v2.1.11: 更新headers，修复对title过长的本子的解析 (#93)

Author: hect0x7

src/jmcomic/__init__.py

@@ -2,6 +2,6 @@
 # 被依赖方 <--- 使用方
 # config <--- entity <--- toolkit <--- client <--- option <--- downloader
 
-__version__ = '2.1.10'
+__version__ = '2.1.11'
 
 from .api import *

src/jmcomic/jm_config.py

@@ -96,9 +96,7 @@ def headers(cls, domain='18comic.vip'):
             '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',
             'referer': f'https://{domain}',
-            'pragma': 'no-cache',
             'sec-ch-ua': '"Not.A/Brand";v="8", "Chromium";v="114", "Google Chrome";v="114"',
             'sec-ch-ua-mobile': '?0',
             'sec-ch-ua-platform': '"Windows"',

src/jmcomic/jm_entity.py

@@ -4,7 +4,21 @@
 
 
 class JmBaseEntity:
-    pass
+
+    @staticmethod
+    def fix_title(title: str, limit=50):
+        """
+        一些过长的标题可能含有 \n，例如album: 360537
+        该方法会把 \n 去除
+        """
+        if len(title) > limit and '\n' in title:
+            title = title.replace('\n', '')
+
+        return title.strip()
+
+    def save_to_file(self, filepath):
+        from common import PackerUtil
+        PackerUtil.pack(self, filepath)
 
 
 class DetailEntity(JmBaseEntity, IterableEntity):
@@ -17,10 +31,6 @@ def id(self) -> str:
     def name(self) -> str:
         return getattr(self, 'title')
 
-    def save_to_file(self, filepath):
-        from common import PackerUtil
-        PackerUtil.pack(self, filepath)
-
     @classmethod
     def __jm_type__(cls):
         # "JmAlbumDetail" -> "album" (本子)
@@ -130,7 +140,7 @@ def __init__(self,
                  ):
         self.photo_id: str = photo_id
         self.scramble_id: str = scramble_id
-        self.title: str = str(title).strip()
+        self.title: str = self.fix_title(str(title))
         self.sort: int = int(sort)
         self._keywords: str = keywords
         self._series_id: int = int(series_id)

src/jmcomic/jm_toolkit.py

@@ -9,7 +9,7 @@ class JmcomicText:
 
     pattern_html_photo_photo_id = compile('<meta property="og:url" content=".*?/photo/(\d+)/?.*?">')
     pattern_html_photo_scramble_id = compile('var scramble_id = (\d+);')
-    pattern_html_photo_title = compile('<title>(.*?)\|.*</title>')
+    pattern_html_photo_title = compile('<title>([\s\S]*?)\|.*</title>')
     # pattern_html_photo_data_original_list = compile('data-original="(.*?)" id="album_photo_.+?"')
     pattern_html_photo_data_original_domain = compile('src="https://(.*?)/media/albums/blank')
     pattern_html_photo_data_original_0 = compile('data-original="(.*?)"[ \n]*?id="album_photo')
@@ -20,9 +20,9 @@ class JmcomicText:
 
     pattern_html_album_album_id = compile('<span class="number">.*?：JM(\d+)</span>')
     pattern_html_album_scramble_id = compile('var scramble_id = (\d+);')
-    pattern_html_album_title = compile('panel-heading[\s\S]*?<h1>(.*?)</h1>')
+    pattern_html_album_title = compile('<h1 class="book-name" id="book-name">([\s\S]*?)</h1>')
     pattern_html_album_episode_list = compile('data-album="(\d+)">\n *?<li.*?>\n *'
-                                              '第(\d+)話\n(.*)\n *'
+                                              '第(\d+)話\n([\s\S]*?)\n *'
                                               '<[\s\S]*?>(\d+-\d+-\d+).*?')
     pattern_html_album_page_count = compile('<span class="pagecount">.*?:(\d+)</span>')
     pattern_html_album_pub_date = compile('>上架日期 : (.*?)</span>')
@@ -135,7 +135,6 @@ def match_field(field_key: str, pattern: Union[Pattern, List[Pattern]], text):
 
         field_dict = {}
         pattern_name: str
-
         for pattern_name, pattern_value in cls.__dict__.items():
             if not pattern_name.startswith(cls_field_prefix):
                 continue