0.5.7

Bump idna from 3.4 to 3.7

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
 ===================
@@ -200,6 +202,8 @@ 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
 

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.3'
+__version__ = '0.5.7'
 __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,
@@ -112,6 +114,8 @@ 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,
@@ -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

@@ -46,7 +46,7 @@ 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 +57,10 @@ 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
 
@@ -96,9 +100,9 @@ def main():
             if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
             elif options.is_cbz:
-                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir, True, options.move_to_folder)
             elif options.is_pdf:
-                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder)
 
         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/downloader.py

@@ -67,10 +67,14 @@ class Downloader(Singleton):
                     try:
                         response = request('get', url, stream=True, timeout=self.timeout, proxies=proxy)
                         if response.status_code != 200:
-                            raise NHentaiImageNotExistException
-
-                    except NHentaiImageNotExistException as e:
-                        raise e
+                            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
 
                     except Exception as e:
                         i += 1

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'})
 
@@ -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:
-        response = request('get', url=constant.LEGACY_SEARCH_URL,
-                           params={'q': keyword, 'page': 1, 'sort': sorting}).content
+        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} ...')
-        response = request('get', url=constant.LEGACY_SEARCH_URL,
-                           params={'q': keyword, 'page': p, 'sort': sorting}).content
+        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/utils.py

@@ -163,9 +163,12 @@ def generate_main_html(output_dir='./'):
         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_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=True, move_to_folder=False):
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+        if os.path.exists(doujinshi_dir+".cbz"):
+            logger.warning(f'Comic Book CBZ file exists, skip "{doujinshi_dir}"')
+            return
         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')
@@ -185,19 +188,31 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     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(cbz_filename, doujinshi_dir)
+
     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):
+def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, move_to_folder=False):
     try:
         import img2pdf
 
         """Write images to a PDF file using img2pdf."""
         if doujinshi_obj is not None:
             doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+            filename = doujinshi_obj.filename.replace('/', '-')
             pdf_filename = os.path.join(
                 os.path.join(doujinshi_dir, '..'),
-                f'{doujinshi_obj.filename}.pdf'
+                f'{filename}.pdf'
             )
         else:
             pdf_filename = './doujinshi.pdf'
@@ -211,11 +226,22 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
             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:
             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(pdf_filename, doujinshi_dir)
+
         logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
 
     except ImportError:
@@ -232,7 +258,7 @@ 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())
 

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++){
@@ -174,4 +174,4 @@ function tag_maker(data){
 			document.getElementById("tags").appendChild(node);
 		}
 	}
-}
+}

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-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
+    {file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"},
+    {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-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
+    {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"},
+    {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-2.28.2.tar.gz", hash = "sha256:98b1b2782e3c6c4904938b84c0eb932721069dfdb9134313beff7c83c2df24bf"},
+    {file = "requests-2.32.0-py3-none-any.whl", hash = "sha256:f2c3881dddb70d056c5bd7600a4fae312b2a300e39be6a118d30b90bd27262b5"},
+    {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 = "urllib3-1.26.14.tar.gz", hash = "sha256:076907bf8fd355cde77728471316625a4d2f7e713c125f51953bb5b3eecf4f72"},
+    {file = "urllib3-1.26.19-py2.py3-none-any.whl", hash = "sha256:37a0344459b199fce0e80b0d3569837ec6b6937435c5244e7fd73fa6006830f3"},
+    {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 = "0.5.7"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"

requirements.txt

@@ -1,5 +1,6 @@
 requests
 soupsieve
+setuptools
 BeautifulSoup4
 tabulate
 iso8601