Compare commits

...

58 Commits

Author SHA1 Message Date
f6e9d08fc7 0.5.8 #343 2024-09-22 14:42:02 +08:00
9c1c2ea069 improve download logic #343 2024-09-22 14:39:32 +08:00
984ae4262c generate_metadata_file no need to use parse_doujinshi_obj 2024-09-22 14:11:55 +08:00
cbf9448ed9 improve #342 2024-09-22 13:35:07 +08:00
16bac45f02 generate html viewer automatically after download #342 2024-09-22 12:30:55 +08:00
7fa9193112 fix: non-image files in pdf conversion causing crash 2024-09-22 02:05:32 +00:00
a05a308e71 fix: check if metadata file is downloaded before skipping 2024-09-22 01:39:40 +00:00
5a29eaf775 fix: add file_type check to downloader
If you wanted to generate both .cbz and .pdf, the .pdf will be skipped if .cbz was generated first.
2024-09-22 01:38:54 +00:00
497eb6fe50 fix: remove warning for folder already exists in downloader
Nothing is wrong with the folder already existing -- silently ignore and move on. Might still have other files inside that haven't been downloaded yet.
2024-09-22 01:00:06 +00:00
4bfe104714 refactor: de-dupe doujinshi_obj parsers 2024-09-22 00:44:06 +00:00
12364e980c fix process continuing despite cbz download request skipped 2024-09-22 00:43:10 +00:00
b51e812449 fix #330 2024-09-21 11:49:22 +08:00
0ed5fa1931 fix #320 2024-09-21 00:43:14 +08:00
7f655b0f10 fix #295 2024-09-21 00:32:10 +08:00
dec3f44542 add some debug hack 2024-09-21 00:21:01 +08:00
40072a8483 0.5.7 2024-09-21 00:00:04 +08:00
f97469259d fix #331 2024-09-20 23:59:34 +08:00
ec608cc741 fix workflow docker issue 2024-09-20 23:58:25 +08:00
30e2814fe2 update version number in pyproject.toml 2024-09-20 23:57:10 +08:00
da298e1fe7 Merge pull request #312 from RicterZ/dependabot/pip/idna-3.7
Bump idna from 3.4 to 3.7
2024-09-20 23:56:25 +08:00
51d43ddde0 Merge branch 'master' into dependabot/pip/idna-3.7 2024-09-20 23:56:18 +08:00
c734881fc7 Merge pull request #316 from RicterZ/dependabot/pip/requests-2.32.0
Bump requests from 2.31.0 to 2.32.0
2024-09-20 23:55:33 +08:00
8d5803a45e Merge branch 'master' into dependabot/pip/requests-2.32.0 2024-09-20 23:55:28 +08:00
b441085b45 Merge pull request #318 from RicterZ/dependabot/pip/urllib3-1.26.19
Bump urllib3 from 1.26.18 to 1.26.19
2024-09-20 23:55:08 +08:00
132b26f8c4 Merge branch 'master' into dependabot/pip/urllib3-1.26.19 2024-09-20 23:54:57 +08:00
a0dc952fd3 Merge pull request #319 from RicterZ/dependabot/pip/certifi-2024.7.4
Bump certifi from 2022.12.7 to 2024.7.4
2024-09-20 23:54:18 +08:00
2bd862777b fix #333 2024-09-20 23:53:26 +08:00
35c55503fa 0.5.6 2024-09-20 23:39:38 +08:00
29aac84d53 fix #336 2024-09-20 23:34:26 +08:00
4ed4523782 fix #341 2024-09-20 23:27:37 +08:00
4223326c13 Merge pull request #340 from vglint/patch-3
Fix gallery search for folders with underscore
2024-09-14 10:17:57 +08:00
a248ff98c4 Fix gallery search for folders with underscore
Gallery title names replace '_' in the folder name with ' ' (generate_main_html()). To match against these title names when searching, we must also replace '_' with ' ' for each folder name we add to the list of titles to unhide.
2024-09-13 15:56:01 -07:00
021f17d229 Merge pull request #321 from PenitentMonke/xdg-base-dir
Adhere to XDG base dir spec on Linux
2024-07-08 22:03:38 +08:00
4162eabe93 Adhere to XDG base dir spec on Linux
Change how NHENTAI_HOME is set to follow the XDG Base Directory
Specification where possible, when running on Linux.

