jmcomic 2.5.15__tar.gz → 2.5.17__tar.gz

{jmcomic-2.5.15/src/jmcomic.egg-info → jmcomic-2.5.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jmcomic
-Version: 2.5.15
+Version: 2.5.17
 Summary: Python API For JMComic (禁漫天堂)
 Home-page: https://github.com/hect0x7/JMComic-Crawler-Python
 Author: hect0x7

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/__init__.py

@@ -2,7 +2,7 @@
 # 被依赖方 <--- 使用方
 # config <--- entity <--- toolkit <--- client <--- option <--- downloader
 
-__version__ = '2.5.15'
+__version__ = '2.5.17'
 
 from .api import *
 from .jm_plugin import *

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/api.py

@@ -2,6 +2,7 @@ from .jm_downloader import *
 
 __DOWNLOAD_API_RET = Tuple[JmAlbumDetail, JmDownloader]
 
+
 def download_batch(download_api,
                    jm_id_iter: Union[Iterable, Generator],
                    option=None,

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/jm_client_impl.py

@@ -27,7 +27,7 @@ class AbstractJmClient(
         self.retry_times = retry_times
         self.domain_list = domain_list
         self.CLIENT_CACHE = None
-        self.__username = None  # help for favorite_folder method
+        self._username = None  # help for favorite_folder method
         self.enable_cache()
         self.after_init()
 
@@ -92,7 +92,7 @@ class AbstractJmClient(
             jm_log(self.log_topic(), self.decode(url))
         else:
             # 图片url
-            pass
+            self.update_request_with_specify_domain(kwargs, None, True)
 
         if domain_index != 0 or retry_count != 0:
             jm_log(f'req.retry',
@@ -133,7 +133,7 @@ class AbstractJmClient(
         """
         return resp
 
-    def update_request_with_specify_domain(self, kwargs: dict, domain: str):
+    def update_request_with_specify_domain(self, kwargs: dict, domain: Optional[str], is_image: bool = False):
         """
         域名自动切换时，用于更新请求参数的回调
         """
@@ -412,7 +412,7 @@ class JmHtmlClient(AbstractJmClient):
             return resp
 
         self['cookies'] = new_cookies
-        self.__username = username
+        self._username = username
 
         return resp
 
@@ -423,8 +423,8 @@ class JmHtmlClient(AbstractJmClient):
                         username='',
                         ) -> JmFavoritePage:
         if username == '':
-            ExceptionTool.require_true(self.__username is not None, 'favorite_folder方法需要传username参数')
-            username = self.__username
+            ExceptionTool.require_true(self._username is not None, 'favorite_folder方法需要传username参数')
+            username = self._username
 
         resp = self.get_jm_html(
             f'/user/{username}/favorite/albums',
@@ -463,7 +463,10 @@ class JmHtmlClient(AbstractJmClient):
 
         return resp
 
-    def update_request_with_specify_domain(self, kwargs: dict, domain: Optional[str]):
+    def update_request_with_specify_domain(self, kwargs: dict, domain: Optional[str], is_image=False):
+        if is_image:
+            return
+
         latest_headers = kwargs.get('headers', None)
         base_headers = self.get_meta_data('headers', None) or JmModuleConfig.new_html_headers(domain)
         base_headers.update(latest_headers or {})
@@ -909,8 +912,10 @@ class JmApiClient(AbstractJmClient):
 
         return resp
 
-    def update_request_with_specify_domain(self, kwargs: dict, domain: str):
-        pass
+    def update_request_with_specify_domain(self, kwargs: dict, domain: Optional[str], is_image=False):
+        if is_image:
+            # 设置APP端的图片请求headers
+            kwargs['headers'] = {**JmModuleConfig.APP_HEADERS_TEMPLATE, **JmModuleConfig.APP_HEADERS_IMAGE}
 
     # noinspection PyMethodMayBeStatic
     def decide_headers_and_ts(self, kwargs, url):
@@ -930,7 +935,7 @@ class JmApiClient(AbstractJmClient):
             token, tokenparam = JmCryptoTool.token_and_tokenparam(ts)
 
