Merge pull request #354 from normalizedwater546/master

asyncio: fix downloader being run sequentially + httpx: fix proxy and missing headers

.gitignore

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

README.rst

@@ -11,6 +11,8 @@ nhentai
 
 nhentai is a CLI tool for downloading doujinshi from `nhentai.net <https://nhentai.net>`_
 
+GUI version: `https://github.com/edgar1016/nhentai-GUI <https://github.com/edgar1016/nhentai-GUI>`_
+
 ===================
 Manual Installation
 ===================
@@ -159,25 +161,21 @@ 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
-
+      -a ARTIST, --artist=ARTIST
-      # Page options, control the page to fetch / download
+                            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
@@ -190,8 +188,6 @@ 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
@@ -200,10 +196,10 @@ 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
       --meta                generate a metadata file in doujinshi format
-      --regenerate-cbz      regenerate the cbz file if exists
+      --regenerate          regenerate the cbz or pdf file if exists
-
-      # nhentai options, set cookie, user-agent, language, remove caches, histories, etc
       --cookie=COOKIE       set cookie of nhentai to bypass Cloudflare captcha
       --useragent=USERAGENT, --user-agent=USERAGENT
                             set useragent to bypass Cloudflare captcha
@@ -227,6 +223,9 @@ 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__ = '0.5.3'
+__version__ = '0.5.12'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -73,6 +73,8 @@ def cmd_parser():
                       help='search doujinshi by keyword')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
                       help='list or download your favorites')
+    parser.add_option('--artist', '-a', action='store', dest='artist',
+                      help='list doujinshi by artist name')
 
     # page options
     parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
@@ -112,10 +114,12 @@ def cmd_parser():
                       help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
                       help='remove downloaded doujinshi dir when generated CBZ or PDF file')
+    parser.add_option('--move-to-folder', dest='move_to_folder', action='store_true', default=False,
+                      help='remove files in doujinshi dir then move new file to folder when generated CBZ or PDF file')
     parser.add_option('--meta', dest='generate_metadata', action='store_true',
                       help='generate a metadata file in doujinshi format')
-    parser.add_option('--regenerate-cbz', dest='regenerate_cbz', action='store_true', default=False,
+    parser.add_option('--regenerate', dest='regenerate', action='store_true', default=False,
-                      help='regenerate the cbz file if exists')
+                      help='regenerate the cbz or pdf file if exists')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
@@ -209,12 +213,12 @@ def cmd_parser():
             _ = [i.strip() for i in f.readlines()]
             args.id = set(int(i) for i in _ if i.isdigit())
 
-    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites:
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites and not args.artist:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
         sys.exit(1)
 
-    if not args.keyword and not args.id and not args.favorites:
+    if not args.keyword and not args.id and not args.favorites and not args.artist:
         parser.print_help()
         sys.exit(1)
 

nhentai/command.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+import os
+import shutil
 import sys
 import signal
 import platform
@@ -11,8 +13,8 @@ from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
+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(page=page_list)
+        doujinshis = favorites_parser() if options.page_all else favorites_parser(page=page_list)
 
     elif options.keyword:
         if constant.CONFIG['language']:
@@ -57,6 +59,10 @@ def main():
         doujinshis = _search_parser(options.keyword, sorting=options.sorting, page=page_list,
                                     is_page_all=options.page_all)
 
+    elif options.artist:
+        doujinshis = legacy_search_parser(options.artist, sorting=options.sorting, page=page_list,
+                                          is_page_all=options.page_all, type_='ARTIST')
+
     elif not doujinshi_ids:
         doujinshi_ids = options.id
 
@@ -71,7 +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:
@@ -83,22 +89,40 @@ def main():
 
             if not options.dryrun:
                 doujinshi.downloader = downloader
-                doujinshi.download(regenerate_cbz=options.regenerate_cbz)
+
+                if doujinshi.check_if_need_download(options):
+                    doujinshi.download()
+                else:
+                    logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {doujinshi.name}')
+                    continue
 
             if options.generate_metadata:
-                table = doujinshi.table
+                generate_metadata_file(options.output_dir, doujinshi)
-                generate_metadata_file(options.output_dir, table, doujinshi)
 
             if options.is_save_download_history:
                 with DB() as db:
                     db.add_one(doujinshi.id)
 