ISSUE: 299
2024-07-07 02:40:33 -03:00
c75e9efb21 Bump certifi from 2022.12.7 to 2024.7.4
Bumps [certifi](https://github.com/certifi/python-certifi) from 2022.12.7 to 2024.7.4.
- [Commits](https://github.com/certifi/python-certifi/compare/2022.12.07...2024.07.04)

---
updated-dependencies:
- dependency-name: certifi
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-07-05 21:52:23 +00:00
f2dec5c2a3 Bump urllib3 from 1.26.18 to 1.26.19
Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.18 to 1.26.19.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/1.26.19/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/1.26.18...1.26.19)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-06-18 01:35:13 +00:00
845a0d5659 ---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-05-21 05:39:26 +00:00
03d85c4e5d Bump idna from 3.4 to 3.7
Bumps [idna](https://github.com/kjd/idna) from 3.4 to 3.7.
- [Release notes](https://github.com/kjd/idna/releases)
- [Changelog](https://github.com/kjd/idna/blob/master/HISTORY.rst)
- [Commits](https://github.com/kjd/idna/compare/v3.4...v3.7)

---
updated-dependencies:
- dependency-name: idna
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-04-12 02:06:40 +00:00
dc54a43610 Merge pull request #311 from RicterZ/dev
Dev merge to master
2024-03-28 17:56:28 +08:00
4ecffaff55 Merge pull request #310 from Spyridion/dev
Changed parser option checks to allow artist search
2024-03-28 17:42:42 +08:00
457f12d40d Changed parser option checks to allow artist search 2024-03-28 02:40:14 -07:00
499081a9cd Merge pull request #306 from myc1ou1d/dev
fix file not found error when cbz file exists.
2024-02-25 00:37:32 +08:00
53aa04af1e fix file not found error when cbz file exists. 2024-02-24 23:27:52 +08:00
473f948565 update 2024-02-20 10:28:54 +08:00
f701485840 remove print 2024-02-20 10:27:34 +08:00
d8e4f50609 support #291 2024-02-20 10:25:44 +08:00
a893f54da1 0.5.4 2023-12-28 17:46:40 +08:00
4e307911ce Merge pull request #297 from RicterZ/dependabot/pip/urllib3-1.26.18
Bump urllib3 from 1.26.14 to 1.26.18
2023-12-28 17:46:07 +08:00
f9b7f828a5 fix #298 2023-12-28 17:45:37 +08:00
092df9e539 Bump urllib3 from 1.26.14 to 1.26.18
Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.14 to 1.26.18.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/1.26.14...1.26.18)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-10-17 23:59:22 +00:00
8d74866abf Update README.rst 2023-08-21 21:47:07 +08:00
bc5b7f982d Merge pull request #294 from edgar1016/master
Added --move-to-folder
2023-08-19 19:13:38 +08:00
e54f3cbd06 Added --move-to-folder 2023-08-18 18:30:14 -07:00
a31c615259 Merge pull request #284 from RicterZ/dependabot/pip/requests-2.31.0
Bump requests from 2.28.2 to 2.31.0
2023-05-25 20:40:59 +08:00
cf0b76204d Bump requests from 2.28.2 to 2.31.0
Bumps [requests](https://github.com/psf/requests) from 2.28.2 to 2.31.0.
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](https://github.com/psf/requests/compare/v2.28.2...v2.31.0)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-05-23 06:19:34 +00:00
17402623c4 Merge pull request #282 from edgar1016/master
--page-all works with favorites
2023-04-22 13:06:40 +08:00
a1a310f06b --page-all works with favorites 2023-04-21 22:00:00 -07:00
57673da762 update version 2023-03-28 21:02:47 +08:00
14 changed files with 235 additions and 140 deletions

