优化企业开发区同步

This commit is contained in:
沈健
2025-06-20 13:26:11 +08:00
parent d0e6714ecd
commit 3975d029f8
+15 -11
View File
@@ -20,6 +20,9 @@ def sync(province):
)
shape_df = DIDATA_DEV_ELASTIC_CLIENT.scan_by_sql_to_data_frame(f"select name, shape from development_zone where province='{province}'")
if len(shape_df) == 0 or 'shape' not in shape_df.columns or len(shape_df[shape_df['shape'].notna()]) == 0:
logger.info(f"{province}无围栏数据")
return
actions = list()
count = 0
for index, item in shape_df[shape_df['shape'].notna()].iterrows():
@@ -40,17 +43,18 @@ def sync(province):
actions.append(action)
logger.info(f"已查找到该围栏下{com_count}个企业数据")
for success, info in helpers.parallel_bulk(
DIDATA_DEV_ELASTIC_CLIENT.elastic_client,
actions,
thread_count=5, # 并行线程数
chunk_size=1000 # 批量大小
):
if not success:
print(f"索引失败: {info}")
count += len(actions)
print("更新:" + str(count))
actions.clear()
if len(actions) > 0:
for success, info in helpers.parallel_bulk(
DIDATA_DEV_ELASTIC_CLIENT.elastic_client,
actions,
thread_count=5, # 并行线程数
chunk_size=1000 # 批量大小
):
if not success:
print(f"索引失败: {info}")
count += len(actions)
print("更新:" + str(count))
actions.clear()
if len(actions) > 0:
for success, info in helpers.parallel_bulk(
DIDATA_DEV_ELASTIC_CLIENT.elastic_client,