v1.9.0: 支持登录禁漫、优化正则表达式 (#20)

Author: hect0x7

.github/workflows/action_run_tests.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         python-version: [ 3.7, 3.8, 3.9, "3.10", "3.11" ]
-        os: [ ubuntu-latest, macos-latest ]
+        os: [ ubuntu-latest ]
     runs-on: ${{ matrix.os }}
     timeout-minutes: 5
 

.github/workflows/action_workflow_local.yml

@@ -36,6 +36,9 @@ jobs:
           pip install -e ./
 
       - name: 运行下载脚本
+        env:
+          JM_USERNAME: ${{ secrets.JM_USERNAME }}
+          JM_PASSWORD: ${{ secrets.JM_PASSWORD }}
         run: |
           cd ./usage/
           python jmcomic_workflows.py

assets/config/workflow_option.yml

@@ -20,6 +20,4 @@ client_config:
     - cffi
     - cffi_Session
   meta_data:
-    proxies: null
-    allow_redirects: true
     cookies: null

src/jmcomic/__init__.py

@@ -1,7 +1,7 @@
 # 模块依赖关系如下:
 # 被依赖方 <--- 使用方
-# config <--- entity <--- toolkit <--- client <--- service <--- option
+# config <--- entity <--- toolkit <--- client <--- option
 
-__version__ = '1.8.0'
+__version__ = '1.9.0'
 
 from .api import *

src/jmcomic/jm_client.py

@@ -192,6 +192,37 @@ def get_jmcomic_url(self, postman=None):
     def get_jmcomic_url_all(self, postman=None):
         return JmModuleConfig.get_jmcomic_url_all(postman or self)
 
+    def login(self,
+              username,
+              password,
+              refresh_client_cookies=True,
+              id_remember='on',
+              login_remember='on',
+              ):
+
+        data = {
+            'username': username,
+            'password': password,
+            'id_remember': id_remember,
+            'login_remember': login_remember,
+            'submit_login': '',
+        }
+
+        resp = self \
+            .get_root_postman() \
+            .post(self.of_api_url('/login'),
+                  data=data,
+                  allow_redirects=False,
+                  )
+
+        if resp.status_code != 301:
+            raise AssertionError(f'登录失败，状态码为{resp.status_code}')
+
+        if refresh_client_cookies is True:
+            self['cookies'] = resp.cookies
+
+        return resp
+
     @classmethod
     def require_resp_success_else_raise(cls, resp, url):
         # 1. 是否 album_missing
@@ -212,28 +243,3 @@ def check_special_html(cls, html: str, url=None):
             return
 
         raise AssertionError(f'{error_msg}' + f': {url}' if url is not None else '')
-
-
-# 爬取策略
-class FetchStrategy:
-
-    def __init__(self,
-                 from_index,
-                 photo_len,
-                 resp_getter,
-                 resp_consumer,
-                 ):
-        self.from_index = from_index
-        self.photo_len = photo_len
-        self.resp_getter = resp_getter
-        self.resp_consumer = resp_consumer
-
-    def do_fetch(self):
-        raise NotImplementedError
-
-    def args(self):
-        return (self.from_index,
-                self.photo_len,
-                self.resp_getter,
-                self.resp_consumer,
-                )

src/jmcomic/jm_config.py

@@ -38,7 +38,8 @@ def domain(cls, postman=None):
         这样一来，配置文件也不用配置域名了，一切都在运行时动态获取。
         """
         if cls._DOMAIN is None:
-            cls._DOMAIN = cls.get_jmcomic_url(postman).replace(cls.PROT, '')
+            from .jm_toolkit import JmcomicText
+            cls._DOMAIN = JmcomicText.parse_to_jm_domain(cls.get_jmcomic_url(postman))
 
         return cls._DOMAIN  # jmcomic默认域名
 
@@ -81,7 +82,8 @@ def get_jmcomic_url(cls, postman=None):
             from common import Postmans
             postman = Postmans.get_impl_clazz('cffi_Session').create()
 
