remove debug print

add webp support

.gitignore

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

README.rst

@@ -161,25 +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
-
-      # 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 +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
@@ -202,12 +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  
+      --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 +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__ = '0.5.8'
+__version__ = '0.5.12'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

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():
@@ -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 +38,9 @@ FAV_URL = f'{BASE_URL}/favorites/'
 
 IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
 IMAGE_URL_MIRRORS = [
-    f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}'
-    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}'
-    f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}'
+    f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}',
 ]
 
 NHENTAI_HOME = get_nhentai_home()

nhentai/doujinshi.py

@@ -12,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -75,26 +76,28 @@ 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

@@ -69,7 +69,7 @@ class Downloader(Singleton):
                         if response.status_code != 200:
                             path = urlparse(url).path
                             for mirror in constant.IMAGE_URL_MIRRORS:
-                                print(f'{mirror}{path}')
+                                # print(f'{mirror}{path}')
                                 mirror_url = f'{mirror}{path}'
                                 response = request('get', mirror_url, stream=True,
                                                    timeout=self.timeout, proxies=proxy)

nhentai/parser.py

@@ -148,7 +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 = []

nhentai/utils.py

@@ -72,8 +72,8 @@ def parse_doujinshi_obj(
         doujinshi_obj=None,
         file_type: str = ''
 ) -> Tuple[str, str]:
-    filename = './doujinshi' + file_type
 
+    filename = f'./doujinshi.{file_type}'
     doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
     if doujinshi_obj is not None:
         _filename = f'{doujinshi_obj.filename}.{file_type}'
@@ -104,7 +104,7 @@ 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'
 
@@ -128,6 +128,27 @@ 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 +206,7 @@ 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 +230,7 @@ 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(('.png', '.jpg', '.jpeg', '.gif', '.webp'))]
             file_list.sort()
 
             logger.info(f'Writing PDF file to path: {filename}')
@@ -225,20 +245,6 @@ 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):
     """
@@ -303,7 +309,7 @@ def generate_metadata_file(output_dir, doujinshi_obj):
               'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
               'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
               'SERIES', 'PARODY', 'URL']
-    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'DATE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
                       'LANGUAGE', 'TAGS', 'URL', 'PAGES']
 
     for i in range(len(fields)):

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.8"
+version = "0.5.12"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"

setup.cfg

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