remove debug print

add webp support

.gitignore

@@ -8,3 +8,4 @@ dist/
 output/
 venv/
 .vscode/
+test-output

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.5.9'
+__version__ = '0.5.12'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/command.py

@@ -94,6 +94,7 @@ def main():
                     doujinshi.download()
                 else:
                     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)
@@ -106,10 +107,10 @@ def main():
                 generate_html(options.output_dir, doujinshi, template=constant.CONFIG['template'])
 
             if options.is_cbz:
-                generate_doc('cbz', options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_doc('cbz', options.output_dir, doujinshi, options.regenerate)
 
             if options.is_pdf:
-                generate_doc('pdf', options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_doc('pdf', options.output_dir, doujinshi, options.regenerate)
 
             if options.move_to_folder:
                 if options.is_cbz:

nhentai/constant.py

@@ -38,9 +38,9 @@ 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}://i3.{urlparse(BASE_URL).hostname}'
-    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}'
-    f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}'
+    f'{urlparse(BASE_URL).scheme}://i3.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i5.{urlparse(BASE_URL).hostname}',
+    f'{urlparse(BASE_URL).scheme}://i7.{urlparse(BASE_URL).hostname}',
 ]
 
 NHENTAI_HOME = get_nhentai_home()

nhentai/doujinshi.py

@@ -12,6 +12,7 @@ EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
     'g': 'gif',
+    'w': 'webp',
 }
 
 
@@ -75,26 +76,28 @@ class Doujinshi(object):
     def check_if_need_download(self, options):
         base_path = os.path.join(self.downloader.path, self.filename)
 
-        # doujinshi directory is not exist, we need to download definitely
-        if not (os.path.exists(base_path) and os.path.isdir(base_path)):
-            return True
-
-        # regenerate, we need to re-download from nhentai
+        # regenerate, re-download
         if options.regenerate:
             return True
 
+        # pdf or cbz file exists, skip re-download
+        # doujinshi directory may not exist b/c of --rm-origin-dir option set.
+        # user should pass --regenerate option to get back origin dir.
+        ret_pdf = ret_cbz = None
         if options.is_pdf:
-            file_ext = 'pdf'
-        elif options.is_cbz:
-            file_ext = 'cbz'
-        else:
-            # re-download
-            return True
+            ret_pdf = os.path.exists(f'{base_path}.pdf') or os.path.exists(f'{base_path}/{self.filename}.pdf')
 
-        # pdf or cbz file exists, we needn't to re-download it
-        if os.path.exists(f'{base_path}.{file_ext}') or os.path.exists(f'{base_path}/{self.filename}.{file_ext}'):
+        if options.is_cbz:
+            ret_cbz = os.path.exists(f'{base_path}.cbz') or os.path.exists(f'{base_path}/{self.filename}.cbz')
+
+        ret = list(filter(lambda s: s is not None, [ret_cbz, ret_pdf]))
+        if ret and all(ret):
             return False
 
+        # doujinshi directory doesn't exist, re-download
+        if not (os.path.exists(base_path) and os.path.isdir(base_path)):
+            return True
+
         # fallback
         return True
 

nhentai/downloader.py

@@ -69,7 +69,7 @@ class Downloader(Singleton):
                         if response.status_code != 200:
                             path = urlparse(url).path
                             for mirror in constant.IMAGE_URL_MIRRORS:
-                                print(f'{mirror}{path}')
+                                # print(f'{mirror}{path}')
                                 mirror_url = f'{mirror}{path}'
                                 response = request('get', mirror_url, stream=True,
                                                    timeout=self.timeout, proxies=proxy)

nhentai/parser.py

@@ -148,7 +148,7 @@ def doujinshi_parser(id_, counter=0):
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif|webp)$',
                        doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []

nhentai/utils.py

@@ -104,7 +104,7 @@ 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'):
+        if not os.path.splitext(image)[1] in ('.jpg', '.png', '.webp'):
             continue
         image_html += f'<img src="{image}" class="image-item"/>\n'
 
@@ -230,7 +230,7 @@ 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'))]
+            file_list = [f for f in os.listdir(doujinshi_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.webp'))]
             file_list.sort()
 
             logger.info(f'Writing PDF file to path: {filename}')
@@ -309,7 +309,7 @@ def generate_metadata_file(output_dir, doujinshi_obj):
               'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
               'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
               'SERIES', 'PARODY', 'URL']
-    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'DATE', 'CHARACTERS', 'AUTHOR', 'GROUPS',
                       'LANGUAGE', 'TAGS', 'URL', 'PAGES']
 
     for i in range(len(fields)):

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nhentai"
-version = "0.5.9"
+version = "0.5.12"
 description = "nhentai doujinshi downloader"
 authors = ["Ricter Z <ricterzheng@gmail.com>"]
 license = "MIT"

setup.cfg

@@ -1,3 +1,3 @@
 [metadata]
-description-file = README.rst
+description_file = README.rst