-            if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
+            if not options.is_nohtml:
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
-            elif options.is_cbz:
+
-                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+            if options.is_cbz:
-            elif options.is_pdf:
+                generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
-                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
+
+            if options.is_pdf:
+                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

@@ -3,6 +3,23 @@ import os
 import tempfile
 
 from urllib.parse import urlparse
+from platform import system
+
+
+def get_nhentai_home() -> str:
+    home = os.getenv('HOME', tempfile.gettempdir())
+
+    if system() == 'Linux':
+        xdgdat = os.getenv('XDG_DATA_HOME')
+        if xdgdat and os.path.exists(os.path.join(xdgdat, 'nhentai')):
+            return os.path.join(xdgdat, 'nhentai')
+        if home and os.path.exists(os.path.join(home, '.nhentai')):
+            return os.path.join(home, '.nhentai')
+        if xdgdat:
+            return os.path.join(xdgdat, 'nhentai')
+
+    # Use old default path in other systems
+    return os.path.join(home, '.nhentai')
 
 
 DEBUG = os.getenv('DEBUG', False)
@@ -11,15 +28,22 @@ BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 DETAIL_URL = f'{BASE_URL}/g'
 LEGACY_SEARCH_URL = f'{BASE_URL}/search/'
 SEARCH_URL = f'{BASE_URL}/api/galleries/search'
+ARTIST_URL = f'{BASE_URL}/artist/'
 
 TAG_API_URL = f'{BASE_URL}/api/galleries/tagged'
 LOGIN_URL = f'{BASE_URL}/login/'
 CHALLENGE_URL = f'{BASE_URL}/challenge'
 FAV_URL = f'{BASE_URL}/favorites/'
 
-IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
 
-NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
+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}',
+]
+
+NHENTAI_HOME = get_nhentai_home()
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
 NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
@@ -30,7 +54,8 @@ CONFIG = {
     'cookie': '',
     'language': '',
     'template': '',
-    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
+    'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+    'max_filename': 85
 }
 
 LANGUAGE_ISO = {

nhentai/doujinshi.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+import os
 
 from tabulate import tabulate
 
@@ -11,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -55,6 +57,7 @@ class Doujinshi(object):
             ['Parodies', self.info.parodies],
             ['Doujinshi', self.name],
             ['Subtitle', self.info.subtitle],
+            ['Date', self.info.date],
             ['Characters', self.info.characters],
             ['Authors', self.info.artists],
             ['Groups', self.info.groups],
@@ -70,7 +73,35 @@ class Doujinshi(object):
     def show(self):
         logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
 
-    def download(self, regenerate_cbz=False):
+    def check_if_need_download(self, options):
+        base_path = os.path.join(self.downloader.path, self.filename)
+
+        # 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:
+            ret_pdf = os.path.exists(f'{base_path}.pdf') or os.path.exists(f'{base_path}/{self.filename}.pdf')
+
+        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
+
+    def download(self):
         logger.info(f'Starting to download doujinshi: {self.name}')
         if self.downloader:
             download_queue = []
@@ -80,9 +111,10 @@ class Doujinshi(object):
             for i in range(1, min(self.pages, len(self.ext)) + 1):
                 download_queue.append(f'{IMAGE_URL}/{self.img_id}/{i}.{self.ext[i-1]}')
 
-            self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
+            return self.downloader.start_download(download_queue, self.filename)
         else:
             logger.critical('Downloader has not been loaded')
+            return False
 
 
 if __name__ == '__main__':

nhentai/downloader.py

@@ -1,24 +1,17 @@
 # coding: utf-
 
-import multiprocessing
-import signal
-
-import sys
 import os
-import requests
+import asyncio
-import time
+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, async_request
-from nhentai.utils import Singleton
 
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-semaphore = multiprocessing.Semaphore(1)
-
 
 class NHentaiImageNotExistException(Exception):
     pass
@@ -39,60 +32,66 @@ def download_callback(result):
         logger.log(16, f'{data} downloaded successfully')
 
 
-class Downloader(Singleton):
+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}')
 