View File

@ -11,6 +11,8 @@ nhentai
nhentai is a CLI tool for downloading doujinshi from `nhentai.net <https://nhentai.net>`_
GUI version: `https://github.com/edgar1016/nhentai-GUI <https://github.com/edgar1016/nhentai-GUI>`_
===================
Manual Installation
===================
@ -200,6 +202,8 @@ Other options:
-P, --pdf generate PDF file
--rm-origin-dir remove downloaded doujinshi dir when generated CBZ or
PDF file
--move-to-folder remove files in doujinshi dir then move new file to folder
when generated CBZ or PDF file
--meta generate a metadata file in doujinshi format
--regenerate-cbz regenerate the cbz file if exists

View File

@ -1,3 +1,3 @@
__version__ = '0.5.3'
__version__ = '0.5.8'
__author__ = 'RicterZ'
__email__ = 'ricterzheng@gmail.com'

View File

@ -73,6 +73,8 @@ def cmd_parser():
help='search doujinshi by keyword')
parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
help='list or download your favorites')
parser.add_option('--artist', '-a', action='store', dest='artist',
help='list doujinshi by artist name')
# page options
parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
@ -112,10 +114,12 @@ def cmd_parser():
help='generate PDF file')
parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
help='remove downloaded doujinshi dir when generated CBZ or PDF file')
parser.add_option('--move-to-folder', dest='move_to_folder', action='store_true', default=False,
help='remove files in doujinshi dir then move new file to folder when generated CBZ or PDF file')
parser.add_option('--meta', dest='generate_metadata', action='store_true',
help='generate a metadata file in doujinshi format')
parser.add_option('--regenerate-cbz', dest='regenerate_cbz', action='store_true', default=False,
help='regenerate the cbz file if exists')
parser.add_option('--regenerate', dest='regenerate', action='store_true', default=False,
help='regenerate the cbz or pdf file if exists')
# nhentai options
parser.add_option('--cookie', type='str', dest='cookie', action='store',
@ -209,12 +213,12 @@ def cmd_parser():
_ = [i.strip() for i in f.readlines()]
args.id = set(int(i) for i in _ if i.isdigit())
if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites:
if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites and not args.artist:
logger.critical('Doujinshi id(s) are required for downloading')
parser.print_help()
sys.exit(1)
if not args.keyword and not args.id and not args.favorites:
if not args.keyword and not args.id and not args.favorites and not args.artist:
parser.print_help()
sys.exit(1)

View File

@ -11,7 +11,7 @@ from nhentai.doujinshi import Doujinshi
from nhentai.downloader import Downloader
from nhentai.logger import logger
from nhentai.constant import BASE_URL
from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata_file, \
paging, check_cookie, signal_handler, DB
@ -46,7 +46,7 @@ def main():
if not options.is_download:
logger.warning('You do not specify --download option')
doujinshis = favorites_parser(page=page_list)
doujinshis = favorites_parser() if options.page_all else favorites_parser(page=page_list)
elif options.keyword:
if constant.CONFIG['language']:
@ -57,6 +57,10 @@ def main():
doujinshis = _search_parser(options.keyword, sorting=options.sorting, page=page_list,
is_page_all=options.page_all)
elif options.artist:
doujinshis = legacy_search_parser(options.artist, sorting=options.sorting, page=page_list,
is_page_all=options.page_all, type_='ARTIST')
elif not doujinshi_ids:
doujinshi_ids = options.id
@ -83,22 +87,29 @@ def main():
if not options.dryrun:
doujinshi.downloader = downloader
doujinshi.download(regenerate_cbz=options.regenerate_cbz)
if doujinshi.check_if_need_download(options):
doujinshi.download()
else:
logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {doujinshi.name}')
if options.generate_metadata:
table = doujinshi.table
generate_metadata_file(options.output_dir, table, doujinshi)
generate_metadata_file(options.output_dir, doujinshi)
if options.is_save_download_history:
with DB() as db:
db.add_one(doujinshi.id)
if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
if not options.is_nohtml:
generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
elif options.is_pdf:
generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
if options.is_cbz:
generate_doc('cbz', options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder,
options.regenerate)
if options.is_pdf:
generate_doc('pdf', options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder,
options.regenerate)
if options.main_viewer:
generate_main_html(options.output_dir)

