0.6.0-beta #394

Update installation instructions in README.rst

README.rst

@@ -22,7 +22,7 @@ From Github:
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
-    python setup.py install
+    pip install --no-cache-dir .
 
 Build Docker container:
 

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.23'
+__version__ = '0.6.0-beta'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -65,6 +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('--no-download', dest='no_download', action='store_true', default=False,
+                      help='download doujinshi (for search results)')
     parser.add_option('--show', '-S', dest='is_show', action='store_true',
                       help='just show the doujinshi information')
 
@@ -107,7 +109,6 @@ def cmd_parser():
                       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')
 
     parser.add_option('--no-filename-padding', action='store_true', dest='no_filename_padding',
                       default=False, help='no padding in the images filename, such as \'001.jpg\'')
@@ -123,16 +124,19 @@ def cmd_parser():
                       help='generate Comic Book CBZ File')
     parser.add_option('--pdf', '-P', dest='is_pdf', action='store_true',
                       help='generate PDF file')
+
+    parser.add_option('--meta', dest='generate_metadata', action='store_true', default=False,
+                      help='generate a metadata file in doujinshi format')
+    parser.add_option('--update-meta', dest='update_metadata', action='store_true', default=False,
+                      help='update the metadata file of a doujinshi, update CBZ metadata if exists')
+
     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', dest='regenerate', action='store_true', default=False,
                       help='regenerate the cbz or pdf file if exists')
-    parser.add_option('--no-metadata', dest='no_metadata', action='store_true', default=False,
-                      help='don\'t generate metadata json file in doujinshi output path')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
@@ -188,7 +192,6 @@ def cmd_parser():
 
     if any([args.cookie, args.useragent, args.language]):
         sys.exit(0)
-    # -- end set config
 
     if args.proxy is not None:
         proxy_url = urlparse(args.proxy)
@@ -242,8 +245,4 @@ def cmd_parser():
         logger.critical('Maximum number of used threads is 15')
         sys.exit(1)
 
-    if args.dryrun and (args.is_cbz or args.is_pdf):
-        logger.critical('Cannot generate PDF or CBZ during dry-run')
-        sys.exit(1)
-
     return args

nhentai/command.py

@@ -13,7 +13,7 @@ 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_doc, generate_main_html, generate_metadata_file, \
+from nhentai.utils import generate_html, generate_doc, generate_main_html, generate_metadata, \
     paging, check_cookie, signal_handler, DB, move_to_folder
 
 
@@ -97,17 +97,15 @@ def main():
             else:
                 continue
 
-            if not options.dryrun:
+            doujinshi.downloader = downloader
-                doujinshi.downloader = downloader
 
-                if doujinshi.check_if_need_download(options):
+            if doujinshi.check_if_need_download(options):
-                    doujinshi.download()
+                doujinshi.download()
-                else:
+            else:
-                    logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {doujinshi.name}')
+                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)
+                generate_metadata(options.output_dir, doujinshi)
 
             if options.is_save_download_history:
                 with DB() as db:
@@ -116,9 +114,6 @@ def main():
             if not options.is_nohtml:
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
 
-            if not options.no_metadata:
-                generate_doc('json', options.output_dir, doujinshi, options.regenerate)
-
             if options.is_cbz:
                 generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
 

nhentai/doujinshi.py

@@ -77,6 +77,9 @@ class Doujinshi(object):
         logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
 
     def check_if_need_download(self, options):
+        if options.no_download:
+            return False
+
         base_path = os.path.join(self.downloader.path, self.filename)
 
         # regenerate, re-download

nhentai/parser.py

@@ -165,7 +165,9 @@ def doujinshi_parser(id_, counter=0):
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
     # 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'])
+
+    # fix cover.webp.webp
+    img_id = re.search(r'/galleries/(\d+)/cover(\.webp|\.jpg|\.png)?\.\w+$', doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):

nhentai/serializer.py

@@ -4,6 +4,7 @@ import os
 
 from nhentai.constant import PATH_SEPARATOR, LANGUAGE_ISO
 from xml.sax.saxutils import escape
+from requests.structures import CaseInsensitiveDict
 
 
 def serialize_json(doujinshi, output_dir: str):
@@ -77,6 +78,26 @@ def serialize_comic_xml(doujinshi, output_dir):
         f.write('</ComicInfo>')
 