         # 设置headers
-        headers = kwargs.get('headers', None) or JmMagicConstants.APP_HEADERS_TEMPLATE.copy()
+        headers = kwargs.get('headers', None) or JmModuleConfig.APP_HEADERS_TEMPLATE.copy()
         headers.update({
             'token': token,
             'tokenparam': tokenparam,
@@ -973,6 +978,11 @@ class JmApiClient(AbstractJmClient):
             # 例如图片请求
             return resp
 
+        code = resp.status_code
+        if code >= 500:
+            msg = JmModuleConfig.JM_ERROR_STATUS_CODE.get(code, f'HTTP状态码: {code}')
+            ExceptionTool.raises_resp(f"禁漫API异常响应, {msg}", resp)
+
         url = resp.request.url
 
         if self.API_SCRAMBLE in url:

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/jm_config.py

@@ -59,50 +59,16 @@ class JmMagicConstants:
     SUB_SINGLE_JAPANESE = SUB_JAPANESE
     SUB_SINGLE_YOUTH = 'youth'
 
-    # 分页大小
-    PAGE_SIZE_SEARCH = 80
-    PAGE_SIZE_FAVORITE = 20
-
     # 图片分割参数
     SCRAMBLE_220980 = 220980
     SCRAMBLE_268850 = 268850
     SCRAMBLE_421926 = 421926  # 2023-02-08后改了图片切割算法
 
-    # 当本子没有作者名字时，顶替作者名字
-    DEFAULT_AUTHOR = 'default_author'
-
     # 移动端API密钥
     APP_TOKEN_SECRET = '18comicAPP'
     APP_TOKEN_SECRET_2 = '18comicAPPContent'
     APP_DATA_SECRET = '185Hcomic3PAPP7R'
-    APP_VERSION = '1.7.0'
-    APP_HEADERS_TEMPLATE = {
-        'Accept-Encoding': 'gzip',
-        'user-agent': 'Mozilla/5.0 (Linux; Android 9; V1938CT Build/PQ3A.190705.11211812; wv) AppleWebKit/537.36 (KHTML, '
-                      'like Gecko) Version/4.0 Chrome/91.0.4472.114 Safari/537.36',
-    }
-
-    # 网页端headers
-    HTML_HEADERS_TEMPLATE = {
-        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,'
-                  'application/signed-exchange;v=b3;q=0.7',
-        'accept-language': 'zh-CN,zh;q=0.9',
-        'cache-control': 'no-cache',
-        'dnt': '1',
-        'pragma': 'no-cache',
-        'priority': 'u=0, i',
-        'referer': 'https://18comic.vip/',
-        'sec-ch-ua': '"Chromium";v="124", "Google Chrome";v="124", "Not-A.Brand";v="99"',
-        'sec-ch-ua-mobile': '?0',
-        'sec-ch-ua-platform': '"Windows"',
-        'sec-fetch-dest': 'document',
-        'sec-fetch-mode': 'navigate',
-        'sec-fetch-site': 'none',
-        'sec-fetch-user': '?1',
-        'upgrade-insecure-requests': '1',
-        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 '
-                      'Safari/537.36',
-    }
+    APP_VERSION = '1.7.1'
 
 
 # 模块级别共用配置
@@ -123,13 +89,55 @@ class JmModuleConfig:
     # JM的异常网页code
     JM_ERROR_STATUS_CODE = {
         403: 'ip地区禁止访问/爬虫被识别',
+        500: '500: 禁漫服务器内部异常（可能是服务器过载，可以切换ip或稍后重试）',
         520: '520: Web server is returning an unknown error (禁漫服务器内部报错)',
         524: '524: The origin web server timed out responding to this request. (禁漫服务器处理超时)',
     }
 