View File

@ -3,6 +3,23 @@ import os
import tempfile
from urllib.parse import urlparse
from platform import system
def get_nhentai_home() -> str:
home = os.getenv('HOME', tempfile.gettempdir())
if system() == 'Linux':
xdgdat = os.getenv('XDG_DATA_HOME')
if xdgdat and os.path.exists(os.path.join(xdgdat, 'nhentai')):
return os.path.join(xdgdat, 'nhentai')
if home and os.path.exists(os.path.join(home, '.nhentai')):
return os.path.join(home, '.nhentai')
if xdgdat:
return os.path.join(xdgdat, 'nhentai')
# Use old default path in other systems
return os.path.join(home, '.nhentai')
DEBUG = os.getenv('DEBUG', False)
@ -11,15 +28,22 @@ BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
DETAIL_URL = f'{BASE_URL}/g'
LEGACY_SEARCH_URL = f'{BASE_URL}/search/'
SEARCH_URL = f'{BASE_URL}/api/galleries/search'
ARTIST_URL = f'{BASE_URL}/artist/'
TAG_API_URL = f'{BASE_URL}/api/galleries/tagged'
LOGIN_URL = f'{BASE_URL}/login/'
CHALLENGE_URL = f'{BASE_URL}/challenge'
FAV_URL = f'{BASE_URL}/favorites/'
IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
IMAGE_URL_MIRRORS = [
f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}'
f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}'
f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}'
]
NHENTAI_HOME = get_nhentai_home()
NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
@ -30,7 +54,8 @@ CONFIG = {
'cookie': '',
'language': '',
'template': '',
'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
'max_filename': 85
}
LANGUAGE_ISO = {

View File

@ -1,4 +1,5 @@
# coding: utf-8
import os
from tabulate import tabulate
@ -55,6 +56,7 @@ class Doujinshi(object):
['Parodies', self.info.parodies],
['Doujinshi', self.name],
['Subtitle', self.info.subtitle],
['Date', self.info.date],
['Characters', self.info.characters],
['Authors', self.info.artists],
['Groups', self.info.groups],
@ -70,7 +72,33 @@ class Doujinshi(object):
def show(self):
logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
def download(self, regenerate_cbz=False):
def check_if_need_download(self, options):
base_path = os.path.join(self.downloader.path, self.filename)
# doujinshi directory is not exist, we need to download definitely
if not (os.path.exists(base_path) and os.path.isdir(base_path)):
return True
# regenerate, we need to re-download from nhentai
if options.regenerate:
return True
if options.is_pdf:
file_ext = 'pdf'
elif options.is_cbz:
file_ext = 'cbz'
else:
# re-download
return True
# pdf or cbz file exists, we needn't to re-download it
if os.path.exists(f'{base_path}.{file_ext}') or os.path.exists(f'{base_path}/{self.filename}.{file_ext}'):
return False
# fallback
return True
def download(self):
logger.info(f'Starting to download doujinshi: {self.name}')
if self.downloader:
download_queue = []
@ -80,9 +108,10 @@ class Doujinshi(object):
for i in range(1, min(self.pages, len(self.ext)) + 1):
download_queue.append(f'{IMAGE_URL}/{self.img_id}/{i}.{self.ext[i-1]}')
self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
return self.downloader.start_download(download_queue, self.filename)
else:
logger.critical('Downloader has not been loaded')
return False
if __name__ == '__main__':

