blandarebiter/ztb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 发布时间从详情页内容提取，避免pipeline二次请求失败

Browse Source
This commit is contained in:
ztb-system
2026-03-03 17:08:01 +08:00
parent bf9be95ae8
commit e8c901b273
4 changed files with 42 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
processors/pipeline.py
View File

@@ -149,10 +149,10 @@ class ProcessingPipeline:
# 基础字段映射：优先使用项目名称（已处理掉批准文号的名称）
record["名称"] = item.get("项目名称", item.get("标题", ""))
pub_date = item.get("发布日期", item.get("项目发布时间", ""))
record["发布时间"] = pub_date
# 项目发布时间修复：使用与发布时间相同的值，确保格式一致
record["项目发布时间"] = pub_date # 台州招标计划 JDY 使用此字段名
# 优先使用爬虫从详情页内容提取的发布时间（含时分秒）
pub_time = item.get("详情页发布时间", "")
record["发布时间"] = pub_time
record["项目发布时间"] = pub_time
record["地区"] = item.get("地区", "")
record["招标阶段"] = item.get("公告类型", notice_type)
record["来源"] = item.get("来源", "")