+    # 分页大小
+    PAGE_SIZE_SEARCH = 80
+    PAGE_SIZE_FAVORITE = 20
+
     # 图片分隔相关
     SCRAMBLE_CACHE = {}
 
+    # 当本子没有作者名字时，顶替作者名字
+    DEFAULT_AUTHOR = 'default_author'
+
+    APP_HEADERS_TEMPLATE = {
+        'Accept-Encoding': 'gzip, deflate',
+        'user-agent': 'Mozilla/5.0 (Linux; Android 9; V1938CT Build/PQ3A.190705.11211812; wv) AppleWebKit/537.36 (KHTML, '
+                      'like Gecko) Version/4.0 Chrome/91.0.4472.114 Safari/537.36',
+    }
+
+    APP_HEADERS_IMAGE = {
+        'Accept': 'image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8',
+        'X-Requested-With': 'com.jiaohua_browser',
+        'Referer': 'https://www.jmfreedomproxy.xyz/',
+        'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
+    }
+
+    # 网页端headers
+    HTML_HEADERS_TEMPLATE = {
+        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,'
+                  'application/signed-exchange;v=b3;q=0.7',
+        'accept-language': 'zh-CN,zh;q=0.9',
+        'cache-control': 'no-cache',
+        'dnt': '1',
+        'pragma': 'no-cache',
+        'priority': 'u=0, i',
+        'referer': 'https://18comic.vip/',
+        'sec-ch-ua': '"Chromium";v="124", "Google Chrome";v="124", "Not-A.Brand";v="99"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': '"Windows"',
+        'sec-fetch-dest': 'document',
+        'sec-fetch-mode': 'navigate',
+        'sec-fetch-site': 'none',
+        'sec-fetch-user': '?1',
+        'upgrade-insecure-requests': '1',
+        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 '
+                      'Safari/537.36',
+    }
     # cookies，目前只在移动端使用，因为移动端请求接口须携带，但不会校验cookies的内容。
     APP_COOKIES = None
 
@@ -335,7 +343,7 @@ class JmModuleConfig:
         """
         网页端的headers
         """
-        headers = JmMagicConstants.HTML_HEADERS_TEMPLATE.copy()
+        headers = cls.HTML_HEADERS_TEMPLATE.copy()
         headers.update({
             'authority': domain,
             'origin': f'https://{domain}',

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/jm_entity.py

@@ -1,3 +1,5 @@
+from functools import lru_cache
+
 from common import *
 
 from .jm_config import *
@@ -303,7 +305,8 @@ class JmPhotoDetail(DetailEntity, Downloadable):
         # 2. 值目前在网页端只在photo页面的图片标签的data-original属性出现
         # 这里的模拟思路是，获取到第一个图片标签的data-original，
         # 取出其query参数 → self.data_original_query_params, 该值未来会传递给 JmImageDetail
-        self.data_original_query_params = self.get_data_original_query_params(data_original_0)
+        # self.data_original_query_params = self.get_data_original_query_params(data_original_0)
+        self.data_original_query_params = None
 
     @property
     def is_single_album(self) -> bool:
@@ -353,7 +356,7 @@ class JmPhotoDetail(DetailEntity, Downloadable):
             return self._author.strip()
 
         # 使用默认
-        return JmMagicConstants.DEFAULT_AUTHOR
+        return JmModuleConfig.DEFAULT_AUTHOR
 
     def create_image_detail(self, index) -> JmImageDetail:
         # 校验参数
@@ -400,6 +403,7 @@ class JmPhotoDetail(DetailEntity, Downloadable):
     def id(self):
         return self.photo_id
 
+    @lru_cache(None)
     def getindex(self, index) -> JmImageDetail:
         return self.create_image_detail(index)
 
@@ -472,7 +476,7 @@ class JmAlbumDetail(DetailEntity, Downloadable):
         if len(self.authors) >= 1:
             return self.authors[0]
 
-        return JmMagicConstants.DEFAULT_AUTHOR
+        return JmModuleConfig.DEFAULT_AUTHOR
 
     @property
     def id(self):
@@ -514,6 +518,7 @@ class JmAlbumDetail(DetailEntity, Downloadable):
 
         return photo
 
+    @lru_cache(None)
     def getindex(self, item) -> JmPhotoDetail:
         return self.create_photo_detail(item)
 
