 'arrowleft':
case 'a':
changePage(currentPage - 1);
break;
// Next Image
case ' ':
case 'enter':
case 'arrowright':
case 'd':
changePage(currentPage + 1);
break;
}
};

69
nhentai/viewer/styles.css Normal file
View File

@ -0,0 +1,69 @@
*, *::after, *::before {
box-sizing: border-box;
}
img {
vertical-align: middle;
}
html, body {
display: flex;
background-color: #e8e6e6;
height: 100%;
width: 100%;
padding: 0;
margin: 0;
font-family: sans-serif;
}
#list {
height: 100%;
overflow: auto;
width: 260px;
text-align: center;
}
#list img {
width: 200px;
padding: 10px;
border-radius: 10px;
margin: 15px 0;
cursor: pointer;
}
#list img.current {
background: #0003;
}
#image-container {
flex: auto;
height: 100vh;
background: #222;
color: #fff;
text-align: center;
cursor: pointer;
-webkit-user-select: none;
user-select: none;
position: relative;
}
#image-container #dest {
height: 100%;
width: 100%;
background-size: contain;
background-repeat: no-repeat;
background-position: center;
}
#image-container #page-num {
position: absolute;
font-size: 18pt;
left: 10px;
bottom: 5px;
font-weight: bold;
opacity: 0.75;
text-shadow: /* Duplicate the same shadow to make it very strong */
0 0 2px #222,
0 0 2px #222,
0 0 2px #222;
}