1.4.9-Fix

ReadMe.md

@@ -199,3 +199,4 @@ The following are the environment variable configurations supported in `config.y
 | `EXPORT_PDF` | `False` | Whether to enable PDF export functionality |
 
 
+

core/db.py

@@ -120,9 +120,8 @@ class Db:
             art.content=art.content
 
             if art.content_html is None:
-                from tools.html import htmltools
-                from driver.wxarticle import Web
-                art.content_html = Web.clean_article_content(art.content)
+                from tools.fix import fix_html
+                art.content_html = fix_html(art.content)
             from core.models.base import DATA_STATUS
             art.status=DATA_STATUS.ACTIVE
             session.add(art)

core/models/article.py

@@ -11,10 +11,10 @@ class ArticleBase(Base):
     url=Column(String(500))
     description=Column(Text)
     status = Column(Integer,default=1)
-    publish_time = Column(BigInteger,index=True)
+    publish_time = Column(Integer,index=True)
     created_at = Column(DateTime)
     updated_at = Column(BigInteger)  
-    updated_at_millis = Column(BigInteger)  
+    updated_at_millis = Column(BigInteger,index=True)  
     is_export = Column(Integer)
     is_read = Column(Integer, default=0)
 class Article(ArticleBase):

driver/wxarticle.py

@@ -62,13 +62,13 @@ class WXArticleFetcher:
                             dt = dt.replace(year=current_year - 1)
                     else:
                         dt = datetime.strptime(publish_time_str, fmt)
-                    return int(dt.timestamp() * 1000)
+                    return int(dt.timestamp())
                 except ValueError:
                     continue
             
             # 如果所有格式都失败，返回当前时间戳
             print_warning(f"无法解析时间格式: {publish_time_str}，使用当前时间")
-            return int(datetime.now().timestamp() * 1000)
+            return int(datetime.now().timestamp())
             
         except Exception as e:
             print_error(f"时间转换失败: {e}")

jobs/fetch_no_article.py

@@ -1,5 +1,6 @@
 from core.models.article import Article,DATA_STATUS
 import core.db as db
+from tools.fix import fix_html
 from core.wait import Wait
 from core.wx.base import WxGather
 from time import sleep
@@ -39,7 +40,7 @@ def fetch_articles_without_content():
             if content:
                 # 更新内容
                 article.content = content
-                article.content_html = Web.clean_article_content(content)
+                article.content_html =fix_html(content)
                 if  content=="DELETED":
                     print_error(f"获取文章 {article.title} 内容已被发布者删除")
                     article.status = DATA_STATUS.DELETED

main.py

@@ -40,7 +40,7 @@ if __name__ == '__main__':
         from jobs.cascade_task_dispatcher import cascade_schedule_service
         cascade_schedule_service.start()
 
-    if  cfg.args.job =="True" and cfg.get("server.enable_job",False) and  cascade_service_started:
+    if  cfg.args.job =="True" and cfg.get("server.enable_job",False):
         from jobs import start_all_task
         threading.Thread(target=start_all_task,daemon=False).start()
     else:

test_article.py

@@ -101,10 +101,8 @@ def test_Gather_Article():
         ]
     for url in urls:
         content= ga.content_extract(url)
-        print(content)
-        
-
-
+        content1 = Web.clean_article_content(content)
+        print(len(content),len(content1))
 def test_screenshot():
     from playwright.sync_api import sync_playwright,TimeoutError
     playwright=sync_playwright().start()
@@ -183,11 +181,11 @@ if __name__=="__main__":
     # asyncio.run(test_Article())
     # test_Gather_Article()
     # testWx_Api()
-    # test_fetch_articles_without_content()
+    test_fetch_articles_without_content()
     # testWeb()
     # testNotice()
     # testMd2Doc()
-    testLogin()
+    # testLogin()
     # test_feed_and_articles_template()
     # testJob()
     # test_send_wx_code()

tools/mdtools/md2html.py

@@ -8,6 +8,8 @@ from markdown.extensions import codehilite, tables, toc, fenced_code
 from bs4 import BeautifulSoup
 import re
 from typing import Dict, List, Optional, Any
+
+from pyee.cls import on
 from core.print import print_info, print_error, print_warning
 
 
@@ -43,6 +45,7 @@ class MarkdownToHtmlConverter:
         ]
         
         # 设置默认配置
+        self.only_body = self.config.get('only_body', True)
         self.extensions = self.config.get('extensions', self.default_extensions)
         self.remove_images = self.config.get('remove_images', False)
         self.remove_links = self.config.get('remove_links', False)
@@ -119,7 +122,7 @@ class MarkdownToHtmlConverter:
             
             html_content = md.convert(markdown_content)
             html_content = self._post_process_html(html_content)
-            html_content = self._wrap_html(html_content)
+            html_content = self._wrap_html(html_content,only_body=self.only_body)
             
             # 提取元数据
             metadata = {
@@ -246,7 +249,7 @@ class MarkdownToHtmlConverter:
             if not img.get('loading'):
                 img['loading'] = 'lazy'
     
-    def _wrap_html(self, html_content: str) -> str:
+    def _wrap_html(self, html_content: str,only_body:bool=True) -> str:
         """
         包装 HTML 内容，添加完整的 HTML 结构
         
@@ -256,6 +259,8 @@ class MarkdownToHtmlConverter:
         Returns:
             完整的 HTML 文档
         """
+        if only_body:
+            return html_content
         css_styles = self._get_default_css()
         if self.custom_css:
             css_styles += '\n' + self.custom_css