@@ -608,7 +613,7 @@ class JmSearchPage(JmPageContent):
 
     @property
     def page_size(self) -> int:
-        return JmMagicConstants.PAGE_SIZE_SEARCH
+        return JmModuleConfig.PAGE_SIZE_SEARCH
 
     # 下面的方法是对单个album的包装
 
@@ -649,7 +654,7 @@ class JmFavoritePage(JmPageContent):
 
     @property
     def page_size(self) -> int:
-        return JmMagicConstants.PAGE_SIZE_FAVORITE
+        return JmModuleConfig.PAGE_SIZE_FAVORITE
 
     def iter_folder_id_name(self) -> Generator[Tuple[str, str], None, None]:
         """

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/jm_option.py

@@ -270,15 +270,7 @@ class JmOption:
         )
 
         if ensure_exists:
-            try:
-                mkdir_if_not_exists(save_dir)
-            except OSError as e:
-                if e.errno == 36:
-                    # 目录名过长
-                    limit = JmModuleConfig.VAR_FILE_NAME_LENGTH_LIMIT
-                    jm_log('error', f'目录名过长，无法创建目录，强制缩短到{limit}个字符并重试')
-                    save_dir = save_dir[0:limit]
-                    mkdir_if_not_exists(save_dir)
+            save_dir = JmcomicText.try_mkdir(save_dir)
 
         return save_dir
 
@@ -517,13 +509,21 @@ class JmOption:
 
     # 下面的方法提供面向对象的调用风格
 
-    def download_album(self, album_id):
+    def download_album(self,
+                       album_id,
+                       downloader=None,
+                       callback=None,
+                       ):
         from .api import download_album
-        download_album(album_id, self)
+        download_album(album_id, self, downloader, callback)
 
-    def download_photo(self, photo_id):
+    def download_photo(self,
+                       photo_id,
+                       downloader=None,
+                       callback=None
+                       ):
         from .api import download_photo
-        download_photo(photo_id, self)
+        download_photo(photo_id, self, downloader, callback)
 
     # 下面的方法为调用插件提供支持
 

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/jm_plugin.py

@@ -601,7 +601,7 @@ class FavoriteFolderExportPlugin(JmOptionPlugin):
         for page in page_data:
             for aid, extra in page.content:
                 data.append(
-                    (aid, extra.get('author', '') or JmMagicConstants.DEFAULT_AUTHOR, extra['name'])
+                    (aid, extra.get('author', '') or JmModuleConfig.DEFAULT_AUTHOR, extra['name'])
                 )
 
         if len(data) == 0:
@@ -734,13 +734,17 @@ class Img2pdfPlugin(JmOptionPlugin):
     plugin_key = 'img2pdf'
 
     def invoke(self,
-               photo: JmPhotoDetail,
+               photo: JmPhotoDetail = None,
+               album: JmAlbumDetail = None,
                downloader=None,
                pdf_dir=None,
                filename_rule='Pid',
                delete_original_file=False,
                **kwargs,
                ):
+        if photo is None and album is None:
+            jm_log('wrong_usage', 'img2pdf必须运行在after_photo或after_album时')
+
         try:
             import img2pdf
         except ImportError:
@@ -749,28 +753,50 @@ class Img2pdfPlugin(JmOptionPlugin):
 
         self.delete_original_file = delete_original_file
 
-        # 处理文件夹配置
-        filename = DirRule.apply_rule_directly(None, photo, filename_rule)
-        photo_dir = self.option.decide_image_save_dir(photo)
-
         # 处理生成的pdf文件的路径
-        if pdf_dir is None:
-            pdf_dir = photo_dir
-        else:
-            pdf_dir = fix_filepath(pdf_dir, True)
-            mkdir_if_not_exists(pdf_dir)
+        pdf_dir = self.ensure_make_pdf_dir(pdf_dir)
+
+        # 处理pdf文件名
+        filename = DirRule.apply_rule_directly(album, photo, filename_rule)
 
+        # pdf路径
         pdf_filepath = os.path.join(pdf_dir, f'{filename}.pdf')
 
