'commit'

dsLightRag/.idea/dsLightRag.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="Python 3.10 (4)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="D:\anaconda3\envs\py310" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyDocumentationSettings">

dsLightRag/.idea/misc.xml

@@ -3,5 +3,5 @@
   <component name="Black">
     <option name="sdkName" value="D:\anaconda3\envs\lightrag" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (4)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="D:\anaconda3\envs\py310" project-jdk-type="Python SDK" />
 </project>

dsLightRag/WxGzh/T2_CollectArticle.py

@@ -4,21 +4,34 @@
 # 微信爬爬猫---公众号文章抓取代码分析
 # https://blog.csdn.net/yajuanpi4899/article/details/121584268
 
+"""
+# 查看selenium版本
+pip show selenium
+4.34.2
 
+# 查看Chrome浏览器版本
+chrome://version/
+138.0.7204.101 (正式版本) （64 位）
+
+# 下载驱动包
+https://googlechromelabs.github.io/chrome-for-testing/
+https://storage.googleapis.com/chrome-for-testing-public/138.0.7204.94/win64/chromedriver-win64.zip
+"""
 import asyncio
 import datetime
 import json
 import logging
 import random
 import re
-
+import time
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.chrome.service import Service as ChromeService
 import requests
-
 from Util.PostgreSQLUtil import init_postgres_pool
 from Util.WxGzhUtil import init_wechat_browser, get_article_content
 
 # 删除重复的日志配置，只保留以下内容
-logger = logging.getLogger('WeiXinGongZhongHao')
+logger = logging.getLogger('WxGzh')
 logger.setLevel(logging.INFO)
 
 # 确保只添加一个handler
@@ -27,7 +40,6 @@ if not logger.handlers:
     handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s'))
     logger.addHandler(handler)
 
-
 async def get_wechat_sources():
     """从t_wechat_source表获取微信公众号列表"""
     try:
@@ -39,32 +51,13 @@ async def get_wechat_sources():
         await pool.close()
 
 
-"""
-# 查看selenium版本
-pip show selenium
-4.34.2
-
-# 查看Chrome浏览器版本
-chrome://version/
-138.0.7204.101 (正式版本) （64 位）
-
-# 下载驱动包
-https://googlechromelabs.github.io/chrome-for-testing/
-https://storage.googleapis.com/chrome-for-testing-public/138.0.7204.94/win64/chromedriver-win64.zip
-"""
-import time
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.chrome.service import Service as ChromeService
-
 
 async def is_article_exist(pool, article_url):
     """检查文章URL是否已存在数据库中"""
     try:
         async with pool.acquire() as conn:
             row = await conn.fetchrow('''
-                                      SELECT 1
+                                      SELECT 1 FROM t_wechat_articles WHERE url = $1 LIMIT 1
-                                      FROM t_wechat_articles
-                                      WHERE url = $1 LIMIT 1
                                       ''', article_url)
             return row is not None
     except Exception as e: