jmcomic 2.1.15__py3-none-any.whl → 2.1.17__py3-none-any.whl

jmcomic/__init__.py

@@ -2,6 +2,6 @@
 # 被依赖方 <--- 使用方
 # config <--- entity <--- toolkit <--- client <--- option <--- downloader
 
-__version__ = '2.1.15'
+__version__ = '2.1.17'
 
 from .api import *

jmcomic/jm_client_impl.py

@@ -143,7 +143,7 @@ class AbstractJmClient(
     def fallback(self, request, url, domain_index, retry_count, **kwargs):
         msg = f"请求重试全部失败: [{url}], {self.domain_list}"
         jm_debug('req.fallback', msg)
-        raise AssertionError(msg)
+        raise JmModuleConfig.exception(msg)
 
 
 # 基于网页实现的JmClient
@@ -216,7 +216,7 @@ class JmHtmlClient(AbstractJmClient):
                          )
 
         if resp.status_code != 301:
-            raise AssertionError(f'登录失败，状态码为{resp.status_code}')
+            raise JmModuleConfig.exception(f'登录失败，状态码为{resp.status_code}')
 
         if refresh_client_cookies is True:
             self['cookies'] = resp.cookies
@@ -251,7 +251,7 @@ class JmHtmlClient(AbstractJmClient):
                   + (f"响应文本=[{resp.text}]" if len(resp.text) < 200 else
                      f'响应文本过长(len={len(resp.text)})，不打印'
                      )
-        raise AssertionError(msg)
+        raise JmModuleConfig.exception(msg)
 
     def get_jm_image(self, img_url) -> JmImageResp:
 
@@ -418,6 +418,9 @@ class JmApiClient(AbstractJmClient):
             "accept-encoding": "gzip",
         }, key_ts
 
+    def debug_topic_request(self):
+        return 'api'
+
 
 class AsyncSaveImageClient(JmImageClient):
 

jmcomic/jm_client_interface.py

@@ -23,13 +23,13 @@ class JmResp(CommonResp):
 class JmImageResp(JmResp):
 
     def json(self, **kwargs) -> Dict:
-        raise AssertionError
+        raise NotImplementedError
 
     def require_success(self):
         if self.is_success:
             return
 
-        raise AssertionError(self.get_error_msg())
+        raise JmModuleConfig.exception(self.get_error_msg())
 
     def get_error_msg(self):
         msg = f'禁漫图片获取失败: [{self.url}]'
@@ -68,7 +68,7 @@ class JmApiResp(JmResp):
     @classmethod
     def wrap(cls, resp, key_ts):
         if isinstance(resp, JmApiResp):
-            raise AssertionError('重复包装')
+            raise JmModuleConfig.exception('重复包装')
 
         return cls(resp, key_ts)
 

jmcomic/jm_config.py

@@ -17,11 +17,19 @@ def default_postman_constructor(session, **kwargs):
     return Postmans.new_postman(**kwargs)
 
 
+def default_raise_regex_error(msg, *_args, **_kwargs):
+    raise JmModuleConfig.exception(msg)
+
+
+class JmcomicException(Exception):
+    pass
+
+
 class JmModuleConfig:
     # 网站相关
     PROT = "https://"
     JM_REDIRECT_URL = f'{PROT}jm365.work/3YeBdF'  # 永久網域，怕走失的小伙伴收藏起来
-    JM_PUB_URL = f'{PROT}jmcomic2.bet'
+    JM_PUB_URL = f'{PROT}jmcomic.ltd'
     JM_CDN_IMAGE_URL_TEMPLATE = PROT + 'cdn-msp.{domain}/media/photos/{photo_id}/{index:05}{suffix}'  # index 从1开始
     JM_IMAGE_SUFFIX = ['.jpg', '.webp', '.png', '.gif']
 
@@ -56,12 +64,17 @@ class JmModuleConfig:
     CLASS_OPTION = None
     CLASS_ALBUM = None
     CLASS_PHOTO = None
+    CLASS_IMAGE = None
     CLASS_CLIENT_IMPL = {}
+    CLASS_EXCEPTION = None
 
     # 执行debug的函数
     debug_executor = default_jm_debug
     # postman构造函数
     postman_constructor = default_postman_constructor
+    # 网页正则表达式解析失败时，执行抛出异常的函数，可以替换掉用于debug
+    raise_regex_error_executor = default_raise_regex_error
+
     # debug开关标记
     enable_jm_debug = True
 
@@ -97,6 +110,14 @@ class JmModuleConfig:
         from .jm_entity import JmPhotoDetail
         return JmPhotoDetail
 
+    @classmethod
+    def image_class(cls):
+        if cls.CLASS_IMAGE is not None:
+            return cls.CLASS_IMAGE
+
+        from .jm_entity import JmImageDetail
+        return JmImageDetail
+
     @classmethod
     def client_impl_class(cls, client_key: str):
         client_impl_dict = cls.CLASS_CLIENT_IMPL
@@ -107,6 +128,13 @@ class JmModuleConfig:
 
         return impl_class
 
+    @classmethod
+    def exception(cls, msg: str):
+        if cls.CLASS_EXCEPTION is not None:
+            return cls.CLASS_EXCEPTION(msg)
+
+        return JmcomicException(msg)
+
     @classmethod
     @field_cache("DOMAIN")
     def domain(cls, postman=None):
@@ -163,7 +191,7 @@ class JmModuleConfig:
         postman = postman or cls.new_postman(session=True)
 
         url = postman.with_redirect_catching().get(cls.JM_REDIRECT_URL)
-        cls.jm_debug('获取禁漫地址', f'[{cls.JM_REDIRECT_URL}] → [{url}]')
+        cls.jm_debug('获取禁漫URL', f'[{cls.JM_REDIRECT_URL}] → [{url}]')
         return url
 
     @classmethod
@@ -178,10 +206,13 @@ class JmModuleConfig:
 
         resp = postman.get(cls.JM_PUB_URL)
         if resp.status_code != 200:
-            raise AssertionError(resp.text)
+            raise JmModuleConfig.exception(resp.text)
 
         from .jm_toolkit import JmcomicText
-        return JmcomicText.analyse_jm_pub_html(resp.text)
+        domain_list = JmcomicText.analyse_jm_pub_html(resp.text)
+
+        cls.jm_debug('获取禁漫全部域名', f'[{resp.url}] → {domain_list}')
+        return domain_list
 
     album_comment_headers = {
         'authority': '18comic.vip',

jmcomic/jm_entity.py

@@ -241,11 +241,11 @@ class JmPhotoDetail(DetailEntity):
         # 校验参数
         length = len(self.page_arr)
         if index >= length:
-            raise AssertionError(f'创建JmImageDetail失败，{index} >= {length}')
+            raise JmModuleConfig.exception(f'创建JmImageDetail失败，{index} >= {length}')
 
         data_original = self.get_img_data_original(self.page_arr[index])
 
-        return JmImageDetail.of(
+        return JmModuleConfig.image_class().of(
             self.photo_id,
             self.scramble_id,
             data_original,
@@ -262,7 +262,7 @@ class JmPhotoDetail(DetailEntity):
         """
         data_original_domain = self.data_original_domain
         if data_original_domain is None:
-            raise AssertionError(f'图片域名为空: {self.__dict__}')
+            raise JmModuleConfig.exception(f'图片域名为空: {self.__dict__}')
 
         return f'https://{data_original_domain}/media/photos/{self.photo_id}/{img_name}'
 
@@ -330,13 +330,13 @@ class JmAlbumDetail(DetailEntity):
         length = len(self.episode_list)
 
         if index >= length:
-            raise AssertionError(f'创建JmPhotoDetail失败，{index} >= {length}')
+            raise JmModuleConfig.exception(f'创建JmPhotoDetail失败，{index} >= {length}')
 
         # episode_info: ('212214', '81', '94 突然打來', '2020-08-29')
         episode_info: tuple = self.episode_list[index]
         photo_id, photo_index, photo_title, photo_pub_date = episode_info
 
-        photo = JmPhotoDetail(
+        photo = JmModuleConfig.photo_class()(
             photo_id=photo_id,
             scramble_id=self.scramble_id,
             title=photo_title,

jmcomic/jm_option.py

@@ -10,7 +10,8 @@ class DirRule:
         # 根目录 / Photo-序号&标题 /
         'Bd_Pindextitle',
         # 根目录 / Photo-自定义类属性 /
-        'Bd_Aauthor_Atitle_Pcustomfield',  # 使用自定义类属性前，需替换 JmcomicText的 PhotoClass / AlbumClass
+        'Bd_Aauthor_Atitle_Pcustomfield',
+        # 需要替换JmModuleConfig.CLASS_ALBUM / CLASS_PHOTO才能让自定义属性生效
     ]
 
