NussNougate/nhentai
4
0
Fork 0
mirror of https://github.com/RicterZ/nhentai.git synced 2025-05-05 11:00:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

remove \r

Browse Source
This commit is contained in:
Ricter Z 2018-08-11 09:28:39 +08:00
parent 4577e9df9a
commit 14b3c82248
5 changed files with 468 additions and 468 deletions

6
nhentai/__init__.py

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

240
nhentai/cmdline.py

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

144
nhentai/command.py

@ -1,72 +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, generate_cbz 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()
if not options.is_nohtml and not options.is_cbz: if not options.is_nohtml and not options.is_cbz:
generate_html(options.output_dir, doujinshi) generate_html(options.output_dir, doujinshi)
elif options.is_cbz: elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi) generate_cbz(options.output_dir, doujinshi)
if not platform.system() == 'Windows': if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.') logger.log(15, '🍻 All done.')
else: else:
logger.log(15, 'All done.') logger.log(15, 'All done.')
else: else:
[doujinshi.show() for doujinshi in doujinshi_list] [doujinshi.show() for doujinshi in doujinshi_list]
def signal_handler(signal, frame): def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Quit.') logger.error('Ctrl-C signal received. Quit.')
exit(1) exit(1)
signal.signal(signal.SIGINT, signal_handler) signal.signal(signal.SIGINT, signal_handler)
if __name__ == '__main__': if __name__ == '__main__':
main() main()

316
nhentai/parser.py

@ -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')
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')
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"))

230
nhentai/utils.py

@ -1,115 +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
import zipfile import zipfile
import shutil import shutil
from nhentai.logger import logger from nhentai.logger import logger
class _Singleton(type): class _Singleton(type):
""" A metaclass that creates a Singleton base class when called. """ """ A metaclass that creates a Singleton base class when called. """
_instances = {} _instances = {}
def __call__(cls, *args, **kwargs): def __call__(cls, *args, **kwargs):
if cls not in cls._instances: if cls not in cls._instances:
cls._instances[cls] = super(_Singleton, cls).__call__(*args, **kwargs) cls._instances[cls] = super(_Singleton, cls).__call__(*args, **kwargs)
return cls._instances[cls] return cls._instances[cls]
class Singleton(_Singleton(str('SingletonMeta'), (object,), {})): class Singleton(_Singleton(str('SingletonMeta'), (object,), {})):
pass pass
def urlparse(url): def urlparse(url):
try: try:
from urlparse import urlparse from urlparse import urlparse
except ImportError: except ImportError:
from urllib.parse import urlparse from urllib.parse import urlparse
return urlparse(url) return urlparse(url)
def readfile(path): def readfile(path):
loc = os.path.dirname(__file__) loc = os.path.dirname(__file__)
with open(os.path.join(loc, path), 'r') as file: with open(os.path.join(loc, path), 'r') as file:
return file.read() return file.read()
def generate_html(output_dir='.', doujinshi_obj=None): def generate_html(output_dir='.', doujinshi_obj=None):
image_html = '' image_html = ''
if doujinshi_obj is not None: 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, format_filename('%s-%s' % (doujinshi_obj.id,
str(doujinshi_obj.name[:200])))) str(doujinshi_obj.name[:200]))))
else: else:
doujinshi_dir = '.' doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir) file_list = os.listdir(doujinshi_dir)
file_list.sort() file_list.sort()
for image in file_list: for image in file_list:
if not os.path.splitext(image)[1] in ('.jpg', '.png'): if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue continue
image_html += '<img src="{0}" class="image-item"/>\n'\ image_html += '<img src="{0}" class="image-item"/>\n'\
.format(image) .format(image)
html = readfile('viewer/index.html') html = readfile('viewer/index.html')
css = readfile('viewer/styles.css') css = readfile('viewer/styles.css')
js = readfile('viewer/scripts.js') js = readfile('viewer/scripts.js')
if doujinshi_obj is not None: if doujinshi_obj is not None:
title = doujinshi_obj.name title = doujinshi_obj.name
else: else:
title = 'nHentai HTML Viewer' title = 'nHentai HTML Viewer'
data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css) data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f: with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data) 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 generate_cbz(output_dir='.', doujinshi_obj=None): def generate_cbz(output_dir='.', doujinshi_obj=None):
if doujinshi_obj is not None: 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, format_filename('%s-%s' % (doujinshi_obj.id,
str(doujinshi_obj.name[:200])))) str(doujinshi_obj.name[:200]))))
cbz_filename = os.path.join(output_dir, format_filename('%s-%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])))) str(doujinshi_obj.name[:200]))))
else: else:
cbz_filename = './doujinshi.cbz' cbz_filename = './doujinshi.cbz'
doujinshi_dir = '.' doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir) file_list = os.listdir(doujinshi_dir)
file_list.sort() file_list.sort()
with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf: with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
for image in file_list: for image in file_list:
image_path = os.path.join(doujinshi_dir, image) image_path = os.path.join(doujinshi_dir, image)
cbz_pf.write(image_path, image) cbz_pf.write(image_path, image)
shutil.rmtree(doujinshi_dir, ignore_errors=True) shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(15, 'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir)) logger.log(15, 'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir))
def format_filename(s): def format_filename(s):
"""Take a string and return a valid filename constructed from the string. """Take a string and return a valid filename constructed from the string.
Uses a whitelist approach: any characters not present in valid_chars are Uses a whitelist approach: any characters not present in valid_chars are
removed. Also spaces are replaced with underscores. removed. Also spaces are replaced with underscores.
Note: this method may produce invalid filenames such as ``, `.` or `..` 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_' 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 and append a file extension like '.txt', so I avoid the potential of using
an invalid filename. 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 = ''.join(c for c in s if c in valid_chars)
filename = filename.replace(' ', '_') # I don't like spaces in filenames. filename = filename.replace(' ', '_') # I don't like spaces in filenames.
return filename return filename