0.5.19

fix favorite_counts output in metadata

Dockerfile

@@ -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"]

README.rst

@@ -59,7 +59,7 @@ On Gentoo Linux:
 
 .. code-block::
 
-    layman -fa glicOne
+    layman -fa glibOne
     sudo emerge net-misc/nhentai
 
 On NixOS:
@@ -129,7 +129,7 @@ Download your favorites with delay:
 
 .. code-block:: bash
 
-    nhentai --favorites --download --delay 1
+    nhentai --favorites --download --delay 1 --page 3-5,7
 
 Format output doujinshi folder name:
 

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.15'
+__version__ = '0.5.19'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -11,6 +11,7 @@ from optparse import OptionParser
 from nhentai import __version__
 from nhentai.utils import generate_html, generate_main_html, DB
 from nhentai.logger import logger
+from nhentai.constant import PATH_SEPARATOR
 
 
 def banner():
@@ -37,7 +38,7 @@ 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 = []
@@ -64,7 +65,8 @@ def cmd_parser():
     # operation options
     parser.add_option('--download', '-D', dest='is_download', action='store_true',
                       help='download doujinshi (for search results)')
-    parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
+    parser.add_option('--show', '-S', dest='is_show', action='store_true',
+                      help='just show the doujinshi information')
 
     # doujinshi options
     parser.add_option('--id', dest='id', action='callback', callback=callback,
@@ -79,14 +81,15 @@ def cmd_parser():
     # page options
     parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
                       help='all search results')
-    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='1',
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store',
                       help='page number of search results. e.g. 1,2-5,14')
     parser.add_option('--sorting', '--sort', dest='sorting', action='store', default='popular',
                       help='sorting of doujinshi (recent / popular / popular-[today|week])',
                       choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
-    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='./',
+    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store',
+                      default=f'.{PATH_SEPARATOR}',
                       help='output dir')
     parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
                       help='thread count for downloading doujinshi')
@@ -96,7 +99,8 @@ def cmd_parser():
                       help='slow down between downloading every doujinshi')
     parser.add_option('--proxy', type='string', dest='proxy', action='store',
                       help='store a proxy, for example: -p "http://127.0.0.1:1080"')
-    parser.add_option('--file', '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+    parser.add_option('--file', '-f', type='string', dest='file', action='store',
+                      help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
                       help='format the saved folder name', default='[%i][%a][%t]')
     parser.add_option('--dry-run', action='store_true', dest='dryrun', help='Dry run, skip file download')

nhentai/command.py

@@ -48,7 +48,7 @@ def main():
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshis = favorites_parser() if options.page_all else favorites_parser(page=page_list)
+        doujinshis = favorites_parser(page=page_list) if options.page else favorites_parser()
 
     elif options.keyword:
         if constant.CONFIG['language']:

nhentai/constant.py

@@ -35,11 +35,16 @@ LOGIN_URL = f'{BASE_URL}/login/'
 CHALLENGE_URL = f'{BASE_URL}/challenge'
 FAV_URL = f'{BASE_URL}/favorites/'
 
+PATH_SEPARATOR = os.path.sep
 
-IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
+
+IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i1.{urlparse(BASE_URL).hostname}/galleries'
 IMAGE_URL_MIRRORS = [
+    f'{urlparse(BASE_URL).scheme}://i2.{urlparse(BASE_URL).hostname}',
     f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i4.{urlparse(BASE_URL).hostname}',
     f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i6.{urlparse(BASE_URL).hostname}',
     f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}',
 ]
 

nhentai/doujinshi.py

@@ -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],
@@ -65,7 +65,7 @@ class Doujinshi(object):
             ['Groups', self.info.groups],
             ['Languages', self.info.languages],
             ['Tags', self.info.tags],
-            ['Favorite Counts', self.info.favorite_counts],
+            ['Favorite Counts', self.favorite_counts],
             ['URL', self.url],
             ['Pages', self.pages],
         ]

nhentai/downloader.py

@@ -13,6 +13,7 @@ from nhentai.utils import Singleton, async_request
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
+
 class NHentaiImageNotExistException(Exception):
     pass
 
@@ -32,35 +33,40 @@ 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)
         for completed_task in asyncio.as_completed(tasks):
             try:
                 result = await completed_task
-                logger.info(f'{result[1]} download completed')
+                if result[1]:
+                    logger.info(f'{result[1]} download completed')
+                else:
+                    logger.warning(f'{result[1]} download failed, return value {result[0]}')
             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)
 
@@ -82,11 +88,11 @@ class Downloader(Singleton):
 
             if not await self.save(filename, response):
                 logger.error(f'Can not download image {url}')
-                return 1, None
+                return 1, url
 
         except (httpx.HTTPStatusError, httpx.TimeoutException, httpx.ConnectError) as e:
             if retried < 3:
-                logger.info(f'Download {filename} failed, retrying({retried + 1}) times...')
+                logger.warning(f'Download {filename} failed, retrying({retried + 1}) times...')
                 return await self.download(
                     url=url,
                     folder=folder,
@@ -95,7 +101,8 @@ class Downloader(Singleton):
                     proxy=proxy,
                 )
             else:
-                return 0, None
+                logger.warning(f'Download {filename} failed with 3 times retried, skipped')
+                return 0, url
 
         except NHentaiImageNotExistException as e:
             os.remove(save_file_path)
@@ -107,10 +114,10 @@ class Downloader(Singleton):
             logger.error(f"Exception type: {type(e)}")
             traceback.print_stack()
             logger.critical(str(e))
-            return 0, None
+            return 0, url
 
         except KeyboardInterrupt:
-            return -3, None
+            return -3, url
 
         return 1, url
 
@@ -129,7 +136,6 @@ 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 +155,10 @@ class Downloader(Singleton):
             # Assuming we want to continue with rest of process.
             return True
 