View File

@ -57,7 +57,7 @@ class Downloader(Singleton):
save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
try:
if os.path.exists(save_file_path):
logger.warning(f'Ignored exists file: {save_file_path}')
logger.warning(f'Skipped download: {save_file_path} already exists')
return 1, url
response = None
@ -67,10 +67,14 @@ class Downloader(Singleton):
try:
response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
if response.status_code != 200:
raise NHentaiImageNotExistException
except NHentaiImageNotExistException as e:
raise e
path = urlparse(url).path
for mirror in constant.IMAGE_URL_MIRRORS:
print(f'{mirror}{path}')
mirror_url = f'{mirror}{path}'
response = request('get', mirror_url, stream=True,
timeout=self.timeout, proxies=proxy)
if response.status_code == 200:
break
except Exception as e:
i += 1
@ -111,18 +115,13 @@ class Downloader(Singleton):
return 1, url
def start_download(self, queue, folder='', regenerate_cbz=False):
def start_download(self, queue, folder='') -> bool:
if not isinstance(folder, (str, )):
folder = str(folder)
if self.path:
folder = os.path.join(self.path, folder)
if os.path.exists(folder + '.cbz'):
if not regenerate_cbz:
logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
return
logger.info(f'Doujinshi will be saved at "{folder}"')
if not os.path.exists(folder):
try:
@ -130,9 +129,9 @@ class Downloader(Singleton):
except EnvironmentError as e:
logger.critical(str(e))
else:
logger.warning(f'Path "{folder}" already exist.')
if os.getenv('DEBUG', None) == 'NODOWNLOAD':
# Assuming we want to continue with rest of process.
return True
queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
pool = multiprocessing.Pool(self.size, init_worker)
@ -141,6 +140,8 @@ class Downloader(Singleton):
pool.close()
pool.join()
return True
def download_wrapper(obj, url, folder='', proxy=None):
if sys.platform == 'darwin' or semaphore.get_value():

View File

@ -135,6 +135,7 @@ def doujinshi_parser(id_, counter=0):
logger.warning(f'Error: {e}, ignored')
return None
# print(response)
html = BeautifulSoup(response, 'html.parser')
doujinshi_info = html.find('div', attrs={'id': 'info'})
@ -240,13 +241,21 @@ def print_doujinshi(doujinshi_list):
print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
def legacy_search_parser(keyword, sorting, page, is_page_all=False):
def legacy_search_parser(keyword, sorting, page, is_page_all=False, type_='SEARCH'):
logger.info(f'Searching doujinshis of keyword {keyword}')
result = []
if type_ not in ('SEARCH', 'ARTIST', ):
raise ValueError('Invalid type')
if is_page_all:
response = request('get', url=constant.LEGACY_SEARCH_URL,
params={'q': keyword, 'page': 1, 'sort': sorting}).content
if type_ == 'SEARCH':
response = request('get', url=constant.LEGACY_SEARCH_URL,
params={'q': keyword, 'page': 1, 'sort': sorting}).content
else:
url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
response = request('get', url=url, params={'page': 1}).content
html = BeautifulSoup(response, 'lxml')
pagination = html.find(attrs={'class': 'pagination'})
last_page = pagination.find(attrs={'class': 'last'})
@ -258,8 +267,13 @@ def legacy_search_parser(keyword, sorting, page, is_page_all=False):
for p in pages:
logger.info(f'Fetching page {p} ...')
response = request('get', url=constant.LEGACY_SEARCH_URL,
params={'q': keyword, 'page': p, 'sort': sorting}).content
if type_ == 'SEARCH':
response = request('get', url=constant.LEGACY_SEARCH_URL,
params={'q': keyword, 'page': p, 'sort': sorting}).content
else:
url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
response = request('get', url=url, params={'page': p}).content
if response is None:
logger.warning(f'No result in response in page {p}')
continue
@ -313,7 +327,9 @@ def search_parser(keyword, sorting, page, is_page_all=False):
for row in response['result']:
title = row['title']['english']
title = title[:85] + '..' if len(title) > 85 else title
title = title[:constant.CONFIG['max_filename']] + '..' if \
len(title) > constant.CONFIG['max_filename'] else title
result.append({'id': row['id'], 'title': title})
not_exists_persist = False