-    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):
+    async def _semaphore_download(self, semaphore, *args, **kwargs):
-        if self.delay:
+        async with semaphore:
-            time.sleep(self.delay)
+            return await self.download(*args, **kwargs)
-        logger.info(f'Starting to download {url} ...')
+
-        filename = filename if filename else os.path.basename(urlparse(url).path)
+    async def download(self, url, folder='', filename='', retried=0, proxy=None):
-        base_filename, extension = os.path.splitext(filename)
+        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'Ignored exists file: {save_file_path}')
+                logger.warning(f'Skipped download: {save_file_path} already exists')
                 return 1, url
 
-            response = None
+            response = await async_request('GET', url, timeout=self.timeout, proxies=proxy)
-            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:
-                            raise NHentaiImageNotExistException
+                path = urlparse(url).path
-
+                for mirror in constant.IMAGE_URL_MIRRORS:
-                    except NHentaiImageNotExistException as e:
+                    logger.info(f"Try mirror: {mirror}{path}")
-                        raise e
+                    mirror_url = f'{mirror}{path}'
-
+                    response = await async_request('GET', mirror_url, timeout=self.timeout, proxies=proxy)
-                    except Exception as e:
+                    if response.status_code == 200:
-                        i += 1
-                        if not i < 10:
-                            logger.critical(str(e))
-                            return 0, None
-                        continue
-
                         break
 
-                length = response.headers.get('content-length')
+            if not await self.save(filename, response):
-                if length is None:
+                logger.error(f'Can not download image {url}')
-                    f.write(response.content)
+                return 1, None
-                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}) ...')
+                logger.info(f'Download {filename} failed, retrying({retried + 1}) times...')
-                return 0, self.download(url=url, folder=folder, filename=filename,
+                return await self.download(
-                                        retried=retried+1, proxy=proxy)
+                    url=url,
+                    folder=folder,
+                    filename=filename,
+                    retried=retried + 1,
+                    proxy=proxy,
+                )
             else:
                 return 0, None
 
@@ -102,6 +101,8 @@ 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
@@ -111,50 +112,49 @@ class Downloader(Singleton):
 
         return 1, url
 
-    def start_download(self, queue, folder='', regenerate_cbz=False):
+    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,)):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
-        if os.path.exists(folder + '.cbz'):
-            if not regenerate_cbz:
-                logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
-                return
-
         logger.info(f'Doujinshi will be saved at "{folder}"')
         if not os.path.exists(folder):
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:
                 logger.critical(str(e))
+        self.folder = folder
 
-        else:
+        if os.getenv('DEBUG', None) == 'NODOWNLOAD':
-            logger.warning(f'Path "{folder}" already exist.')
+            # Assuming we want to continue with rest of process.
+            return True
 
-        queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
+        semaphore = asyncio.Semaphore(self.threads)
 
-        pool = multiprocessing.Pool(self.size, init_worker)
+        coroutines = [
-        [pool.apply_async(download_wrapper, args=item) for item in queue]
+            self._semaphore_download(semaphore, url, filename=os.path.basename(urlparse(url).path))
+            for url in queue
+        ]
 
-        pool.close()
+        # Prevent coroutines infection
-        pool.join()
+        asyncio.run(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

@@ -135,6 +135,7 @@ 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'})
 
@@ -147,7 +148,7 @@ def doujinshi_parser(id_, counter=0):
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     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 = []
@@ -240,13 +241,21 @@ def print_doujinshi(doujinshi_list):
     print(tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def legacy_search_parser(keyword, sorting, page, is_page_all=False):
+def legacy_search_parser(keyword, sorting, page, is_page_all=False, type_='SEARCH'):
     logger.info(f'Searching doujinshis of keyword {keyword}')
     result = []
 
+    if type_ not in ('SEARCH', 'ARTIST', ):
+        raise ValueError('Invalid type')
+
     if is_page_all:
+        if type_ == 'SEARCH':
             response = request('get', url=constant.LEGACY_SEARCH_URL,
                                params={'q': keyword, 'page': 1, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': 1}).content
+
         html = BeautifulSoup(response, 'lxml')
         pagination = html.find(attrs={'class': 'pagination'})
         last_page = pagination.find(attrs={'class': 'last'})
@@ -258,8 +267,13 @@ def legacy_search_parser(keyword, sorting, page, is_page_all=False):
 
