fix #349

add favorites count metadata

.gitignore

@@ -8,3 +8,4 @@ dist/
 output/
 venv/
 .vscode/
+test-output

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:
 
@@ -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
@@ -161,25 +162,21 @@ Other options:
       NHENTAI                 nhentai mirror url
 
     Options:
-      # Operation options, control the program behaviors
       -h, --help            show this help message and exit
       -D, --download        download doujinshi (for search results)
       -S, --show            just show the doujinshi information
-
-      # Doujinshi options, specify id, keyword, etc.
       --id                  doujinshi ids set, e.g. 167680 167681 167682
       -s KEYWORD, --search=KEYWORD
                             search doujinshi by keyword
       -F, --favorites       list or download your favorites
-
-      # Page options, control the page to fetch / download
+      -a ARTIST, --artist=ARTIST
+                            list doujinshi by artist name
       --page-all            all search results
       --page=PAGE, --page-range=PAGE
                             page number of search results. e.g. 1,2-5,14
-      --sorting=SORTING     sorting of doujinshi (recent / popular /
+      --sorting=SORTING, --sort=SORTING
+                            sorting of doujinshi (recent / popular /
                             popular-[today|week])
-
-      # Download options, the output directory, threads, timeout, delay, etc.
       -o OUTPUT_DIR, --output=OUTPUT_DIR
                             output dir
       -t THREADS, --threads=THREADS
@@ -192,8 +189,6 @@ Other options:
       -f FILE, --file=FILE  read gallery IDs from file.
       --format=NAME_FORMAT  format the saved folder name
       --dry-run             Dry run, skip file download
-
-      # Generate options, for generate html viewer, cbz file, pdf file, etc
       --html                generate a html viewer at current directory
       --no-html             don't generate HTML after downloading
       --gen-main            generate a main viewer contain all the doujin in the
@@ -202,12 +197,10 @@ 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  
+      --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
-
-      # nhentai options, set cookie, user-agent, language, remove caches, histories, etc
+      --regenerate          regenerate the cbz or pdf file if exists
       --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
       --useragent=USERAGENT, --user-agent=USERAGENT
                             set useragent to bypass Cloudflare captcha
@@ -231,6 +224,9 @@ For example:
 .. code-block::
 
     i.h.loli.club -> i.nhentai.net
+    i3.h.loli.club -> i3.nhentai.net
+    i5.h.loli.club -> i5.nhentai.net
+    i7.h.loli.club -> i7.nhentai.net
     h.loli.club -> nhentai.net
 
 Set `NHENTAI` env var to your nhentai mirror.

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.8'
+__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 = []
@@ -79,7 +79,7 @@ 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])',

nhentai/command.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+import os
+import shutil
 import sys
 import signal
 import platform
@@ -12,7 +14,7 @@ from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
 from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata_file, \
-    paging, check_cookie, signal_handler, DB
+    paging, check_cookie, signal_handler, DB, move_to_folder
 
 
 def main():
@@ -46,7 +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']:
@@ -75,7 +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:
@@ -92,6 +94,7 @@ def main():
                     doujinshi.download()
                 else:
                     logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {doujinshi.name}')
+                    continue
 
             if options.generate_metadata:
                 generate_metadata_file(options.output_dir, doujinshi)
@@ -104,12 +107,22 @@ def main():
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
 
             if options.is_cbz:
-                generate_doc('cbz', options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder,
-                             options.regenerate)
+                generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
 
             if options.is_pdf:
-                generate_doc('pdf', options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder,
-                             options.regenerate)
+                generate_doc('pdf', options.output_dir, doujinshi, options.regenerate)
+
+            if options.move_to_folder:
+                if options.is_cbz:
+                    move_to_folder(options.output_dir, doujinshi, 'cbz')
+                if options.is_pdf:
+                    move_to_folder(options.output_dir, doujinshi, 'pdf')
+
+            if options.rm_origin_dir:
+                if options.move_to_folder:
+                    logger.critical('You specified both --move-to-folder and --rm-origin-dir options, '
+                                    'you will not get anything :(')
+                shutil.rmtree(os.path.join(options.output_dir, doujinshi.filename), ignore_errors=True)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)

nhentai/constant.py

@@ -38,9 +38,13 @@ 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}://i1.{urlparse(BASE_URL).hostname}',
+    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_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))
 
@@ -54,7 +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],
@@ -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],
         ]
@@ -75,26 +79,28 @@ class Doujinshi(object):
     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
+        # regenerate, re-download
         if options.regenerate:
             return True
 
+        # pdf or cbz file exists, skip re-download
+        # doujinshi directory may not exist b/c of --rm-origin-dir option set.
+        # user should pass --regenerate option to get back origin dir.
+        ret_pdf = ret_cbz = None
         if options.is_pdf:
-            file_ext = 'pdf'
-        elif options.is_cbz:
-            file_ext = 'cbz'
-        else:
-            # re-download
-            return True
+            ret_pdf = os.path.exists(f'{base_path}.pdf') or os.path.exists(f'{base_path}/{self.filename}.pdf')
 
