0.5.16

add favorites count metadata

README.rst

@@ -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__ = '0.5.9'
+__version__ = '0.5.16'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/command.py

@@ -77,7 +77,7 @@ def main():
         doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
 
     if not options.is_show:
-        downloader = Downloader(path=options.output_dir, size=options.threads,
+        downloader = Downloader(path=options.output_dir, threads=options.threads,
                                 timeout=options.timeout, delay=options.delay)
 
         for doujinshi_id in doujinshi_ids:

nhentai/constant.py

@@ -38,9 +38,9 @@ FAV_URL = f'{BASE_URL}/favorites/'
 
 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}'
+    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/doujinshi.py

@@ -12,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -28,11 +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
@@ -44,6 +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))
 
@@ -62,6 +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],
         ]
@@ -89,7 +93,8 @@ class Doujinshi(object):
         if options.is_cbz:
             ret_cbz = os.path.exists(f'{base_path}.cbz') or os.path.exists(f'{base_path}/{self.filename}.cbz')
 
-        if all(filter(lambda s: s is not None, [ret_cbz, ret_pdf])):
+        ret = list(filter(lambda s: s is not None, [ret_cbz, ret_pdf]))
+        if ret and all(ret):
             return False
 
         # doujinshi directory doesn't exist, re-download

nhentai/downloader.py

@@ -1,24 +1,17 @@
 # coding: utf-
 
-import multiprocessing
-import signal
-
-import sys
 import os
-import requests
-import time
+import asyncio
+import httpx
 import urllib3.exceptions
 
 from urllib.parse import urlparse
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.parser import request
-from nhentai.utils import Singleton
+from nhentai.utils import Singleton, async_request
 
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-semaphore = multiprocessing.Semaphore(1)
-
 
 class NHentaiImageNotExistException(Exception):
     pass
@@ -39,64 +32,68 @@ def download_callback(result):
         logger.log(16, f'{data} downloaded successfully')
 
 
-class Downloader(Singleton):
 
-    def __init__(self, path='', size=5, timeout=30, delay=0):
-        self.size = size
+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
 
-    def download(self, url, folder='', filename='', retried=0, proxy=None):
-        if self.delay:
-            time.sleep(self.delay)
-        logger.info(f'Starting to download {url} ...')
-        filename = filename if filename else os.path.basename(urlparse(url).path)
-        base_filename, extension = os.path.splitext(filename)
+    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):
+        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)
+
+        save_file_path = os.path.join(self.folder, filename)
 
-        save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
         try:
             if os.path.exists(save_file_path):
                 logger.warning(f'Skipped download: {save_file_path} already exists')
                 return 1, url
 
-            response = None
-            with open(save_file_path, "wb") as f:
-                i = 0
-                while i < 10:
-                    try:
-                        response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
-                        if response.status_code != 200:
-                            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
+            response = await async_request('GET', url, timeout=self.timeout, proxies=proxy)
 
-                    except Exception as e:
-                        i += 1
-                        if not i < 10:
-                            logger.critical(str(e))
-                            return 0, None
-                        continue
+            if response.status_code != 200:
+                path = urlparse(url).path
+                for mirror in constant.IMAGE_URL_MIRRORS:
+                    logger.info(f"Try mirror: {mirror}{path}")
+                    mirror_url = f'{mirror}{path}'
+                    response = await async_request('GET', mirror_url, timeout=self.timeout, proxies=proxy)
+                    if response.status_code == 200:
+                        break
 
-                    break
+            if not await self.save(filename, response):
+                logger.error(f'Can not download image {url}')
+                return 1, None
 
-                length = response.headers.get('content-length')
-                if length is None:
-                    f.write(response.content)
-                else:
-                    for chunk in response.iter_content(2048):
-                        f.write(chunk)
-
-        except (requests.HTTPError, requests.Timeout) as e:
+        except (httpx.HTTPStatusError, httpx.TimeoutException, httpx.ConnectError) as e:
             if retried < 3:
-                logger.warning(f'Warning: {e}, retrying({retried}) ...')
-                return 0, self.download(url=url, folder=folder, filename=filename,
-                                        retried=retried+1, proxy=proxy)
+                logger.info(f'Download {filename} failed, retrying({retried + 1}) times...')
+                return await self.download(
+                    url=url,
+                    folder=folder,
+                    filename=filename,
+                    retried=retried + 1,
+                    proxy=proxy,
+                )
             else:
                 return 0, None
 