     for p in pages:
         logger.info(f'Fetching page {p} ...')
+        if type_ == 'SEARCH':
             response = request('get', url=constant.LEGACY_SEARCH_URL,
                                params={'q': keyword, 'page': p, 'sort': sorting}).content
+        else:
+            url = constant.ARTIST_URL + keyword + '/' + ('' if sorting == 'recent' else sorting)
+            response = request('get', url=url, params={'page': p}).content
+
         if response is None:
             logger.warning(f'No result in response in page {p}')
             continue
@@ -313,7 +327,9 @@ def search_parser(keyword, sorting, page, is_page_all=False):
 
         for row in response['result']:
             title = row['title']['english']
-            title = title[:85] + '..' if len(title) > 85 else title
+            title = title[:constant.CONFIG['max_filename']] + '..' if \
+                len(title) > constant.CONFIG['max_filename'] else title
+
             result.append({'id': row['id'], 'title': title})
 
         not_exists_persist = False

nhentai/serializer.py

@@ -22,7 +22,7 @@ def serialize_json(doujinshi, output_dir):
         metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
     if doujinshi.info.languages:
         metadata['language'] = [i.strip() for i in doujinshi.info.languages.split(',')]
-    metadata['category'] = doujinshi.info.categories
+    metadata['category'] = [i.strip() for i in doujinshi.info.categories.split(',')]
     metadata['URL'] = doujinshi.url
     metadata['Pages'] = doujinshi.pages
 

nhentai/utils.py

@@ -5,14 +5,17 @@ import re
 import os
 import zipfile
 import shutil
+
+import httpx
 import requests
 import sqlite3
+import urllib.parse
+from typing import Optional, Tuple
 
 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
 
 
@@ -30,15 +33,36 @@ 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
+
+    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)
 
     username = re.findall('"/users/[0-9]+/(.*?)"', response.text)
     if not username:
-        logger.warning('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
+        logger.warning(
+            'Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
     else:
         logger.log(16, f'Login successfully! Your username: {username[0]}')
 
@@ -64,13 +88,31 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
+def parse_doujinshi_obj(
-    image_html = ''
+        output_dir: str,
+        doujinshi_obj=None,
+        file_type: str = ''
+) -> Tuple[str, str]:
 
-    if doujinshi_obj is not None:
+    filename = f'./doujinshi.{file_type}'
     doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    else:
+    if doujinshi_obj is not None:
-        doujinshi_dir = '.'
+        _filename = f'{doujinshi_obj.filename}.{file_type}'
+
+        if file_type == 'cbz':
+            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+
+        if file_type == 'pdf':
+            _filename = _filename.replace('/', '-')
+
+        filename = os.path.join(output_dir, _filename)
+
+    return doujinshi_dir, filename
+
+
+def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '.html')
+    image_html = ''
 
     if not os.path.exists(doujinshi_dir):
         logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
@@ -83,7 +125,7 @@ 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'
 
@@ -107,6 +149,27 @@ 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.
@@ -148,7 +211,7 @@ def generate_main_html(output_dir='./'):
         else:
             title = 'nHentai HTML Viewer'
 
-        image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
+        image_html += element.format(FOLDER=urllib.parse.quote(folder), IMAGE=image, TITLE=title)
     if image_html == '':
         logger.warning('No index.html found, --gen-main paused.')
         return
@@ -158,65 +221,47 @@ def generate_main_html(output_dir='./'):
             f.write(data.encode('utf-8'))
         shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
         set_js_database()
-        logger.log(16, f'Main Viewer has been written to "{output_dir}main.html"')
+        output_dir = output_dir[:-1] if output_dir.endswith('/') else output_dir
+        logger.log(16, f'Main Viewer has been written to "{output_dir}/main.html"')
     except Exception as e:
         logger.warning(f'Writing Main Viewer failed ({e})')
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True):
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
-    if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-        if write_comic_info:
-            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
-        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), f'{doujinshi_obj.filename}.cbz')
-    else:
-        cbz_filename = './doujinshi.cbz'
-        doujinshi_dir = '.'
 