     RuleFunc = Callable[[Union[JmAlbumDetail, JmPhotoDetail, None]], str]
@@ -45,8 +46,10 @@ class DirRule:
                 path_ls.append(str(ret))
             except BaseException as e:
                 # noinspection PyUnboundLocalVariable
-                raise AssertionError(f'路径规则"{self.rule_dsl}"的第{i + 1}个解析出错: {e},'
-                                     f'param is {param}')
+                raise JmModuleConfig.exception(
+                    f'路径规则"{self.rule_dsl}"的第{i + 1}个解析出错: {e},'
+                    f'param is {param}'
+                )
 
         return fix_filepath('/'.join(path_ls), is_dir=True)
 
@@ -214,7 +217,7 @@ class JmOption:
             filepath = self.filepath
 
         if filepath is None:
-            raise AssertionError("未指定JmOption的保存路径")
+            raise JmModuleConfig.exception("未指定JmOption的保存路径")
 
         PackerUtil.pack(self.deconstruct(), filepath)
 

jmcomic/jm_toolkit.py

@@ -52,7 +52,7 @@ class JmcomicText:
             return str(text)
 
         if not isinstance(text, str):
-            raise AssertionError(f"无法解析jm车号, 参数类型为: {type(text)}")
+            raise JmModuleConfig.exception(f"无法解析jm车号, 参数类型为: {type(text)}")
 
         # 43210
         if text.isdigit():
@@ -60,7 +60,7 @@ class JmcomicText:
 
         # Jm43210
         if len(text) <= 2:
-            raise AssertionError(f"无法解析jm车号, 文本为: {text}")
+            raise JmModuleConfig.exception(f"无法解析jm车号, 文本为: {text}")
 
         # text: JM12341
         c0 = text[0]
@@ -72,7 +72,7 @@ class JmcomicText:
             # https://xxx/photo/412038
             match = cls.pattern_jm_pa_id.search(text)
             if match is None:
-                raise AssertionError(f"无法解析jm车号, 文本为: {text}")
+                raise JmModuleConfig.exception(f"无法解析jm车号, 文本为: {text}")
             return match[2]
 
     @classmethod
@@ -141,8 +141,12 @@ class JmcomicText:
             field_value = match_field(field_name, pattern_value, html)
 
             if field_value is None:
-                write_text('./resp.txt', html)  # debug
-                raise AssertionError(f"文本没有匹配上字段：字段名为'{field_name}'，pattern: [{pattern_value.pattern}]")
+                JmModuleConfig.raise_regex_error_executor(
+                    f"文本没有匹配上字段：字段名为'{field_name}'，pattern: [{pattern_value.pattern}]",
+                    html,
+                    field_name,
+                    pattern_value
+                )
 
             # 保存字段
             field_dict[field_name] = field_value
@@ -167,9 +171,7 @@ class JmcomicText:
 
 class JmSearchSupport:
     # 用来缩减html的长度
-    pattern_html_search_shorten_for = compile('<div class="well well-sm">([\s\S]*)'
-                                              '<div class="row">[\s\S]*'
-                                              '<div class="bot-per visible-xs visible-sm">')
+    pattern_html_search_shorten_for = compile('<div class="well well-sm">([\s\S]*)<div class="row">')
 
     # 用来提取搜索页面的的album的信息
     pattern_html_search_album_info_list = compile(
@@ -185,9 +187,24 @@ class JmSearchSupport:
     # 用来查找tag列表
     pattern_html_search_tag_list = compile('<a href=".*?">(.*?)</a>')
 
+    # 查找错误，例如 [错误，關鍵字過短，請至少輸入兩個字以上。]
+    pattern_html_search_error = compile('<fieldset>\n<legend>(.*?)</legend>\n<div class=.*?>\n(.*?)\n</div>\n</fieldset>')
+
     @classmethod
     def analyse_jm_search_html(cls, html: str) -> JmSearchPage:
-        html = cls.pattern_html_search_shorten_for.search(html)[0]
+        # 检查是否失败
+        match = cls.pattern_html_search_error.search(html)
+        if match is not None:
+            topic, reason = match[1], match[2]
+            JmModuleConfig.raise_regex_error_executor(f'{topic}: {reason}', html)
+
+        # 缩小文本范围
+        match = cls.pattern_html_search_shorten_for.search(html)
+        if match is None:
+            JmModuleConfig.raise_regex_error_executor('未匹配到搜索结果', html)
+        html = match[0]
+
+        # 提取结果
         album_info_list = cls.pattern_html_search_album_info_list.findall(html)
 
         for i, (album_id, title, *args) in enumerate(album_info_list):