-
+        digit_length = len(str(len(queue)))
+        logger.info(f'Total download pages: {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
         ]
 

nhentai/parser.py

@@ -135,31 +135,36 @@ 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 = doujinshi_info.find('span', class_='nobold').find('span', class_='count')
+
     doujinshi['name'] = title
     doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
-    doujinshi['favorite_counts'] = favorite_counts
+    doujinshi['favorite_counts'] = int(favorite_counts.text.strip()) if favorite_counts else 0
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
+    # img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
-                       doujinshi_cover.a.img.attrs['data-src'])
+    #                   doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search(r'/galleries/(\d+)/cover\.\w+$', doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):
-        _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
+        base_name = os.path.basename(i.img.attrs['data-src'])
-        ext.append(ext_name)
+        ext_name = base_name.split('.')
+        if len(ext_name) == 3:
+            ext.append(ext_name[1])
+        else:
+            ext.append(ext_name[-1])
 
     if not img_id:
-        logger.critical('Tried yo get image id failed')
+        logger.critical(f'Tried yo get image id failed of id: {id_}')
-        sys.exit(1)
+        return None
 
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
@@ -186,53 +191,6 @@ 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

nhentai/serializer.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 import json
 import os
+
+from nhentai.constant import PATH_SEPARATOR
 from xml.sax.saxutils import escape
 from nhentai.constant import LANGUAGE_ISO
 
@@ -82,7 +84,7 @@ def xml_write_simple_tag(f, name, val, indent=1):
 
 def merge_json():
     lst = []
-    output_dir = "./"
+    output_dir = f".{PATH_SEPARATOR}"
     os.chdir(output_dir)
     doujinshi_dirs = next(os.walk('.'))[1]
     for folder in doujinshi_dirs:

nhentai/utils.py

@@ -5,19 +5,21 @@ 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.constant import PATH_SEPARATOR
 from nhentai.logger import logger
 from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
 
 MAX_FIELD_LENGTH = 100
+EXTENSIONS = ('.png', '.jpg', '.jpeg', '.gif', '.webp')
 
 
 def request(method, url, **kwargs):
@@ -99,9 +101,9 @@ def parse_doujinshi_obj(
         file_type: str = ''
 ) -> Tuple[str, str]:
 
-    filename = f'./doujinshi.{file_type}'
+    filename = f'.{PATH_SEPARATOR}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)
         _filename = f'{doujinshi_obj.filename}.{file_type}'
 
         if file_type == 'cbz':
@@ -111,6 +113,8 @@ def parse_doujinshi_obj(
             _filename = _filename.replace('/', '-')
 
         filename = os.path.join(output_dir, _filename)
+    else:
+        doujinshi_dir = f'.{PATH_SEPARATOR}'
 
     return doujinshi_dir, filename
 
@@ -130,7 +134,7 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     file_list.sort()
 
     for image in file_list:
-        if not os.path.splitext(image)[1] in ('.jpg', '.png', '.webp'):
+        if not os.path.splitext(image)[1] in EXTENSIONS:
             continue
         image_html += f'<img src="{image}" class="image-item"/>\n'
 
@@ -175,7 +179,7 @@ def move_to_folder(output_dir='.', doujinshi_obj=None, file_type=None):
     shutil.move(filename, os.path.join(doujinshi_dir, os.path.basename(filename)))
 
 
-def generate_main_html(output_dir='./'):
+def generate_main_html(output_dir=f'.{PATH_SEPARATOR}'):
     """
     Generate a main html to show all the contains doujinshi.
     With a link to their `index.html`.
@@ -256,7 +260,7 @@ def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=Fa
             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', '.webp'))]
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(EXTENSIONS)]
             file_list.sort()
 
             logger.info(f'Writing PDF file to path: {filename}')
@@ -277,7 +281,7 @@ 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 +304,7 @@ 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)
 
@@ -308,7 +312,8 @@ def signal_handler(signal, frame):
 def paging(page_string):
     # 1,3-5,14 -> [1, 3, 4, 5, 14]
     if not page_string:
-        return []
+        # default, the first page
+        return [1]
 
     page_list = []
     for i in page_string.split(','):
@@ -333,16 +338,16 @@ def generate_metadata_file(output_dir, doujinshi_obj):
 
     fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
               'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
-              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'TAGS',  'FAVORITE COUNTS', '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)):
+    temp_dict = CaseInsensitiveDict(dict(doujinshi_obj.table))
-        f.write(f'{fields[i]}: ')
+    for i in fields:
-        if fields[i] in special_fields:
+        v = temp_dict.get(i)
-            f.write(str(doujinshi_obj.table[special_fields.index(fields[i])][1]))
+        v = temp_dict.get(f'{i}s') if v is None else v
-        f.write('\n')
+        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}"')

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.15"
+version = "0.5.19"
 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'

qodana.yaml

@@ -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

setup.cfg

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

setup.py

@@ -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',
-)