v2.4.2: 实现网页端正则匹配收藏夹列表，补充安装依赖项install_requires (#163) (#165)

Author: hect0x7

assets/docs/mkdocs.yml

@@ -5,7 +5,6 @@ theme:
 plugins:
   - search
   - mkdocstrings:
-      custom_templates: templates
       handlers:
         # See: https://mkdocstrings.github.io/python/usage/
         python:

setup.py

@@ -27,10 +27,11 @@
     package_dir={"": "src"},
     python_requires=">=3.7",
     install_requires=[
-        'commonX>=0.6.2',
+        'commonX>=0.6.3',
         'curl_cffi',
         'PyYAML',
         'Pillow',
+        'pycryptodome',
     ],
     keywords=['python', 'jmcomic', '18comic', '禁漫天堂', 'NSFW'],
     classifiers=[

src/jmcomic/__init__.py

@@ -2,7 +2,7 @@
 # 被依赖方 <--- 使用方
 # config <--- entity <--- toolkit <--- client <--- option <--- downloader
 
-__version__ = '2.4.1'
+__version__ = '2.4.2'
 
 from .api import *
 from .jm_plugin import *

src/jmcomic/api.py

@@ -19,7 +19,7 @@ def download_batch(download_api,
     from common import multi_thread_launcher
 
     if option is None:
-        option = JmOption.default()
+        option = JmModuleConfig.option_class().default()
 
     return multi_thread_launcher(
         iter_objs=set(

src/jmcomic/jm_client_impl.py

@@ -216,6 +216,7 @@ def get_photo_detail(self,
         # 一并获取该章节的所处本子
         # todo: 可优化，获取章节所在本子，其实不需要等待章节获取完毕后。
         #  可以直接调用 self.get_album_detail(photo_id)，会重定向返回本子的HTML
+        # (had polished by FutureClientProxy)
         if fetch_album is True:
             photo.from_album = self.get_album_detail(photo.album_id)
 
@@ -594,7 +595,7 @@ def fetch_photo_additional_field(self, photo: JmPhotoDetail, fetch_album: bool,
         2. album
         如果都需要获取，会排队，效率低
 
-        todo: 改进实现
+        todo: 改进实现 (had polished by FutureClientProxy)
         1. 直接开两个线程跑
         2. 开两个线程，但是开之前检查重复性
         3. 线程池，也要检查重复性
@@ -658,9 +659,6 @@ def setting(self) -> JmApiResp:
     def login(self,
               username,
               password,
-              refresh_client_cookies=True,
-              id_remember='on',
-              login_remember='on',
               ) -> JmApiResp:
         """
         {

src/jmcomic/jm_client_interface.py

@@ -192,9 +192,13 @@ def check_photo(self, photo: JmPhotoDetail):
 class JmUserClient:
 
     def login(self,
-              username,
-              password,
+              username: str,
+              password: str,
               ):
+        """
+        1. 返回response响应对象
+        2. 保证当前client拥有登录cookies
+        """
         raise NotImplementedError
 
     def album_comment(self,

src/jmcomic/jm_entity.py

@@ -457,7 +457,7 @@ def __init__(self, content: List[ContentItem], total: int):
           album_id, {title, tag_list, ...}
         ]
         :param content: 分页数据
-        :param total: 一共多少页
+        :param total: 总结果数
         """
         self.content = content
         self.total = total
@@ -513,7 +513,6 @@ class JmSearchPage(JmPageContent):
 
     @property
     def page_size(self) -> int:
-        from .jm_client_interface import JmMagicConstants
         return JmMagicConstants.PAGE_SIZE_SEARCH
 
     # 下面的方法是对单个album的包装
@@ -533,7 +532,7 @@ def wrap_single_album(cls, album: JmAlbumDetail) -> 'JmSearchPage':
                 'name': album.name,
                 'tag_list': album.tags,
             }
-        )], -1)
+        )], 1)
         setattr(page, 'album', album)
         return page
 
