improve #342

nhentai/cmdline.py

@@ -118,8 +118,8 @@ def cmd_parser():
                       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',

nhentai/command.py

@@ -11,7 +11,7 @@ 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_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
 
 
@@ -85,21 +85,22 @@ def main():
             else:
                 continue
 
-            file_type = ''
-            if options.is_cbz: file_type = '.cbz'
-            elif options.is_pdf: file_type = '.pdf'
-
             if not options.dryrun:
                 doujinshi.downloader = downloader
-                result = doujinshi.download(regenerate_cbz=options.regenerate_cbz, file_type=file_type)
+
+                result = doujinshi.download(skip_exists=not options.regenerate)
                 # Already downloaded; continue on with the other doujins.
-                if not result: continue
+                if not result:
+                    continue
 
             if options.generate_metadata:
                 table = doujinshi.table
-                result = generate_metadata_file(options.output_dir, table, doujinshi, file_type)
+                result = generate_metadata_file(options.output_dir, table, doujinshi)
                 # Already downloaded; continue on with the other doujins.
-                if not result: continue
+                # if cbz / pdf file exists, skip the download process?
+                # regenerate but not re-download?
+                if not result:
+                    continue
 
             if options.is_save_download_history:
                 with DB() as db:
@@ -107,10 +108,14 @@ 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, True, options.move_to_folder)
+            if options.is_cbz:
-            elif options.is_pdf:
+                generate_doc('cbz', options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder,
-                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder)
+                             options.regenerate)
+
+            if options.is_pdf:
+                generate_doc('pdf', options.output_dir, doujinshi, options.rm_origin_dir, options.move_to_folder,
+                             options.regenerate)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)

nhentai/doujinshi.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-import datetime
+import os
 
 from tabulate import tabulate
 
@@ -72,8 +72,14 @@ 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, file_type=''):
+    def download(self, skip_exists=True):
         logger.info(f'Starting to download doujinshi: {self.name}')
+
+        base_path = os.path.join(self.downloader.path, self.filename)
+        if (os.path.exists(base_path + '.pdf') or os.path.exists(base_path + '.cbz')) and skip_exists:
+            logger.info(f'Skip download doujinshi because a PDF/CBZ file exists of doujinshi {self.name}')
+            return False
+
         if self.downloader:
             download_queue = []
             if len(self.ext) != self.pages:
@@ -82,7 +88,7 @@ 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]}')
 
-            return self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz, file_type=file_type)
+            return self.downloader.start_download(download_queue, self.filename)
         else:
             logger.critical('Downloader has not been loaded')
             return False

nhentai/downloader.py

@@ -115,18 +115,13 @@ class Downloader(Singleton):
 
         return 1, url
 
-
+    def start_download(self, queue, folder='') -> bool:
-    def start_download(self, queue, folder='', regenerate_cbz=False, file_type='') -> bool:
         if not isinstance(folder, (str, )):
             folder = str(folder)
 
         if self.path:
             folder = os.path.join(self.path, folder)
 
-        if file_type != '' and os.path.exists(folder + file_type) and not regenerate_cbz:
-            logger.warning(f'Skipped download: "{folder}{file_type}" already exists')
-            return False
-
         logger.info(f'Doujinshi will be saved at "{folder}"')
         if not os.path.exists(folder):
             try:

nhentai/utils.py

@@ -15,7 +15,6 @@ 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
 
 
@@ -41,7 +40,8 @@ def check_cookie():
 
     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]}')
 
@@ -70,37 +70,27 @@ def readfile(path):
 def parse_doujinshi_obj(
         output_dir: str,
         doujinshi_obj=None,
-    file_type: str = '',
+        file_type: str = ''
-    write_comic_info = False
+) -> Tuple[str, str]:
-) -> Tuple[str, str, bool]:
-    doujinshi_dir = '.'
     filename = './doujinshi' + file_type
-    already_downloaded = False
 
     doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    if doujinshi_obj is not None and file_type != '.html':
+    if doujinshi_obj is not None:
-        if os.path.exists(doujinshi_dir + file_type):
+        _filename = f'{doujinshi_obj.filename}.{file_type}'
-            already_downloaded = True
-        elif file_type != '':
-            _filename = f'{doujinshi_obj.filename}{file_type}'
 
-            if file_type == '.cbz' and write_comic_info:
+        if file_type == 'cbz':
             serialize_comic_xml(doujinshi_obj, doujinshi_dir)
 
-            if file_type == '.pdf':
+        if file_type == 'pdf':
             _filename = _filename.replace('/', '-')
 
         filename = os.path.join(output_dir, _filename)
 
-    return doujinshi_dir, filename, already_downloaded
+    return doujinshi_dir, filename
 
 
 def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
-    doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj, '.html')
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj, '.html')
-    if already_downloaded:
-        logger.info(f'Skipped download: {doujinshi_dir} already exists')
-        return
-
     image_html = ''
 
     if not os.path.exists(doujinshi_dir):
@@ -195,12 +185,16 @@ 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, move_to_folder=False):
+def generate_doc(file_type='', output_dir='.', doujinshi_obj=None, rm_origin_dir=False,
-    doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj, '.cbz', write_comic_info)
+                 move_to_folder=False, regenerate=False):
-    if already_downloaded:
+
-        logger.info(f'Skipped download: {doujinshi_dir} already exists')
+    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 download: {doujinshi_dir}.{file_type} already exists')
         return
 
+    if file_type == 'cbz':
         file_list = os.listdir(doujinshi_dir)
         file_list.sort()
 
@@ -210,33 +204,12 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
                 image_path = os.path.join(doujinshi_dir, image)
                 cbz_pf.write(image_path, image)
 
-    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)
-
         logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
-
+    elif file_type == 'pdf':
-
-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."""
-        doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj, '.pdf')
-        if already_downloaded:
-            logger.info(f'Skipped download: {doujinshi_dir} already exists')
-            return
-
             file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif'))]
             file_list.sort()
 
@@ -247,6 +220,11 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, move_t
                 )
                 pdf_f.write(img2pdf.convert(full_path_list, rotation=img2pdf.Rotation.ifvalid))
 
+            logger.log(16, f'PDF file has been written to "{filename}"')
+
+        except ImportError:
+            logger.error("Please install img2pdf package by using pip.")
+
     if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
@@ -261,11 +239,6 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, move_t
 
         shutil.move(filename, doujinshi_dir)
 
-        logger.log(16, f'PDF file has been written to "{filename}"')
-
-    except ImportError:
-        logger.error("Please install img2pdf package by using pip.")
-
 
 def format_filename(s, length=MAX_FIELD_LENGTH, _truncate_only=False):
     """
@@ -320,20 +293,12 @@ def paging(page_string):
     return page_list
 
 
-def generate_metadata_file(output_dir, table, doujinshi_obj=None, check_file_type=''):
+def generate_metadata_file(output_dir, table, doujinshi_obj=None):
     logger.info('Writing Metadata Info')
 
-    doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type=check_file_type)
+    doujinshi_dir, filename = parse_doujinshi_obj(output_dir, doujinshi_obj)
     info_txt_path = os.path.join(doujinshi_dir, 'info.txt')
 
-    if already_downloaded:
-        # Ensure that info.txt was generated for the folder (if it exists) before exiting.
-        if os.path.exists(doujinshi_dir) and os.path.exists(info_txt_path):
-            logger.info(f'Skipped download: {info_txt_path} already exists')
-            return False
-
-    logger.info(doujinshi_dir)
-
     f = open(info_txt_path, 'w', encoding='utf-8')
 
     fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',