{jmcomic-2.1.15.dist-info → jmcomic-2.1.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: jmcomic
-Version: 2.1.15
+Version: 2.1.17
 Summary: Python API For JMComic (禁漫天堂)
 Home-page: https://github.com/hect0x7/JMComic-Crawler-Python
 Author: hect0x7

jmcomic-2.1.17.dist-info/RECORD

@@ -0,0 +1,14 @@
+jmcomic/__init__.py,sha256=P841NJsb9rk_BcH56LkydBcqTWqLJ_2U5Ruo5tCqd2s,176
+jmcomic/api.py,sha256=s1LTgpKQh5hMnl3Im6qD5nvrnusf6NHawzvJKbZxwCo,1864
+jmcomic/jm_client_impl.py,sha256=CxuJEQnF9b_kfAkHVJZByn6JdxOP-noiflm67sjwCtw,14101
+jmcomic/jm_client_interface.py,sha256=OhS-pC2FXQT4vuu2WejypEGns2fbL0yD8ZEItAvSLE8,8073
+jmcomic/jm_config.py,sha256=g2BXvXpYIEHewaMmh4WeHc8jz3kCJFOijls2bfpgdrA,8086
+jmcomic/jm_downloader.py,sha256=NrDp8q7l1-FChAsEUOnWp9Vcx-C3xn5R2Cq6kG4s2nc,5910
+jmcomic/jm_entity.py,sha256=VEw4vCpsmzCJqlOuzLz7O9aeHIuGpwCLX10yzoX4ZIc,12908
+jmcomic/jm_option.py,sha256=X5fOCFpk4h7wQi5pPBJUzhsEMOKgsIRiZH4cNb7gCR8,9494
+jmcomic/jm_toolkit.py,sha256=p0Z6WNAwil-F9S3BRYRnPA-b8uR9a6TA9yhMWATv2KY,12053
+jmcomic-2.1.17.dist-info/LICENSE,sha256=kz4coTxZxuGxisK3W00tjK57Zh3RcMGq-EnbXrK7-xA,1064
+jmcomic-2.1.17.dist-info/METADATA,sha256=y2hfchFCFgIU2DzvNYd_sWUwRLgUikGbKfSkDSrX5rc,3922
+jmcomic-2.1.17.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+jmcomic-2.1.17.dist-info/top_level.txt,sha256=puvVMFYJqIbd6NOTMEvOyugMTT8woBfSQyxEBan3zY4,8
+jmcomic-2.1.17.dist-info/RECORD,,

jmcomic-2.1.15.dist-info/RECORD

@@ -1,14 +0,0 @@
-jmcomic/__init__.py,sha256=GlziFJIG_aXTQ9qAJ-TZ4pwGmNafxiuBJi4BenPQv64,176
-jmcomic/api.py,sha256=s1LTgpKQh5hMnl3Im6qD5nvrnusf6NHawzvJKbZxwCo,1864
-jmcomic/jm_client_impl.py,sha256=Xaaeh14FtbHIutjh6m2jJT_k7lThCefs4CfQ-YOukzg,14014
-jmcomic/jm_client_interface.py,sha256=5cbxTVxkEsTU7O11FN2J34P67_eRbfiFqSKl8wZLim8,8048
-jmcomic/jm_config.py,sha256=p1PU-5SgVvssxCqIqIaN2A3mcMQDk2-bhoCQ5Cj_Ung,7234
-jmcomic/jm_downloader.py,sha256=NrDp8q7l1-FChAsEUOnWp9Vcx-C3xn5R2Cq6kG4s2nc,5910
-jmcomic/jm_entity.py,sha256=Xh7Yl-jOro2oUtkrAcbb6S00MCttveZXhn4ZUs-nDKU,12848
-jmcomic/jm_option.py,sha256=1U3_Yubl7uRF31e6HAKXpzg2apCUS2tk2Wm3w7s2pHM,9442
-jmcomic/jm_toolkit.py,sha256=5B040C6_dDhaBy5VFqW7sdLokYVfxHiu3hNSDYD7vSw,11423
-jmcomic-2.1.15.dist-info/LICENSE,sha256=kz4coTxZxuGxisK3W00tjK57Zh3RcMGq-EnbXrK7-xA,1064
-jmcomic-2.1.15.dist-info/METADATA,sha256=Yqg2VUC7zx4t7XvRfBSkyZlz3O8YQnPC9H8Ryv0jR88,3922
-jmcomic-2.1.15.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-jmcomic-2.1.15.dist-info/top_level.txt,sha256=puvVMFYJqIbd6NOTMEvOyugMTT8woBfSQyxEBan3zY4,8
-jmcomic-2.1.15.dist-info/RECORD,,