View File

@ -22,7 +22,7 @@ def serialize_json(doujinshi, output_dir):
metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
if doujinshi.info.languages:
metadata['language'] = [i.strip() for i in doujinshi.info.languages.split(',')]
metadata['category'] = doujinshi.info.categories
metadata['category'] = [i.strip() for i in doujinshi.info.categories.split(',')]
metadata['URL'] = doujinshi.url
metadata['Pages'] = doujinshi.pages

View File

@ -5,14 +5,16 @@ import re
import os
import zipfile
import shutil
import requests
import sqlite3
import urllib.parse
from typing import Optional, Tuple
from nhentai import constant
from nhentai.logger import logger
from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
MAX_FIELD_LENGTH = 100
@ -38,7 +40,8 @@ def check_cookie():
username = re.findall('"/users/[0-9]+/(.*?)"', response.text)
if not username:
logger.warning('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
logger.warning(
'Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
else:
logger.log(16, f'Login successfully! Your username: {username[0]}')
@ -64,13 +67,31 @@ def readfile(path):
return file.read()
def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
image_html = ''
def parse_doujinshi_obj(
output_dir: str,
doujinshi_obj=None,
file_type: str = ''
) -> Tuple[str, str]:
filename = './doujinshi' + file_type
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
else:
doujinshi_dir = '.'
_filename = f'{doujinshi_obj.filename}.{file_type}'
if file_type == 'cbz':
serialize_comic_xml(doujinshi_obj, doujinshi_dir)
if file_type == 'pdf':
_filename = _filename.replace('/', '-')
filename = os.path.join(output_dir, _filename)
return doujinshi_dir, filename
def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '.html')
image_html = ''
if not os.path.exists(doujinshi_dir):
logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
@ -148,7 +169,7 @@ def generate_main_html(output_dir='./'):
else:
title = 'nHentai HTML Viewer'
image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
image_html += element.format(FOLDER=urllib.parse.quote(folder), IMAGE=image, TITLE=title)
if image_html == '':
logger.warning('No index.html found, --gen-main paused.')
return
@ -158,68 +179,65 @@ def generate_main_html(output_dir='./'):
f.write(data.encode('utf-8'))
shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
set_js_database()
logger.log(16, f'Main Viewer has been written to "{output_dir}main.html"')
output_dir = output_dir[:-1] if output_dir.endswith('/') else output_dir
logger.log(16, f'Main Viewer has been written to "{output_dir}/main.html"')
except Exception as e:
logger.warning(f'Writing Main Viewer failed ({e})')
def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True):
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
if write_comic_info:
serialize_comic_xml(doujinshi_obj, doujinshi_dir)
cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), f'{doujinshi_obj.filename}.cbz')
else:
cbz_filename = './doujinshi.cbz'
doujinshi_dir = '.'
def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, rm_origin_dir=False,
move_to_folder=False, regenerate=False):
file_list = os.listdir(doujinshi_dir)
file_list.sort()
doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
logger.info(f'Writing CBZ file to path: {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 os.path.exists(f'{doujinshi_dir}.{file_type}') and not regenerate:
logger.info(f'Skipped {file_type} file generation: {doujinshi_dir}.{file_type} already exists')
