Compare commits

..

12 Commits

Author SHA1 Message Date
d74fd103f0 remove setup.py 2025-01-08 09:35:44 +08:00
0cb2411955 Merge branch 'master' of github.com:RicterZ/nhentai 2025-01-08 09:17:01 +08:00
de08d3daaa 0.5.17.1 2025-01-07 14:26:38 +08:00
946b85ace9 tiny fix 2024-12-21 09:32:33 +08:00
5bde24f159 remove debug print 2024-12-21 09:18:34 +08:00
3cae13e76f fix #363 2024-12-18 23:37:00 +08:00
7483b8f923 workaround of #359 2024-12-11 23:58:48 +08:00
eae42c8eb5 fix #356 2024-12-11 23:57:01 +08:00
b841747761 fix #356 2024-12-11 23:47:48 +08:00
1f3528afad try to fix #361 2024-12-09 14:36:44 +08:00
bb41e502c1 0.5.17 for fix #360 2024-12-09 09:26:33 +08:00
7089144ac6 fix #360 #359 2024-12-09 09:25:40 +08:00
12 changed files with 64 additions and 116 deletions

View File

@ -5,7 +5,7 @@ COPY requirements.txt ./
RUN pip install --no-cache-dir -r requirements.txt
COPY . .
RUN python setup.py install
RUN pip install .
WORKDIR /output
ENTRYPOINT ["nhentai"]

View File

@ -59,7 +59,7 @@ On Gentoo Linux:
.. code-block::
layman -fa glicOne
layman -fa glibOne
sudo emerge net-misc/nhentai
On NixOS:

View File

@ -1,3 +1,3 @@
__version__ = '0.5.15'
__version__ = '0.5.17.2'
__author__ = 'RicterZ'
__email__ = 'ricterzheng@gmail.com'

View File

@ -37,7 +37,7 @@ def write_config():
f.write(json.dumps(constant.CONFIG))
def callback(option, opt_str, value, parser):
def callback(option, _opt_str, _value, parser):
if option == '--id':
pass
value = []

View File

@ -57,7 +57,7 @@ class Doujinshi(object):
self.table = [
['Parodies', self.info.parodies],
['Doujinshi', self.name],
['Title', self.name],
['Subtitle', self.info.subtitle],
['Date', self.info.date],
['Characters', self.info.characters],

View File

@ -13,6 +13,7 @@ from nhentai.utils import Singleton, async_request
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
class NHentaiImageNotExistException(Exception):
pass
@ -32,13 +33,14 @@ def download_callback(result):
logger.log(16, f'{data} downloaded successfully')
class Downloader(Singleton):
def __init__(self, path='', threads=5, timeout=30, delay=0):
self.threads = threads
self.path = str(path)
self.timeout = timeout
self.delay = delay
self.folder = None
self.semaphore = None
async def fiber(self, tasks):
self.semaphore = asyncio.Semaphore(self.threads)
@ -49,18 +51,19 @@ class Downloader(Singleton):
except Exception as e:
logger.error(f'An error occurred: {e}')
async def _semaphore_download(self, *args, **kwargs):
async with self.semaphore:
return await self.download(*args, **kwargs)
async def download(self, url, folder='', filename='', retried=0, proxy=None):
async def download(self, url, folder='', filename='', retried=0, proxy=None, length=0):
logger.info(f'Starting to download {url} ...')
if self.delay:
await asyncio.sleep(self.delay)
filename = filename if filename else os.path.basename(urlparse(url).path)
base_filename, extension = os.path.splitext(filename)
filename = base_filename.zfill(length) + extension
save_file_path = os.path.join(self.folder, filename)
@ -129,7 +132,6 @@ class Downloader(Singleton):
f.write(chunk)
return True
def start_download(self, queue, folder='') -> bool:
if not isinstance(folder, (str,)):
folder = str(folder)
@ -149,9 +151,9 @@ class Downloader(Singleton):
# Assuming we want to continue with rest of process.
return True
digit_length = len(str(len(queue)))
coroutines = [
self._semaphore_download(url, filename=os.path.basename(urlparse(url).path))
self._semaphore_download(url, filename=os.path.basename(urlparse(url).path), length=digit_length)
for url in queue
]

View File

@ -135,18 +135,20 @@ 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'})
title = doujinshi_info.find('h1').text
pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
subtitle = doujinshi_info.find('h2')
favorite_counts = doujinshi_info.find('span', class_='nobold').find('span', class_='count').text.strip()
favorite_counts = str(doujinshi_info.find('span', class_='nobold').find('span', class_='count'))
if favorite_counts is None:
favorite_counts = '0'
doujinshi['name'] = title
doujinshi['pretty_name'] = pretty_name
doujinshi['subtitle'] = subtitle.text if subtitle else ''
doujinshi['favorite_counts'] = favorite_counts
doujinshi['favorite_counts'] = favorite_counts.strip()
doujinshi_cover = html.find('div', attrs={'id': 'cover'})
img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
@ -158,8 +160,8 @@ def doujinshi_parser(id_, counter=0):
ext.append(ext_name)
if not img_id:
logger.critical('Tried yo get image id failed')
sys.exit(1)
logger.critical(f'Tried yo get image id failed of id: {id_}')
return None
doujinshi['img_id'] = img_id.group(1)
doujinshi['ext'] = ext
@ -186,53 +188,6 @@ def doujinshi_parser(id_, counter=0):
return doujinshi
def legacy_doujinshi_parser(id_):
if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
raise Exception(f'Doujinshi id({id_}) is not valid')
id_ = int(id_)
logger.info(f'Fetching information of doujinshi id {id_}')
doujinshi = dict()
doujinshi['id'] = id_
url = f'{constant.DETAIL_URL}/{id_}'
i = 0
while 5 > i:
try:
response = request('get', url).json()
except Exception as e:
i += 1
if not i < 5:
logger.critical(str(e))
sys.exit(1)
continue
break
doujinshi['name'] = response['title']['english']
doujinshi['subtitle'] = response['title']['japanese']
doujinshi['img_id'] = response['media_id']
doujinshi['ext'] = ''.join([i['t'] for i in response['images']['pages']])
doujinshi['pages'] = len(response['images']['pages'])
# gain information of the doujinshi
needed_fields = ['character', 'artist', 'language', 'tag', 'parody', 'group', 'category']
for tag in response['tags']:
tag_type = tag['type']
if tag_type in needed_fields:
if tag_type == 'tag':
if tag_type not in doujinshi:
doujinshi[tag_type] = {}
tag['name'] = tag['name'].replace(' ', '-')
tag['name'] = tag['name'].lower()
doujinshi[tag_type][tag['name']] = tag['id']
elif tag_type not in doujinshi:
doujinshi[tag_type] = tag['name']
else:
doujinshi[tag_type] += ', ' + tag['name']
return doujinshi
def print_doujinshi(doujinshi_list):
if not doujinshi_list:
return

