remove setup.py

add favorites count 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:
@@ -140,6 +140,7 @@ Format output doujinshi folder name:
 Supported doujinshi folder formatter:
 
 - %i: Doujinshi id
+- %f: Doujinshi favorite count
 - %t: Doujinshi name
 - %s: Doujinshi subtitle (translated name)
 - %a: Doujinshi authors' name

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.12'
+__version__ = '0.5.17.2'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -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 = []

nhentai/doujinshi.py

@@ -29,11 +29,12 @@ class DoujinshiInfo(dict):
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, pretty_name=None, id=None, img_id=None,
+    def __init__(self, name=None, pretty_name=None, id=None, favorite_counts=0, img_id=None,
                  ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
         self.pretty_name = pretty_name
         self.id = id
+        self.favorite_counts = favorite_counts
         self.img_id = img_id
         self.ext = ext
         self.pages = pages
@@ -45,6 +46,7 @@ class Doujinshi(object):
         name_format = name_format.replace('%ag', format_filename(ag_value))
 
         name_format = name_format.replace('%i', format_filename(str(self.id)))
+        name_format = name_format.replace('%f', format_filename(str(self.favorite_counts)))
         name_format = name_format.replace('%a', format_filename(self.info.artists))
         name_format = name_format.replace('%g', format_filename(self.info.groups))
 
@@ -55,7 +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],
@@ -63,6 +65,7 @@ class Doujinshi(object):
             ['Groups', self.info.groups],
             ['Languages', self.info.languages],
             ['Tags', self.info.tags],
+            ['Favorite Counts', self.info.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
 
@@ -32,33 +33,37 @@ def download_callback(result):
         logger.log(16, f'{data} downloaded successfully')
 
 
-async def fiber(tasks):
-    for completed_task in asyncio.as_completed(tasks):
-        try:
-            result = await completed_task
-            logger.info(f'{result[1]} download completed')
-        except Exception as e:
-            logger.error(f'An error occurred: {e}')
-
-
 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 _semaphore_download(self, semaphore, *args, **kwargs):
-        async with semaphore:
+    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')
+            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)
 
@@ -127,7 +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)
@@ -147,14 +151,13 @@ class Downloader(Singleton):
             # Assuming we want to continue with rest of process.
             return True
 
-        semaphore = asyncio.Semaphore(self.threads)
-
+        digit_length = len(str(len(queue)))
         coroutines = [
-            self._semaphore_download(semaphore, 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
         ]
 
         # Prevent coroutines infection
-        asyncio.run(fiber(coroutines))
+        asyncio.run(self.fiber(coroutines))
 
         return True

nhentai/parser.py

@@ -135,17 +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 = 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.strip()
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
     img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
@@ -157,8 +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
@@ -185,53 +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

nhentai/serializer.py

@@ -8,6 +8,8 @@ from nhentai.constant import LANGUAGE_ISO
 def serialize_json(doujinshi, output_dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
+    if doujinshi.info.favorite_counts:
+        metadata['favorite_counts'] = doujinshi.favorite_counts
     if doujinshi.info.date:
         metadata['upload_date'] = doujinshi.info.date
     if doujinshi.info.parodies:
@@ -44,6 +46,7 @@ def serialize_comic_xml(doujinshi, output_dir):
         xml_write_simple_tag(f, 'PageCount', doujinshi.pages)
         xml_write_simple_tag(f, 'URL', doujinshi.url)
         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
+        xml_write_simple_tag(f, 'Favorites', doujinshi.favorite_counts)
         xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
 
         xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and

nhentai/utils.py

@@ -10,7 +10,8 @@ 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
@@ -46,6 +47,10 @@ async def async_request(method, url, proxies = None, **kwargs):
     if proxies.get('http') == '' and proxies.get('https') == '':
         proxies = None
 
+    if proxies:
+        _proxies = {f'{k}://': v for k, v in proxies.items() if v}
+        proxies = _proxies
+
     async with httpx.AsyncClient(headers=headers, verify=False, proxies=proxies, **kwargs) as client:
         response = await client.request(method, url, **kwargs)
 