return
if file_type == 'cbz':
file_list = os.listdir(doujinshi_dir)
file_list.sort()
logger.info(f'Writing CBZ file to path: {filename}')
with zipfile.ZipFile(filename, 'w') as cbz_pf:
for image in file_list:
image_path = os.path.join(doujinshi_dir, image)
cbz_pf.write(image_path, image)
logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
elif file_type == 'pdf':
try:
import img2pdf
"""Write images to a PDF file using img2pdf."""
file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif'))]
file_list.sort()
logger.info(f'Writing PDF file to path: {filename}')
with open(filename, 'wb') as pdf_f:
full_path_list = (
[os.path.join(doujinshi_dir, image) for image in file_list]
)
pdf_f.write(img2pdf.convert(full_path_list, rotation=img2pdf.Rotation.ifvalid))
logger.log(16, f'PDF file has been written to "{filename}"')
except ImportError:
logger.error("Please install img2pdf package by using pip.")
if rm_origin_dir:
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(16, f'Comic Book CBZ file has been written to "{doujinshi_dir}"')
if move_to_folder:
for filename in os.listdir(doujinshi_dir):
file_path = os.path.join(doujinshi_dir, filename)
if os.path.isfile(file_path):
try:
os.remove(file_path)
except Exception as e:
print(f"Error deleting file: {e}")
def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
try:
import img2pdf
"""Write images to a PDF file using img2pdf."""
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
pdf_filename = os.path.join(
os.path.join(doujinshi_dir, '..'),
f'{doujinshi_obj.filename}.pdf'
)
else:
pdf_filename = './doujinshi.pdf'
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
logger.info(f'Writing PDF file to path: {pdf_filename}')
with open(pdf_filename, 'wb') as pdf_f:
full_path_list = (
[os.path.join(doujinshi_dir, image) for image in file_list]
)
pdf_f.write(img2pdf.convert(full_path_list))
if rm_origin_dir:
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
except ImportError:
logger.error("Please install img2pdf package by using pip.")
shutil.move(filename, doujinshi_dir)
def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
@ -232,7 +250,7 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
# maybe you can use `--format` to select a suitable filename
if not _truncate_only:
ban_chars = '\\\'/:,;*?"<>|\t'
ban_chars = '\\\'/:,;*?"<>|\t\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b'
filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
filename = ' '.join(filename.split())
@ -275,17 +293,11 @@ def paging(page_string):
return page_list
def generate_metadata_file(output_dir, table, doujinshi_obj=None):
logger.info('Writing Metadata Info')
def generate_metadata_file(output_dir, doujinshi_obj):
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
else:
doujinshi_dir = '.'
info_txt_path = os.path.join(output_dir, doujinshi_obj.filename, 'info.txt')
logger.info(doujinshi_dir)
f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
f = open(info_txt_path, 'w', encoding='utf-8')
fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
@ -297,10 +309,11 @@ def generate_metadata_file(output_dir, table, doujinshi_obj=None):
for i in range(len(fields)):
f.write(f'{fields[i]}: ')
if fields[i] in special_fields:
f.write(str(table[special_fields.index(fields[i])][1]))
f.write(str(doujinshi_obj.table[special_fields.index(fields[i])][1]))
f.write('\n')
f.close()
logger.log(16, f'Metadata Info has been written to "{info_txt_path}"')
class DB(object):