View File

@ -5,13 +5,13 @@ import re
import os
import zipfile
import shutil
import copy
import httpx
import requests
import sqlite3
import urllib.parse
from typing import Optional, Tuple
from typing import Tuple
from requests.structures import CaseInsensitiveDict
from nhentai import constant
from nhentai.logger import logger
@ -277,7 +277,7 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
It used to be a whitelist approach allowed only alphabet and a part of symbols.
but most doujinshi's names include Japanese 2-byte characters and these was rejected.
so it is using blacklist approach now.
if filename include forbidden characters (\'/:,;*?"<>|) ,it replace space character(' ').
if filename include forbidden characters (\'/:,;*?"<>|) ,it replaces space character(" ").
"""
# maybe you can use `--format` to select a suitable filename
@ -300,7 +300,7 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
return filename
def signal_handler(signal, frame):
def signal_handler(_signal, _frame):
logger.error('Ctrl-C signal received. Stopping...')
sys.exit(1)
@ -335,14 +335,14 @@ def generate_metadata_file(output_dir, doujinshi_obj):
'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
'SERIES', 'PARODY', 'URL']
special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'DATE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
'LANGUAGE', 'TAGS', 'URL', 'PAGES']
for i in range(len(fields)):
f.write(f'{fields[i]}: ')
if fields[i] in special_fields:
f.write(str(doujinshi_obj.table[special_fields.index(fields[i])][1]))
f.write('\n')
temp_dict = CaseInsensitiveDict(dict(doujinshi_obj.table))
for i in fields:
v = temp_dict.get(i)
v = temp_dict.get(f'{i}s') if v is None else v
v = doujinshi_obj.info.get(i.lower(), None) if v is None else v
v = doujinshi_obj.info.get(f'{i.lower()}s', "Unknown") if v is None else v
f.write(f'{i}: {v}\n')
f.close()
logger.log(16, f'Metadata Info has been written to "{info_txt_path}"')

View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "nhentai"
version = "0.5.15"
version = "0.5.17.2"
description = "nhentai doujinshi downloader"
authors = ["Ricter Z <ricterzheng@gmail.com>"]
license = "MIT"
@ -20,3 +20,6 @@ httpx = "0.27.2"
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"
[tool.poetry.scripts]
nhentai = 'nhentai.command:main'

29
qodana.yaml Executable file
View File

@ -0,0 +1,29 @@
#-------------------------------------------------------------------------------#
# Qodana analysis is configured by qodana.yaml file #
# https://www.jetbrains.com/help/qodana/qodana-yaml.html #
#-------------------------------------------------------------------------------#
version: "1.0"
#Specify inspection profile for code analysis
profile:
name: qodana.starter
#Enable inspections
#include:
# - name: <SomeEnabledInspectionId>
#Disable inspections
#exclude:
# - name: <SomeDisabledInspectionId>
# paths:
# - <path/where/not/run/inspection>
#Execute shell command before Qodana execution (Applied in CI/CD pipeline)
#bootstrap: sh ./prepare-qodana.sh
#Install IDE plugins before Qodana execution (Applied in CI/CD pipeline)
#plugins:
# - id: <plugin.id> #(plugin id can be found at https://plugins.jetbrains.com)
#Specify Qodana linter for analysis (Applied in CI/CD pipeline)
linter: jetbrains/qodana-python:2024.3

View File

@ -1,3 +0,0 @@
[metadata]
description_file = README.rst

View File

@ -1,38 +0,0 @@
# coding: utf-8
import codecs
from setuptools import setup, find_packages
from nhentai import __version__, __author__, __email__
with open('requirements.txt') as f:
requirements = [l for l in f.read().splitlines() if l]
def long_description():
with codecs.open('README.rst', 'rb') as readme:
return readme.read().decode('utf-8')
setup(
name='nhentai',
version=__version__,
packages=find_packages(),
author=__author__,
author_email=__email__,
keywords=['nhentai', 'doujinshi', 'downloader'],
description='nhentai.net doujinshis downloader',
long_description=long_description(),
url='https://github.com/RicterZ/nhentai',
download_url='https://github.com/RicterZ/nhentai/tarball/master',
include_package_data=True,
zip_safe=False,
install_requires=requirements,
entry_points={
'console_scripts': [
'nhentai = nhentai.command:main',
]
},
license='MIT',
)