|
@@ -185,7 +185,7 @@ class DetailSpider(feapder.AirSpider):
|
|
|
insert = {k: v for k, v in item.items() if k not in ignore}
|
|
|
insert['comeintime'] = tools.ensure_int64(int(time.time()))
|
|
|
self.to_db.add("data_bak", insert)
|
|
|
- log.info(f"{msg}--采集成功")
|
|
|
+ log.info(f"{msg}--采集成功,状态:{state.value}")
|
|
|
|
|
|
def get_response(self, request, response):
|
|
|
"""
|
|
@@ -250,6 +250,9 @@ class DetailSpider(feapder.AirSpider):
|
|
|
# 情况2.1:结构化数据,直接提取数据
|
|
|
resp_json = response.json
|
|
|
else:
|
|
|
+ if business_keyword == 'openBidRecord':
|
|
|
+ return None, DataStreamReadStatus.LOSE
|
|
|
+
|
|
|
# 情况2.2:非结构化数据
|
|
|
if self._data_transmission_limit <= 3:
|
|
|
# 数据的内容越大(3M以上)首次解码耗时越长,且解码时会将无法识别的字符转换成替换字符
|