View File

@ -139,7 +139,7 @@ function filter_searcher(){
break
}
}
if (verifier){doujinshi_id.push(data[i].Folder);}
if (verifier){doujinshi_id.push(data[i].Folder.replace("_", " "));}
}
var gallery = document.getElementsByClassName("gallery-favorite");
for (var i = 0; i < gallery.length; i++){
@ -174,4 +174,4 @@ function tag_maker(data){
document.getElementById("tags").appendChild(node);
}
}
}
}

43
poetry.lock generated
View File

@ -1,10 +1,9 @@
# This file is automatically @generated by Poetry 1.4.0 and should not be changed by hand.
# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
[[package]]
name = "beautifulsoup4"
version = "4.11.2"
description = "Screen-scraping library"
category = "main"
optional = false
python-versions = ">=3.6.0"
files = [
@ -21,21 +20,19 @@ lxml = ["lxml"]
[[package]]
name = "certifi"
version = "2022.12.7"
version = "2024.7.4"
description = "Python package for providing Mozilla's CA Bundle."
category = "main"
optional = false
python-versions = ">=3.6"
files = [
{file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"},
{file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
{file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"},
{file = "certifi-2024.7.4.tar.gz", hash = "sha256:5a1e7645bc0ec61a09e26c36f6106dd4cf40c6db3a1fb6352b0244e7fb057c7b"},
]
[[package]]
name = "charset-normalizer"
version = "3.0.1"
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
category = "main"
optional = false
python-versions = "*"
files = [
@ -131,21 +128,19 @@ files = [
[[package]]
name = "idna"
version = "3.4"
version = "3.7"
description = "Internationalized Domain Names in Applications (IDNA)"
category = "main"
optional = false
python-versions = ">=3.5"
files = [
{file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
{file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
{file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"},
{file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"},
]
[[package]]
name = "iso8601"
version = "1.1.0"
description = "Simple module to parse ISO 8601 dates"
category = "main"
optional = false
python-versions = ">=3.6.2,<4.0"
files = [
@ -155,21 +150,20 @@ files = [
[[package]]
name = "requests"
version = "2.28.2"
version = "2.32.0"
description = "Python HTTP for Humans."
category = "main"
optional = false
python-versions = ">=3.7, <4"
python-versions = ">=3.8"
files = [
{file = "requests-2.28.2-py3-none-any.whl", hash = "sha256:64299f4909223da747622c030b781c0d7811e359c37124b4bd368fb8c6518baa"},
{file = "requests-2.28.2.tar.gz", hash = "sha256:98b1b2782e3c6c4904938b84c0eb932721069dfdb9134313beff7c83c2df24bf"},
{file = "requests-2.32.0-py3-none-any.whl", hash = "sha256:f2c3881dddb70d056c5bd7600a4fae312b2a300e39be6a118d30b90bd27262b5"},
{file = "requests-2.32.0.tar.gz", hash = "sha256:fa5490319474c82ef1d2c9bc459d3652e3ae4ef4c4ebdd18a21145a47ca4b6b8"},
]
[package.dependencies]
certifi = ">=2017.4.17"
charset-normalizer = ">=2,<4"
idna = ">=2.5,<4"
urllib3 = ">=1.21.1,<1.27"
urllib3 = ">=1.21.1,<3"
[package.extras]
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
@ -179,7 +173,6 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
name = "soupsieve"
version = "2.4"
description = "A modern CSS selector implementation for Beautiful Soup."
category = "main"
optional = false
python-versions = ">=3.7"
files = [
@ -191,7 +184,6 @@ files = [
name = "tabulate"
version = "0.9.0"
description = "Pretty-print tabular data"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
@ -204,18 +196,17 @@ widechars = ["wcwidth"]
[[package]]
name = "urllib3"
version = "1.26.14"
version = "1.26.19"
description = "HTTP library with thread-safe connection pooling, file post, and more."
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
files = [
{file = "urllib3-1.26.14-py2.py3-none-any.whl", hash = "sha256:75edcdc2f7d85b137124a6c3c9fc3933cdeaa12ecb9a6a959f22797a0feca7e1"},
{file = "urllib3-1.26.14.tar.gz", hash = "sha256:076907bf8fd355cde77728471316625a4d2f7e713c125f51953bb5b3eecf4f72"},
{file = "urllib3-1.26.19-py2.py3-none-any.whl", hash = "sha256:37a0344459b199fce0e80b0d3569837ec6b6937435c5244e7fd73fa6006830f3"},
{file = "urllib3-1.26.19.tar.gz", hash = "sha256:3e3d753a8618b86d7de333b4223005f68720bcd6a7d2bcb9fbd2229ec7c1e429"},
]
[package.extras]
brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]

View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "nhentai"
version = "0.5.2"
version = "0.5.8"
description = "nhentai doujinshi downloader"
authors = ["Ricter Z <ricterzheng@gmail.com>"]
license = "MIT"

View File

@ -1,5 +1,6 @@
requests
soupsieve
setuptools
BeautifulSoup4
tabulate
iso8601