-        url = postman.with_redirect_catching().get(cls.JM_REDIRECT_URL)
+        resp = postman.get(cls.JM_REDIRECT_URL)
+        url = resp.url
         cls.jm_debug('获取禁漫地址', f'[{cls.JM_REDIRECT_URL}] → [{url}]')
         return url
 

src/jmcomic/jm_entity.py

@@ -126,7 +126,10 @@ def is_single_album(self) -> bool:
         return self._series_id == 0
 
     @property
-    def keyword_list(self) -> List[str]:
+    def keywords(self) -> List[str]:
+        if self.from_album is not None:
+            return self.from_album.keywords
+
         return self._keywords.split(',')
 
     @property
@@ -204,6 +207,7 @@ def __init__(self,
                  episode_list,
                  page_count,
                  author_list,
+                 keywords_list,
                  pub_date,
                  update_date,
                  ):
@@ -212,6 +216,7 @@ def __init__(self,
         self.title: str = title
         self.page_count = int(page_count)
         self._author_list: List[str] = author_list
+        self._keywords_list: List[str] = keywords_list
         self.pub_date: str = pub_date  # 发布日期
         self.update_date: str = update_date  # 更新日期
 
@@ -254,6 +259,10 @@ def author(self):
             return self._author_list[0]
         return JmModuleConfig.default_author
 
+    @property
+    def keywords(self) -> List[str]:
+        return self._keywords_list
+
     def get_id(self):
         return self.album_id
 

src/jmcomic/jm_option.py

@@ -1,4 +1,4 @@
-from .jm_service import *
+from .jm_client import *
 
 
 class JmOptionAdvice:
@@ -431,58 +431,6 @@ def handle_postman():
 
         return client
 
-    """
-    下面的方法是对【CdnOption】的支持，已弃用
-    """
-
-    def build_cdn_option(self, use_multi_thread_strategy=True):
-
-        return CdnConfig.create(
-            cdn_domain=self.client_config.get('domain', JmModuleConfig.domain()),
-            fetch_strategy=MultiThreadFetch if use_multi_thread_strategy else InOrderFetch,
-            cdn_image_suffix=None,
-            use_cache=self.download_use_disk_cache,
-            decode_image=self.download_image_then_decode
-        )
-
-    def build_cdn_crawler(self, use_multi_thread_strategy=True):
-        return CdnFetchService(self.build_cdn_option(use_multi_thread_strategy),
-                               self.build_jm_client())
-
-    def build_cdn_request(self,
-                          photo_id: str,
-                          scramble_id=str(JmModuleConfig.SCRAMBLE_10),
-                          from_index=1,
-                          photo_len=None,
-                          use_default=False
-                          ) -> CdnRequest:
-        return CdnRequest.create(
-            photo_id,
-            self.build_save_path_provider(use_default, None if use_default else photo_id),
-            scramble_id,
-            from_index,
-            photo_len,
-        )
-
-    def build_save_path_provider(self,
-                                 use_all_default_save_path,
-                                 photo_id=None,
-                                 ) -> CdnRequest.SavePathProvider:
-
-        if use_all_default_save_path is True:
-            # 不通过请求获取 photo 的信息，相当于使用【空本子】和【空集】
-            photo_detail = None
-        else:
-            # 通过请求获得 photo 的本子信息
-            photo_detail = self.build_jm_client().get_photo_detail(photo_id)
-
-        def save_path_provider(url, _suffix: str, _index, _is_decode):
-            return '{0}{1}{2}'.format(self.decide_image_save_dir(photo_detail),
-                                      of_file_name(url, trim_suffix=True),
-                                      self.download_convert_image_suffix or _suffix)
-
-        return save_path_provider
-
 
 def _register_yaml_constructor():
     from yaml import add_constructor, Loader, Node