 
+def serialize_info_txt(doujinshi, output_dir: str):
+    info_txt_path = os.path.join(output_dir, 'info.txt')
+    f = open(info_txt_path, 'w', encoding='utf-8')
+
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
+              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
+              'TAGS',  'FAVORITE COUNTS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+
+    temp_dict = CaseInsensitiveDict(dict(doujinshi.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.info.get(i.lower(), None) if v is None else v
+        v = doujinshi.info.get(f'{i.lower()}s', "Unknown") if v is None else v
+        f.write(f'{i}: {v}\n')
+
+    f.close()
+
+
 def xml_write_simple_tag(f, name, val, indent=1):
     f.write(f'{" "*indent}<{name}>{escape(str(val))}</{name}>\n')
 
@@ -131,3 +152,4 @@ def set_js_database():
         indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)
+

nhentai/utils.py

@@ -11,12 +11,11 @@ import requests
 import sqlite3
 import urllib.parse
 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_comic_xml, serialize_json, set_js_database
+from nhentai.serializer import serialize_comic_xml, serialize_json, serialize_info_txt, set_js_database
 
 MAX_FIELD_LENGTH = 100
 EXTENSIONS = ('.png', '.jpg', '.jpeg', '.gif', '.webp')
@@ -105,9 +104,6 @@ def parse_doujinshi_obj(
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
         _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('/', '-')
 
@@ -115,6 +111,9 @@ def parse_doujinshi_obj(
     else:
         doujinshi_dir = f'.{PATH_SEPARATOR}'
 
+    if not os.path.exists(doujinshi_dir):
+        os.makedirs(doujinshi_dir)
+
     return doujinshi_dir, filename
 
 
@@ -235,8 +234,20 @@ def generate_main_html(output_dir=f'.{PATH_SEPARATOR}'):
         logger.warning(f'Writing Main Viewer failed ({e})')
 
 
-def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
+def generate_cbz(doujinshi_dir, filename):
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
 
+    logger.info(f'Writing CBZ file to path: {filename}')
+    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)
+
+    logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
+
+
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=False):
     doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type)
 
     if os.path.exists(f'{doujinshi_dir}.{file_type}') and not regenerate:
@@ -244,16 +255,9 @@ def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=Fa
         return
 
     if file_type == 'cbz':
-        file_list = os.listdir(doujinshi_dir)
+        serialize_comic_xml(doujinshi_obj, doujinshi_dir)
-        file_list.sort()
+        generate_cbz(doujinshi_dir, filename)
 
-        logger.info(f'Writing CBZ file to path: {filename}')
-        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)
-
-        logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
     elif file_type == 'pdf':
         try:
             import img2pdf
@@ -273,9 +277,16 @@ def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, regenerate=Fa
 
         except ImportError:
             logger.error("Please install img2pdf package by using pip.")
+    else:
+        raise ValueError('invalid file type')
 
-    elif file_type == 'json':
+
-        serialize_json(doujinshi_obj, doujinshi_dir)
+def generate_metadata(output_dir, doujinshi_obj=None):
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '')
+    serialize_json(doujinshi_obj, doujinshi_dir)
+    serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+    serialize_info_txt(doujinshi_obj, doujinshi_dir)
+    logger.log(16, f'Metadata files have been written to "{doujinshi_dir}"')
 
 
 def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
@@ -332,29 +343,6 @@ def paging(page_string):
     return page_list
 
 
-def generate_metadata_file(output_dir, doujinshi_obj):
-
-    info_txt_path = os.path.join(output_dir, doujinshi_obj.filename, 'info.txt')
-
-    f = open(info_txt_path, 'w', encoding='utf-8')
-
-    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
-              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
-              'TAGS',  'FAVORITE COUNTS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
-              'SERIES', 'PARODY', 'URL']
-
-    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}"')
-
-
 class DB(object):
     conn = None
     cur = None

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.23"
+version = "0.6.0-beta"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"