@@ -272,7 +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
 
@@ -295,7 +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)
 
@@ -330,14 +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}"')

poetry.lock

@@ -1,4 +1,26 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
+
+[[package]]
+name = "anyio"
+version = "4.5.2"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "anyio-4.5.2-py3-none-any.whl", hash = "sha256:c011ee36bc1e8ba40e5a81cb9df91925c218fe9b778554e0b56a21e1b5d4716f"},
+    {file = "anyio-4.5.2.tar.gz", hash = "sha256:23009af4ed04ce05991845451e11ef02fc7c5ed29179ac9a420e5ad0ac7ddc5b"},
+]
+
+[package.dependencies]
+exceptiongroup = {version = ">=1.0.2", markers = "python_version < \"3.11\""}
+idna = ">=2.8"
+sniffio = ">=1.1"
+typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "truststore (>=0.9.1)", "uvloop (>=0.21.0b1)"]
+trio = ["trio (>=0.26.1)"]
 
 [[package]]
 name = "beautifulsoup4"
@@ -126,6 +148,77 @@ files = [
     {file = "charset_normalizer-3.0.1-py3-none-any.whl", hash = "sha256:7e189e2e1d3ed2f4aebabd2d5b0f931e883676e51c7624826e0a4e5fe8a0bf24"},
 ]
 
+[[package]]
+name = "exceptiongroup"
+version = "1.2.2"
+description = "Backport of PEP 654 (exception groups)"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
+    {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
+]
+
+[package.extras]
+test = ["pytest (>=6)"]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
+    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.7"
+description = "A minimal low-level HTTP client."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "httpcore-1.0.7-py3-none-any.whl", hash = "sha256:a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd"},
+    {file = "httpcore-1.0.7.tar.gz", hash = "sha256:8551cb62a169ec7162ac7be8d4817d561f60e08eaa485234898414bb5a8a0b4c"},
+]
+
+[package.dependencies]
+certifi = "*"
+h11 = ">=0.13,<0.15"
+
+[package.extras]
+asyncio = ["anyio (>=4.0,<5.0)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (==1.*)"]
+trio = ["trio (>=0.22.0,<1.0)"]
+
+[[package]]
+name = "httpx"
+version = "0.27.2"
+description = "The next generation HTTP client."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0"},
+    {file = "httpx-0.27.2.tar.gz", hash = "sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2"},
+]
+
+[package.dependencies]
+anyio = "*"
+certifi = "*"
+httpcore = "==1.*"
+idna = "*"
+sniffio = "*"
+
+[package.extras]
+brotli = ["brotli", "brotlicffi"]
+cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (==1.*)"]
+zstd = ["zstandard (>=0.18.0)"]
+
 [[package]]
 name = "idna"
 version = "3.7"
@@ -169,6 +262,17 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "sniffio"
+version = "1.3.1"
+description = "Sniff out which async library your code is running under"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2"},
+    {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"},
+]
+
 [[package]]
 name = "soupsieve"
 version = "2.4"
@@ -194,6 +298,17 @@ files = [
 [package.extras]
 widechars = ["wcwidth"]
 
+[[package]]
+name = "typing-extensions"
+version = "4.12.2"
+description = "Backported and Experimental Type Hints for Python 3.8+"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"},
+    {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
+]
+
 [[package]]
 name = "urllib3"
 version = "1.26.19"
@@ -213,4 +328,4 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.8"
-content-hash = "0a1d5abd47a669c7a1f2dc7b43824a449e29ba94908a4338d2ea0f2dfb4f805e"
+content-hash = "a69dbf5dcfd6dcc5afc0fd2de4ab153841f7d210d4be60c426e332e36a79d679"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.12"
+version = "0.5.17.2"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"
@@ -14,8 +14,12 @@ beautifulsoup4 = "^4.11.2"
 tabulate = "^0.9.0"
 iso8601 = "^1.1.0"
 urllib3 = "^1.26.14"
+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

requirements.txt

@@ -1,4 +1,4 @@
-httpx
+httpx==0.27.2
 requests
 soupsieve
 setuptools

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',
-)