fix #349

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/cmdline.py

@@ -79,7 +79,7 @@ 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])',

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

@@ -38,8 +38,12 @@ 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}://i1.{urlparse(BASE_URL).hostname}',
+    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/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

@@ -151,13 +151,18 @@ def doujinshi_parser(id_, counter=0):
     doujinshi['favorite_counts'] = favorite_counts.strip()
 
     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/utils.py

@@ -18,6 +18,7 @@ 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):
@@ -100,8 +101,8 @@ def parse_doujinshi_obj(
 ) -> Tuple[str, str]:
 
     filename = f'./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 +112,8 @@ def parse_doujinshi_obj(
             _filename = _filename.replace('/', '-')
 
         filename = os.path.join(output_dir, _filename)
+    else:
+        doujinshi_dir = './'
 
     return doujinshi_dir, filename
 
@@ -130,7 +133,7 @@ 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'
 
@@ -256,7 +259,7 @@ 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 +311,8 @@ 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(','):