fix: 发布时间从详情页内容提取，避免pipeline二次请求失败

2026-03-03 17:08:01 +08:00
parent bf9be95ae8
commit e8c901b273
4 changed files with 42 additions and 4 deletions
--- a/spiders/zhejiang.py
+++ b/spiders/zhejiang.py
@@ -159,6 +159,12 @@ class ZhejiangSpider(BaseSpider):
        detail = {}
        soup = BeautifulSoup(resp.text, "html.parser")

+        # 提取发布时间（从页面内容中获取，含时分秒）
+        page_text = soup.get_text(separator="\n", strip=True)
+        publish_time = self._extract_publish_time(soup, page_text)
+        if publish_time:
+            detail["详情页发布时间"] = publish_time
+
        # 解析表格字段
        field_map = {
            "项目名称": "项目名称",