re-common 10.0.35__tar.gz → 10.0.36__tar.gz

{re_common-10.0.35/re_common.egg-info → re_common-10.0.36}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: re_common
-Version: 10.0.35
+Version: 10.0.36
 Summary: a library about all python projects
 Home-page: https://gitee.com/xujiangios/re-common
 Author: vic

{re_common-10.0.35 → re_common-10.0.36}/re_common/v2/baselibrary/utils/db.py

@@ -1,4 +1,6 @@
 import os
+import time
+
 import aiomysql
 import asyncio
 from contextlib import asynccontextmanager
@@ -92,6 +94,7 @@ aiomysql_pool = None
 pool_lock = asyncio.Lock()  # 全局异步锁
 
 
+
 async def init_aiomysql_pool_async():
     global aiomysql_pool
     if aiomysql_pool is None:
@@ -100,3 +103,54 @@ async def init_aiomysql_pool_async():
                 print(f"[{os.getpid()}] Initializing aiomysql pool...")
                 aiomysql_pool = await aiomysql.create_pool(**DB_CONFIG)
     return aiomysql_pool
+
+
+motor_fs = None
+client = None
+motor_fs_lock = asyncio.Lock()  # 全局异步锁
+_loop_id_mongo = None
+
+async def check_connection(client):
+    try:
+        print("check mongodb client ping")
+        await client.admin.command("ping")
+        return True
+    except Exception:
+        return False
+
+
+async def init_motor_async(uri, db_name, bucket_name, is_reload=False):
+    global motor_fs, client, _loop_id_mongo
+    is_ping = True
+
+    if _loop_id_mongo is not None:
+        loop_id = id(asyncio.get_running_loop())
+        if loop_id != _loop_id_mongo:
+            is_reload = True
+
+    # 防止 每次都检查 只有 is_reload 时才检查连接
+    if is_reload:
+        is_ping = await check_connection(client)
+    if motor_fs is None or not is_ping:
+        async with motor_fs_lock:
+            if motor_fs is None or not is_ping:
+                print(f"[{os.getpid()}] Initializing motor_fs...")
+                from motor.motor_asyncio import AsyncIOMotorClient, AsyncIOMotorGridFSBucket
+                client = AsyncIOMotorClient(uri)
+                db = client[db_name]
+                motor_fs = AsyncIOMotorGridFSBucket(database=db, bucket_name=bucket_name)
+                _loop_id_mongo = id(asyncio.get_running_loop())
+    return motor_fs, client
+
+# async def run_main():
+#     while True:
+#         uri = "mongodb://192.168.98.80:27001/wpdc"
+#         db_name = "wpdc"
+#         bucket_name = "sci_doc"
+#         motor_fs, client = await init_motor_async(uri, db_name, bucket_name,is_reload=True)
+#         # print(await check_connection(client))
+#         time.sleep(3)
+#
+#
+# if __name__ == "__main__":
+#     asyncio.run(run_main())

{re_common-10.0.35 → re_common-10.0.36}/re_common/v2/baselibrary/utils/stringutils.py

@@ -181,7 +181,7 @@ class HTMLTextExtractor(HTMLParser):
 
 def clean_html(html):
     """使用 Parsel 提取 HTML 中的纯文本"""
-    sel = Selector(text=html)
+    sel = Selector(text=html, type='html')
     # 提取所有文本（包括子元素的文本）
     text = sel.xpath("string()").getall()
     return "".join(text).strip()

{re_common-10.0.35 → re_common-10.0.36/re_common.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: re_common
-Version: 10.0.35
+Version: 10.0.36
 Summary: a library about all python projects
 Home-page: https://gitee.com/xujiangios/re-common
 Author: vic

{re_common-10.0.35 → re_common-10.0.36}/setup.py

@@ -34,7 +34,7 @@ long_description = """
 """
 setuptools.setup(
     name="re_common",
-    version="10.0.35",
+    version="10.0.36",
     author="vic",
     author_email="xujiang5@163.com",
     description="a library about all python projects",