Bug fixes & improve duplicate checks

nhentai/command.py

@@ -85,13 +85,21 @@ 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
-                doujinshi.download(regenerate_cbz=options.regenerate_cbz)
+                result = doujinshi.download(regenerate_cbz=options.regenerate_cbz, file_type=file_type)
+                # Already downloaded; continue on with the other doujins.
+                if not result: continue
 
             if options.generate_metadata:
                 table = doujinshi.table
-                generate_metadata_file(options.output_dir, table, doujinshi)
+                result = generate_metadata_file(options.output_dir, table, doujinshi, file_type)
+                # Already downloaded; continue on with the other doujins.
+                if not result: continue
 
             if options.is_save_download_history:
                 with DB() as db:

nhentai/doujinshi.py

@@ -72,7 +72,7 @@ def __repr__(self):
     def show(self):
         logger.info(f'Print doujinshi information of {self.id}\n{tabulate(self.table)}')
 
-    def download(self, regenerate_cbz=False):
+    def download(self, regenerate_cbz=False, file_type=''):
         logger.info(f'Starting to download doujinshi: {self.name}')
         if self.downloader:
             download_queue = []
@@ -82,9 +82,10 @@ def download(self, regenerate_cbz=False):
             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]}')
 
-            self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz)
+            return self.downloader.start_download(download_queue, self.filename, regenerate_cbz=regenerate_cbz, file_type=file_type)
         else:
             logger.critical('Downloader has not been loaded')
+            return False
 
 
 if __name__ == '__main__':

nhentai/downloader.py

@@ -57,7 +57,7 @@ def download(self, url, folder='', filename='', retried=0, proxy=None):
         save_file_path = os.path.join(folder, base_filename.zfill(3) + extension)
         try:
             if os.path.exists(save_file_path):
-                logger.warning(f'Ignored exists file: {save_file_path}')
+                logger.warning(f'Skipped download: {save_file_path} already exists')
                 return 1, url
 
             response = None
@@ -115,17 +115,17 @@ def download(self, url, folder='', filename='', retried=0, proxy=None):
 
         return 1, url
 
-    def start_download(self, queue, folder='', regenerate_cbz=False):
+
+    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 os.path.exists(folder + '.cbz'):
-            if not regenerate_cbz:
-                logger.warning(f'CBZ file "{folder}.cbz" exists, ignored download request')
-                return
+        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):
@@ -134,11 +134,9 @@ def start_download(self, queue, folder='', regenerate_cbz=False):
             except EnvironmentError as e:
                 logger.critical(str(e))
 
-        else:
-            logger.warning(f'Path "{folder}" already exist.')
-
         if os.getenv('DEBUG', None) == 'NODOWNLOAD':
-            return
+            # Assuming we want to continue with rest of process.
+            return True
         queue = [(self, url, folder, constant.CONFIG['proxy']) for url in queue]
 
         pool = multiprocessing.Pool(self.size, init_worker)
@@ -147,6 +145,8 @@ def start_download(self, queue, folder='', regenerate_cbz=False):
         pool.close()
         pool.join()
 
+        return True
+
 
 def download_wrapper(obj, url, folder='', proxy=None):
     if sys.platform == 'darwin' or semaphore.get_value():

nhentai/utils.py

@@ -5,9 +5,11 @@
 import os
 import zipfile
 import shutil
+
 import requests
 import sqlite3
 import urllib.parse
+from typing import Optional, Tuple
 
 from nhentai import constant
 from nhentai.logger import logger
@@ -65,13 +67,41 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
-    image_html = ''
+def parse_doujinshi_obj(
+    output_dir: str,
+    doujinshi_obj = None,
+    file_type: str = '',
+    write_comic_info = False
+) -> Tuple[str, str, bool]:
+    doujinshi_dir = '.'
+    filename = './doujinshi' + file_type
+    already_downloaded = False
 
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    else:
-        doujinshi_dir = '.'
+        if os.path.exists(doujinshi_dir + file_type):
+            already_downloaded = True
+        elif file_type != '':
+            _filename = f'{doujinshi_obj.filename}{file_type}'
+
+            if file_type == '.cbz' and write_comic_info:
+                serialize_comic_xml(doujinshi_obj, doujinshi_dir)
+
+            if file_type == '.pdf':
+                _filename = _filename.replace('/', '-')
+
+            filename = os.path.join(output_dir, _filename)
+
+    return doujinshi_dir, filename, already_downloaded
+
+
+def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
+    doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj)
+    if already_downloaded:
+        logger.info(f'Skipped download: {doujinshi_dir} already exists')
+        return
+
+    image_html = ''
 
     if not os.path.exists(doujinshi_dir):
         logger.warning(f'Path "{doujinshi_dir}" does not exist, creating.')
@@ -166,23 +196,16 @@ def generate_main_html(output_dir='./'):
 
 
 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')
-    else:
-        cbz_filename = './doujinshi.cbz'
-        doujinshi_dir = '.'
+    doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj, '.cbz', write_comic_info)
+    if already_downloaded:
+        logger.info(f'Skipped download: {doujinshi_dir} already exists')
+        return
 
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
-    logger.info(f'Writing CBZ file to path: {cbz_filename}')
-    with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
+    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)
@@ -191,40 +214,34 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
         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}")
+        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)
+        shutil.move(filename, doujinshi_dir)
 
-    logger.log(16, f'Comic Book CBZ file has been written to "{doujinshi_dir}"')
+    logger.log(16, f'Comic Book CBZ file has been written to "{filename}"')
 
 
 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'{filename}.pdf'
-            )
-        else:
-            pdf_filename = './doujinshi.pdf'
-            doujinshi_dir = '.'
+        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 = os.listdir(doujinshi_dir)
+        file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif'))]
         file_list.sort()
 
-        logger.info(f'Writing PDF file to path: {pdf_filename}')
-        with open(pdf_filename, 'wb') as pdf_f:
+        logger.info(f'Writing PDF file to path: {filename}')
+        with open(filename, 'wb') as pdf_f:
             full_path_list = (
                 [os.path.join(doujinshi_dir, image) for image in file_list]
             )
@@ -242,9 +259,9 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, move_t
                     except Exception as e:
                         print(f"Error deleting file: {e}")
 
-            shutil.move(pdf_filename, doujinshi_dir)
+            shutil.move(filename, doujinshi_dir)
 
-        logger.log(16, f'PDF file has been written to "{doujinshi_dir}"')
+        logger.log(16, f'PDF file has been written to "{filename}"')
 
     except ImportError:
         logger.error("Please install img2pdf package by using pip.")
@@ -303,17 +320,21 @@ def paging(page_string):
     return page_list
 
 
-def generate_metadata_file(output_dir, table, doujinshi_obj=None):
+def generate_metadata_file(output_dir, table, doujinshi_obj=None, check_file_type=''):
     logger.info('Writing Metadata Info')
 
-    if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
-    else:
-        doujinshi_dir = '.'
+    doujinshi_dir, filename, already_downloaded = parse_doujinshi_obj(output_dir, doujinshi_obj, file_type=check_file_type)
+    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(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
+    f = open(info_txt_path, 'w', encoding='utf-8')
 
     fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'GROUPS', 'CIRCLE', 'SCANLATOR',
               'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
@@ -330,6 +351,8 @@ def generate_metadata_file(output_dir, table, doujinshi_obj=None):
 
     f.close()
 
+    return True
+
 
 class DB(object):
     conn = None