-        # 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}'):
+        if options.is_cbz:
+            ret_cbz = os.path.exists(f'{base_path}.cbz') or os.path.exists(f'{base_path}/{self.filename}.cbz')
+
+        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
+        if not (os.path.exists(base_path) and os.path.isdir(base_path)):
+            return True
+
         # fallback
         return True
 

nhentai/downloader.py

@@ -1,23 +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):
@@ -40,65 +34,75 @@ def download_callback(result):
 
 
 class Downloader(Singleton):
-
-    def __init__(self, path='', size=5, timeout=30, delay=0):
-        self.size = size
+    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
 
-    def download(self, url, folder='', filename='', retried=0, proxy=None):
-        if self.delay:
-            time.sleep(self.delay)
+    async def fiber(self, tasks):
+        self.semaphore = asyncio.Semaphore(self.threads)
+        for completed_task in asyncio.as_completed(tasks):
+            try:
+                result = await completed_task
+                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, 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)
 
-        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, url
 
-                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.warning(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
+                logger.warning(f'Download {filename} failed with 3 times retried, skipped')
+                return 0, url
 
         except NHentaiImageNotExistException as e:
             os.remove(save_file_path)
@@ -106,17 +110,34 @@ 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
+            return 0, url
 
         except KeyboardInterrupt:
-            return -3, None
+            return -3, url
 
         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 +149,20 @@ 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]
+        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), length=digit_length)
+            for url in queue
+        ]
 
-        pool.close()
-        pool.join()
+        # 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

@@ -135,30 +135,38 @@ 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)$',
-                       doujinshi_cover.a.img.attrs['data-src'])
+    # img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
+    #                   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)
-        ext.append(ext_name)
+        base_name = os.path.basename(i.img.attrs['data-src'])
+        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')
-        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 +193,6 @@ 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

@@ -6,16 +6,19 @@ import os
 import zipfile
 import shutil
 
+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
 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):
@@ -32,8 +35,32 @@ 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)
@@ -72,10 +99,10 @@ def parse_doujinshi_obj(
         doujinshi_obj=None,
         file_type: str = ''
 ) -> Tuple[str, str]:
-    filename = './doujinshi' + file_type
 
-    doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    filename = f'./doujinshi.{file_type}'
     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':
@@ -85,6 +112,8 @@ def parse_doujinshi_obj(
             _filename = _filename.replace('/', '-')
 
         filename = os.path.join(output_dir, _filename)
+    else:
+        doujinshi_dir = './'
 
     return doujinshi_dir, filename
 
@@ -104,7 +133,7 @@ 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 EXTENSIONS:
             continue
         image_html += f'<img src="{image}" class="image-item"/>\n'
 
@@ -128,6 +157,27 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
         logger.warning(f'Writing HTML Viewer failed ({e})')
 
 
+def move_to_folder(output_dir='.', doujinshi_obj=None, file_type=None):
+    if not file_type:
+        raise RuntimeError('no file_type specified')
+
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
+
+    for fn in os.listdir(doujinshi_dir):
+        file_path = os.path.join(doujinshi_dir, fn)
+        _, ext = os.path.splitext(file_path)
+        if ext in ['.pdf', '.cbz']:
+            continue
+
+        if os.path.isfile(file_path):
+            try:
+                os.remove(file_path)
+            except Exception as e:
+                print(f"Error deleting file: {e}")
+
+    shutil.move(filename, os.path.join(doujinshi_dir, os.path.basename(filename)))
+
+
 def generate_main_html(output_dir='./'):
     """
     Generate a main html to show all the contains doujinshi.
@@ -185,8 +235,7 @@ def generate_main_html(output_dir='./'):
         logger.warning(f'Writing Main Viewer failed ({e})')
 
 
-def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, rm_origin_dir=False,
-                 move_to_folder=False, regenerate=False):
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
 
     doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
 
@@ -210,7 +259,7 @@ def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, rm_origin_dir
             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(EXTENSIONS)]
             file_list.sort()
 
             logger.info(f'Writing PDF file to path: {filename}')
@@ -225,27 +274,13 @@ def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, rm_origin_dir
         except ImportError:
             logger.error("Please install img2pdf package by using pip.")
 
-    if rm_origin_dir:
-        shutil.rmtree(doujinshi_dir, ignore_errors=True)
-
-    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}")
-
-        shutil.move(filename, doujinshi_dir)
-
 
 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
 
@@ -268,7 +303,7 @@ 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)
 
@@ -276,7 +311,8 @@ 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(','):
@@ -303,14 +339,14 @@ 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', '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 = "0.5.8"
+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

@@ -1,3 +1,4 @@
+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',
-)

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'))