0.5.19

fix favorite_counts output in metadata

README.rst

@@ -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:
 

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.17.2'
+__version__ = '0.5.19'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -11,6 +11,7 @@ from optparse import OptionParser
 from nhentai import __version__
 from nhentai.utils import generate_html, generate_main_html, DB
 from nhentai.logger import logger
+from nhentai.constant import PATH_SEPARATOR
 
 
 def banner():
@@ -64,7 +65,8 @@ def cmd_parser():
     # operation options
     parser.add_option('--download', '-D', dest='is_download', action='store_true',
                       help='download doujinshi (for search results)')
-    parser.add_option('--show', '-S', dest='is_show', action='store_true', help='just show the doujinshi information')
+    parser.add_option('--show', '-S', dest='is_show', action='store_true',
+                      help='just show the doujinshi information')
 
     # doujinshi options
     parser.add_option('--id', dest='id', action='callback', callback=callback,
@@ -79,14 +81,15 @@ 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])',
                       choices=['recent', 'popular', 'popular-today', 'popular-week', 'date'])
 
     # download options
-    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='./',
+    parser.add_option('--output', '-o', type='string', dest='output_dir', action='store',
+                      default=f'.{PATH_SEPARATOR}',
                       help='output dir')
     parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
                       help='thread count for downloading doujinshi')
@@ -96,7 +99,8 @@ def cmd_parser():
                       help='slow down between downloading every doujinshi')
     parser.add_option('--proxy', type='string', dest='proxy', action='store',
                       help='store a proxy, for example: -p "http://127.0.0.1:1080"')
-    parser.add_option('--file', '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+    parser.add_option('--file', '-f', type='string', dest='file', action='store',
+                      help='read gallery IDs from file.')
     parser.add_option('--format', type='string', dest='name_format', action='store',
                       help='format the saved folder name', default='[%i][%a][%t]')
     parser.add_option('--dry-run', action='store_true', dest='dryrun', help='Dry run, skip file download')

nhentai/command.py

@@ -48,7 +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']:

nhentai/constant.py

@@ -35,11 +35,16 @@ LOGIN_URL = f'{BASE_URL}/login/'
 CHALLENGE_URL = f'{BASE_URL}/challenge'
 FAV_URL = f'{BASE_URL}/favorites/'
 
+PATH_SEPARATOR = os.path.sep
 
-IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i.{urlparse(BASE_URL).hostname}/galleries'
+
+IMAGE_URL = f'{urlparse(BASE_URL).scheme}://i1.{urlparse(BASE_URL).hostname}/galleries'
 IMAGE_URL_MIRRORS = [
+    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/doujinshi.py

@@ -65,7 +65,7 @@ class Doujinshi(object):
             ['Groups', self.info.groups],
             ['Languages', self.info.languages],
             ['Tags', self.info.tags],
-            ['Favorite Counts', self.info.favorite_counts],
+            ['Favorite Counts', self.favorite_counts],
             ['URL', self.url],
             ['Pages', self.pages],
         ]

nhentai/downloader.py

@@ -47,7 +47,10 @@ class Downloader(Singleton):
         for completed_task in asyncio.as_completed(tasks):
             try:
                 result = await completed_task
-                logger.info(f'{result[1]} download completed')
+                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}')
 
@@ -85,11 +88,11 @@ class Downloader(Singleton):
 
             if not await self.save(filename, response):
                 logger.error(f'Can not download image {url}')
-                return 1, None
+                return 1, url
 
         except (httpx.HTTPStatusError, httpx.TimeoutException, httpx.ConnectError) as e:
             if retried < 3:
-                logger.info(f'Download {filename} failed, retrying({retried + 1}) times...')
+                logger.warning(f'Download {filename} failed, retrying({retried + 1}) times...')
                 return await self.download(
                     url=url,
                     folder=folder,
@@ -98,7 +101,8 @@ class Downloader(Singleton):
                     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)
@@ -110,10 +114,10 @@ class Downloader(Singleton):
             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
 
@@ -152,6 +156,7 @@ class Downloader(Singleton):
             return True
 
         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

nhentai/parser.py

@@ -141,23 +141,26 @@ def doujinshi_parser(id_, counter=0):
     title = doujinshi_info.find('h1').text
     pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
     subtitle = doujinshi_info.find('h2')
-    favorite_counts = str(doujinshi_info.find('span', class_='nobold').find('span', class_='count'))
+    favorite_counts = 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['favorite_counts'] = int(favorite_counts.text.strip()) if favorite_counts else 0
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
+    # img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
-                       doujinshi_cover.a.img.attrs['data-src'])
+    #                   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)
+        base_name = os.path.basename(i.img.attrs['data-src'])
-        ext.append(ext_name)
+        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(f'Tried yo get image id failed of id: {id_}')

nhentai/serializer.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 import json
 import os
+
+from nhentai.constant import PATH_SEPARATOR
 from xml.sax.saxutils import escape
 from nhentai.constant import LANGUAGE_ISO
 
@@ -82,7 +84,7 @@ def xml_write_simple_tag(f, name, val, indent=1):
 
 def merge_json():
     lst = []
-    output_dir = "./"
+    output_dir = f".{PATH_SEPARATOR}"
     os.chdir(output_dir)
     doujinshi_dirs = next(os.walk('.'))[1]
     for folder in doujinshi_dirs:

nhentai/utils.py

@@ -14,10 +14,12 @@ from typing import Tuple
 from requests.structures import CaseInsensitiveDict
 
 from nhentai import constant
+from nhentai.constant import PATH_SEPARATOR
 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):
@@ -99,9 +101,9 @@ def parse_doujinshi_obj(
         file_type: str = ''
 ) -> Tuple[str, str]:
 
-    filename = f'./doujinshi.{file_type}'
+    filename = f'.{PATH_SEPARATOR}doujinshi.{file_type}'
-    doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
     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':
@@ -111,6 +113,8 @@ def parse_doujinshi_obj(
             _filename = _filename.replace('/', '-')
 
         filename = os.path.join(output_dir, _filename)
+    else:
+        doujinshi_dir = f'.{PATH_SEPARATOR}'
 
     return doujinshi_dir, filename
 
@@ -130,7 +134,7 @@ 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', '.webp'):
+        if not os.path.splitext(image)[1] in EXTENSIONS:
             continue
         image_html += f'<img src="{image}" class="image-item"/>\n'
 
@@ -175,7 +179,7 @@ def move_to_folder(output_dir='.', doujinshi_obj=None, file_type=None):
     shutil.move(filename, os.path.join(doujinshi_dir, os.path.basename(filename)))
 
 
-def generate_main_html(output_dir='./'):
+def generate_main_html(output_dir=f'.{PATH_SEPARATOR}'):
     """
     Generate a main html to show all the contains doujinshi.
     With a link to their `index.html`.
@@ -256,7 +260,7 @@ def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=Fa
             import img2pdf
 
             """Write images to a PDF file using img2pdf."""
-            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.webp'))]
+            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}')
@@ -308,7 +312,8 @@ 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(','):
@@ -333,7 +338,7 @@ def generate_metadata_file(output_dir, doujinshi_obj):
 
     fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
               'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
-              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'TAGS',  'FAVORITE COUNTS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
               'SERIES', 'PARODY', 'URL']
 
     temp_dict = CaseInsensitiveDict(dict(doujinshi_obj.table))

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.17.2"
+version = "0.5.19"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"
@@ -22,4 +22,4 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
-nhentai = 'nhentai.command:main'
+nhentai = 'nhentai.command:main'