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
+
+    if os.path.exists(f'{doujinshi_dir}.{file_type}') and not regenerate:
+        logger.info(f'Skipped {file_type} file generation: {doujinshi_dir}.{file_type} already exists')
+        return
+
+    if file_type == 'cbz':
         file_list = os.listdir(doujinshi_dir)
         file_list.sort()
 
-    logger.info(f'Writing CBZ file to path: {cbz_filename}')
+        logger.info(f'Writing CBZ file to path: {filename}')
-    with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
+        with zipfile.ZipFile(filename, 'w') as cbz_pf:
             for image in file_list:
                 image_path = os.path.join(doujinshi_dir, image)
                 cbz_pf.write(image_path, image)
 
-    if rm_origin_dir:
+        logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
-        shutil.rmtree(doujinshi_dir, ignore_errors=True)
+    elif file_type == 'pdf':
-
-    logger.log(16, f'Comic Book CBZ file has been written to "{doujinshi_dir}"')
-
-
-def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
         try:
             import img2pdf
 
             """Write images to a PDF file using img2pdf."""
-        if doujinshi_obj is not None:
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.webp'))]
-            doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-            pdf_filename = os.path.join(
-                os.path.join(doujinshi_dir, '..'),
-                f'{doujinshi_obj.filename}.pdf'
-            )
-        else:
-            pdf_filename = './doujinshi.pdf'
-            doujinshi_dir = '.'
-
-        file_list = os.listdir(doujinshi_dir)
             file_list.sort()
 
-        logger.info(f'Writing PDF file to path: {pdf_filename}')
+            logger.info(f'Writing PDF file to path: {filename}')
-        with open(pdf_filename, 'wb') as pdf_f:
+            with open(filename, 'wb') as pdf_f:
                 full_path_list = (
                     [os.path.join(doujinshi_dir, image) for image in file_list]
                 )
-            pdf_f.write(img2pdf.convert(full_path_list))
+                pdf_f.write(img2pdf.convert(full_path_list, rotation=img2pdf.Rotation.ifvalid))
 
-        if rm_origin_dir:
+            logger.log(16, f'PDF file has been written to "{filename}"')
-            shutil.rmtree(doujinshi_dir, ignore_errors=True)
-
-        logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
 
         except ImportError:
             logger.error("Please install img2pdf package by using pip.")
@@ -232,7 +277,7 @@ def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
     # maybe you can use `--format` to select a suitable filename
 
     if not _truncate_only:
-        ban_chars = '\\\'/:,;*?"<>|\t'
+        ban_chars = '\\\'/:,;*?"<>|\t\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b'
         filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
         filename = ' '.join(filename.split())
 
@@ -275,32 +320,27 @@ def paging(page_string):
     return page_list
 
 
-def generate_metadata_file(output_dir, table, doujinshi_obj=None):
+def generate_metadata_file(output_dir, doujinshi_obj):
-    logger.info('Writing Metadata Info')
 
-    if doujinshi_obj is not None:
+    info_txt_path = os.path.join(output_dir, doujinshi_obj.filename, 'info.txt')
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    else:
-        doujinshi_dir = '.'
 
-    logger.info(doujinshi_dir)
+    f = open(info_txt_path, 'w', encoding='utf-8')
-
-    f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
 
     fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
               '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)):
         f.write(f'{fields[i]}: ')
         if fields[i] in special_fields:
-            f.write(str(table[special_fields.index(fields[i])][1]))
+            f.write(str(doujinshi_obj.table[special_fields.index(fields[i])][1]))
         f.write('\n')
 
     f.close()
+    logger.log(16, f'Metadata Info has been written to "{info_txt_path}"')
 
 
 class DB(object):

nhentai/viewer/main.js

@@ -139,7 +139,7 @@ function filter_searcher(){
 					break
 			}
 		}
-		if (verifier){doujinshi_id.push(data[i].Folder);}
+		if (verifier){doujinshi_id.push(data[i].Folder.replace("_", " "));}
 	}
 	var gallery = document.getElementsByClassName("gallery-favorite");
 	for (var i = 0; i < gallery.length; i++){

poetry.lock

@@ -1,10 +1,9 @@
-# This file is automatically @generated by Poetry 1.4.0 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "beautifulsoup4"
 version = "4.11.2"
 description = "Screen-scraping library"
-category = "main"
 optional = false
 python-versions = ">=3.6.0"
 files = [
@@ -21,21 +20,19 @@ lxml = ["lxml"]
 