@@ -553,3 +552,11 @@ def __init__(self, content, folder_list, total):
     @property
     def page_size(self) -> int:
         return JmMagicConstants.PAGE_SIZE_FAVORITE
+
+    def folder_id_name_iter(self) -> Generator[Tuple[str, str], None, None]:
+        """
+        用户文件夹的迭代器
+        """
+        for folder_info in self.folder_list:
+            fid, fname = folder_info['FID'], folder_info['name']
+            yield fid, fname

src/jmcomic/jm_plugin.py

@@ -185,12 +185,10 @@ class FindUpdatePlugin(JmOptionPlugin):
     def invoke(self, **kwargs) -> None:
         self.download_album_with_find_update(kwargs or {})
 
-    def download_album_with_find_update(self, dic):
+    def download_album_with_find_update(self, dic: Dict[str, int]):
         from .api import download_album
         from .jm_downloader import JmDownloader
 
-        dic: Dict[str, int]
-
         # 带入漫画id, 章节id(第x章)，寻找该漫画下第x章节後的所有章节Id
         def find_update(album: JmAlbumDetail):
             if album.album_id not in dic:

src/jmcomic/jm_toolkit.py

@@ -120,7 +120,7 @@ def analyse_jm_search_html(cls, html: str) -> JmSearchPage:
     @classmethod
     def reflect_new_instance(cls, html: str, cls_field_prefix: str, clazz: type):
 
-        def match_field(field_key: str, pattern: Union[Pattern, List[Pattern]], text):
+        def match_field(field_name: str, pattern: Union[Pattern, List[Pattern]], text):
 
             if isinstance(pattern, list):
                 # 如果是 pattern 是 List[re.Pattern]，
@@ -136,7 +136,7 @@ def match_field(field_key: str, pattern: Union[Pattern, List[Pattern]], text):
 
                 return last_pattern.findall(text)
 
-            if field_key.endswith("_list"):
+            if field_name.endswith("_list"):
                 return pattern.findall(text)
             else:
                 match = pattern.search(text)
@@ -283,9 +283,15 @@ class JmPageTool:
         r'</div>'
     )
 
-    # 收藏页面的文件夹收藏总数
+    # 收藏夹的收藏总数
     pattern_html_favorite_total = compile(r' : (\d+)[^/]*/\D*(\d+)')
 
+    # 所有的收藏夹
+    pattern_html_favorite_folder_list = [
+        compile(r'<select class="user-select" name="movefolder-fid">([\s\S]*)</select>'),
+        compile(r'<option value="(\d+)">([^<]*?)</option>')
+    ]
+
     @classmethod
     def parse_html_to_search_page(cls, html: str) -> JmSearchPage:
         # 1. 检查是否失败
@@ -327,15 +333,18 @@ def parse_html_to_favorite_page(cls, html: str) -> JmFavoritePage:
             '未匹配到收藏夹的本子总数',
         ))
 
-        # 收藏页面的本子结果
+        # 收藏夹的本子结果
         content = cls.pattern_html_favorite_content.findall(html)
         content = [
             (aid, {'name': atitle})
             for aid, atitle in content
         ]
 
-        # 暂不实现匹配文件夹列表，感觉没什么意义..
-        folder_list = []
+        # 匹配收藏夹列表
+        p1, p2 = cls.pattern_html_favorite_folder_list
+        folder_list_text = PatternTool.require_match(html, p1, '未匹配到收藏夹列表')
+        folder_list_raw = p2.findall(folder_list_text)
+        folder_list = [{'name': fname, 'FID': fid} for fid, fname in folder_list_raw]
 
         return JmFavoritePage(content, folder_list, total)
 
@@ -397,8 +406,8 @@ def parse_api_to_favorite_page(cls, data: DictModel) -> JmFavoritePage:
               "FID": "123",
               "1": "456",
               "UID": "456",
-              "2": "文件夹名",
-              "name": "文件夹名"
+              "2": "收藏夹名",
+              "name": "收藏夹名"
             }
           ],
           "total": "87",
@@ -408,7 +417,7 @@ def parse_api_to_favorite_page(cls, data: DictModel) -> JmFavoritePage:
         total: int = int(data.total)
         # count: int = int(data.count)
         content = cls.adapt_content(data.list)
-        folder_list = data.folder_list
+        folder_list = data.get('folder_list', [])
 
         return JmFavoritePage(content, folder_list, total)