         # 调用 img2pdf 把 photo_dir 下的所有图片转为pdf
-        all_img = files_of_dir(photo_dir)
-        with open(pdf_filepath, 'wb') as f:
-            f.write(img2pdf.convert(all_img))
+        img_path_ls, img_dir_ls = self.write_img_2_pdf(pdf_filepath, album, photo)
+        self.log(f'Convert Successfully: JM{album or photo} → {pdf_filepath}')
 
         # 执行删除
-        self.log(f'Convert Successfully: JM{photo.id} → {pdf_filepath}')
-        all_img.append(self.option.decide_image_save_dir(photo, ensure_exists=False))
-        self.execute_deletion(all_img)
+        img_path_ls += img_dir_ls
+        self.execute_deletion(img_path_ls)
+
+    def write_img_2_pdf(self, pdf_filepath, album: JmAlbumDetail, photo: JmPhotoDetail):
+        import img2pdf
+
+        if album is None:
+            img_dir_ls = [self.option.decide_image_save_dir(photo)]
+        else:
+            img_dir_ls = [self.option.decide_image_save_dir(photo) for photo in album]
+
+        img_path_ls = []
+
+        for img_dir in img_dir_ls:
+            imgs = files_of_dir(img_dir)
+            if not imgs:
+                continue
+            img_path_ls += imgs
+
+        with open(pdf_filepath, 'wb') as f:
+            f.write(img2pdf.convert(img_path_ls))
+
+        return img_path_ls, img_dir_ls
+
+    @staticmethod
+    def ensure_make_pdf_dir(pdf_dir: str):
+        pdf_dir = pdf_dir or os.getcwd()
+        pdf_dir = fix_filepath(pdf_dir, True)
+        mkdir_if_not_exists(pdf_dir)
+        return pdf_dir
 
 
 class JmServerPlugin(JmOptionPlugin):
@@ -1067,3 +1093,27 @@ class DeleteDuplicatedFilesPlugin(JmOptionPlugin):
                           [f'  {path}' for path in paths]
                 self.log('\n'.join(message))
                 self.execute_deletion(paths)
+
+
+class ReplacePathStringPlugin(JmOptionPlugin):
+    plugin_key = 'replace_path_string'
+
+    def invoke(self,
+               replace: Dict[str, str],
+               ):
+        if not replace:
+            return
+
+        old_decide_dir = self.option.decide_image_save_dir
+
+        def new_decide_dir(photo, ensure_exists=True) -> str:
+            original_path: str = old_decide_dir(photo, False)
+            for k, v in replace.items():
+                original_path = original_path.replace(k, v)
+
+            if ensure_exists:
+                JmcomicText.try_mkdir(original_path)
+
+            return original_path
+
+        self.option.decide_image_save_dir = new_decide_dir

{jmcomic-2.5.15 → jmcomic-2.5.17}/src/jmcomic/jm_toolkit.py

@@ -316,6 +316,19 @@ class JmcomicText:
         import zhconv
         return zhconv.convert(s, 'zh_cn')
 
+    @classmethod
+    def try_mkdir(cls, save_dir: str):
+        try:
+            mkdir_if_not_exists(save_dir)
+        except OSError as e:
+            if e.errno == 36:
+                # 目录名过长
+                limit = JmModuleConfig.VAR_FILE_NAME_LENGTH_LIMIT
+                jm_log('error', f'目录名过长，无法创建目录，强制缩短到{limit}个字符并重试')
+                save_dir = save_dir[0:limit]
+                mkdir_if_not_exists(save_dir)
+        return save_dir
+
 
 # 支持dsl: #{???} -> os.getenv(???)
 JmcomicText.dsl_replacer.add_dsl_and_replacer(r'\$\{(.*?)\}', JmcomicText.match_os_env)

{jmcomic-2.5.15 → jmcomic-2.5.17/src/jmcomic.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jmcomic
-Version: 2.5.15
+Version: 2.5.17
 Summary: Python API For JMComic (禁漫天堂)
 Home-page: https://github.com/hect0x7/JMComic-Crawler-Python
 Author: hect0x7