 [[package]]
 name = "certifi"
-version = "2022.12.7"
+version = "2024.7.4"
 description = "Python package for providing Mozilla's CA Bundle."
-category = "main"
 optional = false
 python-versions = ">=3.6"
 files = [
-    {file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"},
+    {file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"},
-    {file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
+    {file = "certifi-2024.7.4.tar.gz", hash = "sha256:5a1e7645bc0ec61a09e26c36f6106dd4cf40c6db3a1fb6352b0244e7fb057c7b"},
 ]
 
 [[package]]
 name = "charset-normalizer"
 version = "3.0.1"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
-category = "main"
 optional = false
 python-versions = "*"
 files = [
@@ -131,21 +128,19 @@ files = [
 
 [[package]]
 name = "idna"
-version = "3.4"
+version = "3.7"
 description = "Internationalized Domain Names in Applications (IDNA)"
-category = "main"
 optional = false
 python-versions = ">=3.5"
 files = [
-    {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
+    {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"},
-    {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
+    {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"},
 ]
 
 [[package]]
 name = "iso8601"
 version = "1.1.0"
 description = "Simple module to parse ISO 8601 dates"
-category = "main"
 optional = false
 python-versions = ">=3.6.2,<4.0"
 files = [
@@ -155,21 +150,20 @@ files = [
 
 [[package]]
 name = "requests"
-version = "2.28.2"
+version = "2.32.0"
 description = "Python HTTP for Humans."
-category = "main"
 optional = false
-python-versions = ">=3.7, <4"
+python-versions = ">=3.8"
 files = [
-    {file = "requests-2.28.2-py3-none-any.whl", hash = "sha256:64299f4909223da747622c030b781c0d7811e359c37124b4bd368fb8c6518baa"},
+    {file = "requests-2.32.0-py3-none-any.whl", hash = "sha256:f2c3881dddb70d056c5bd7600a4fae312b2a300e39be6a118d30b90bd27262b5"},
-    {file = "requests-2.28.2.tar.gz", hash = "sha256:98b1b2782e3c6c4904938b84c0eb932721069dfdb9134313beff7c83c2df24bf"},
+    {file = "requests-2.32.0.tar.gz", hash = "sha256:fa5490319474c82ef1d2c9bc459d3652e3ae4ef4c4ebdd18a21145a47ca4b6b8"},
 ]
 
 [package.dependencies]
 certifi = ">=2017.4.17"
 charset-normalizer = ">=2,<4"
 idna = ">=2.5,<4"
-urllib3 = ">=1.21.1,<1.27"
+urllib3 = ">=1.21.1,<3"
 
 [package.extras]
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
@@ -179,7 +173,6 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 name = "soupsieve"
 version = "2.4"
 description = "A modern CSS selector implementation for Beautiful Soup."
-category = "main"
 optional = false
 python-versions = ">=3.7"
 files = [
@@ -191,7 +184,6 @@ files = [
 name = "tabulate"
 version = "0.9.0"
 description = "Pretty-print tabular data"
-category = "main"
 optional = false
 python-versions = ">=3.7"
 files = [
@@ -204,18 +196,17 @@ widechars = ["wcwidth"]
 
 [[package]]
 name = "urllib3"
-version = "1.26.14"
+version = "1.26.19"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
-category = "main"
 optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
 files = [
-    {file = "urllib3-1.26.14-py2.py3-none-any.whl", hash = "sha256:75edcdc2f7d85b137124a6c3c9fc3933cdeaa12ecb9a6a959f22797a0feca7e1"},
+    {file = "urllib3-1.26.19-py2.py3-none-any.whl", hash = "sha256:37a0344459b199fce0e80b0d3569837ec6b6937435c5244e7fd73fa6006830f3"},
-    {file = "urllib3-1.26.14.tar.gz", hash = "sha256:076907bf8fd355cde77728471316625a4d2f7e713c125f51953bb5b3eecf4f72"},
+    {file = "urllib3-1.26.19.tar.gz", hash = "sha256:3e3d753a8618b86d7de333b4223005f68720bcd6a7d2bcb9fbd2229ec7c1e429"},
 ]
 
 [package.extras]
-brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
 secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.2"
+version = "0.5.12"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"

requirements.txt

@@ -1,5 +1,7 @@
+httpx
 requests
 soupsieve
+setuptools
 BeautifulSoup4
 tabulate
 iso8601

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'))