@@ -106,6 +103,8 @@ class Downloader(Singleton):
 
         except Exception as e:
             import traceback
+
+            logger.error(f"Exception type: {type(e)}")
             traceback.print_stack()
             logger.critical(str(e))
             return 0, None
@@ -115,8 +114,24 @@ class Downloader(Singleton):
 
         return 1, url
 
+    async def save(self, save_file_path, response) -> bool:
+        if response is None:
+            logger.error('Error: Response is None')
+            return False
+        save_file_path = os.path.join(self.folder, save_file_path)
+        with open(save_file_path, 'wb') as f:
+            if response is not None:
+                length = response.headers.get('content-length')
+                if length is None:
+                    f.write(response.content)
+                else:
+                    async for chunk in response.aiter_bytes(2048):
+                        f.write(chunk)
+        return True
+
+
     def start_download(self, queue, folder='') -> bool:
-        if not isinstance(folder, (str, )):
+        if not isinstance(folder, (str,)):
             folder = str(folder)
 
         if self.path:
@@ -128,34 +143,19 @@ class Downloader(Singleton):
                 os.makedirs(folder)
             except EnvironmentError as e:
                 logger.critical(str(e))
+        self.folder = folder
 
         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)
-        [pool.apply_async(download_wrapper, args=item) for item in queue]
 
-        pool.close()
-        pool.join()
+        coroutines = [
+            self._semaphore_download(url, filename=os.path.basename(urlparse(url).path))
+            for url in queue
+        ]
+
+        # Prevent coroutines infection
+        asyncio.run(self.fiber(coroutines))
 
         return True
-
-
-def download_wrapper(obj, url, folder='', proxy=None):
-    if sys.platform == 'darwin' or semaphore.get_value():
-        return Downloader.download(obj, url=url, folder=folder, proxy=proxy)
-    else:
-        return -3, None
-
-
-def init_worker():
-    signal.signal(signal.SIGINT, subprocess_signal)
-
-
-def subprocess_signal(sig, frame):
-    if semaphore.acquire(timeout=1):
-        logger.warning('Ctrl-C pressed, exiting sub processes ...')
-
-    raise KeyboardInterrupt

nhentai/parser.py

@@ -142,13 +142,20 @@ def doujinshi_parser(id_, counter=0):
     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')\
+
+    if favorite_counts:
+        favorite_counts = favorite_counts.text.strip()
+    else:
+        favorite_counts = 0
 
     doujinshi['name'] = title
     doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
+    doujinshi['favorite_counts'] = favorite_counts
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
                        doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []

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

@@ -5,7 +5,9 @@ import re
 import os
 import zipfile
 import shutil
+import copy
 
+import httpx
 import requests
 import sqlite3
 import urllib.parse
@@ -32,8 +34,32 @@ def request(method, url, **kwargs):
     return getattr(session, method)(url, verify=False, **kwargs)
 
 
+async def async_request(method, url, proxies = None, **kwargs):
+    headers = {
+        'Referer': constant.LOGIN_URL,
+        'User-Agent': constant.CONFIG['useragent'],
+        'Cookie': constant.CONFIG['cookie'],
+    }
+
+    if proxies is None:
+        proxies = constant.CONFIG['proxy']
+
+    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)
+
+    return response
+
+
 def check_cookie():
     response = request('get', constant.BASE_URL)
+
     if response.status_code == 403 and 'Just a moment...' in response.text:
         logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
         sys.exit(1)
@@ -104,7 +130,7 @@ 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'):
+        if not os.path.splitext(image)[1] in ('.jpg', '.png', '.webp'):
             continue
         image_html += f'<img src="{image}" class="image-item"/>\n'
 
@@ -230,7 +256,7 @@ 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'))]
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.webp'))]
             file_list.sort()
 
             logger.info(f'Writing PDF file to path: {filename}')
@@ -309,7 +335,7 @@ 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', 'CHARACTERS', 'AUTHOR', 'GROUPS',
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'DATE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
                       'LANGUAGE', 'TAGS', 'URL', 'PAGES']
 
     for i in range(len(fields)):

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 = "0.5.9"
+version = "0.5.15"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"
@@ -14,6 +14,7 @@ beautifulsoup4 = "^4.11.2"
 tabulate = "^0.9.0"
 iso8601 = "^1.1.0"
 urllib3 = "^1.26.14"
+httpx = "0.27.2"
 
 
 [build-system]

requirements.txt

@@ -1,3 +1,4 @@
+httpx==0.27.2
 requests
 soupsieve
 setuptools

setup.cfg

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

tests/test_download.py

@@ -20,7 +20,7 @@ class TestDownload(unittest.TestCase):
     def test_download(self):
         did = 440546
         info = Doujinshi(**doujinshi_parser(did), name_format='%i')
-        info.downloader = Downloader(path='/tmp', size=5)
+        info.downloader = Downloader(path='/tmp', threads=5)
         info.download()
 
         self.assertTrue(os.path.exists(f'/tmp/{did}/001.jpg'))