Move policy-analysis reports to output/ subdirectory

skills/jd-fapai-scrape/scrape.py

@@ -448,7 +448,8 @@ def print_stats(listings, new_items=None, updated_items=None, early_stopped=Fals
 
 
 def scrape(keyword="塘厦", cate_id="15", sort_field="11",
-           max_scrolls=100, output_dir=".", incremental=False):
+           max_scrolls=100, output_dir="output/法拍",
+           incremental=False, csv_only=False):
     os.makedirs(output_dir, exist_ok=True)
 
     now_str = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
@@ -463,10 +464,12 @@ def scrape(keyword="塘厦", cate_id="15", sort_field="11",
     if incremental:
         existing, known_ids = load_existing(json_path)
         if not known_ids:
-            print("未找到已有数据，转为首次抓取模式")
+            print("未找到已有 JSON 数据，转为首次抓取模式")
             incremental = False
         else:
             print(f"已有数据: {len(existing)} 条, 已知 {len(known_ids)} 个 paimaiId")
+            if csv_only:
+                print("提示: csv_only 模式下增量更新仍需 JSON 做合并，临时使用后删除")
 
     new_listings, early_stopped = fetch_listings(
         keyword, cate_id, sort_field, max_scrolls,
@@ -482,9 +485,12 @@ def scrape(keyword="塘厦", cate_id="15", sort_field="11",
         print(f"合并后总数: {len(merged)} 条")
         print(f"新增: {len(new_items)} 条 | 更新: {len(updated_items)} 条")
 
-        with open(json_path, "w", encoding="utf-8") as f:
-            json.dump(merged, f, indent=2, ensure_ascii=False)
+        if not csv_only:
+            with open(json_path, "w", encoding="utf-8") as f:
+                json.dump(merged, f, indent=2, ensure_ascii=False)
         save_csv(merged, csv_path)
+        if csv_only and os.path.exists(json_path):
+            os.remove(json_path)
 
         log_path = os.path.join(output_dir, f"{keyword}_增量日志.log")
         with open(log_path, "a", encoding="utf-8") as f:
@@ -505,7 +511,8 @@ def scrape(keyword="塘厦", cate_id="15", sort_field="11",
                         f"{ts_to_str(item.get('_startTime'))}\n")
 
         print(f"\n输出文件:")
-        print(f"  JSON: {json_path}")
+        if not csv_only:
+            print(f"  JSON: {json_path}")
         print(f"  CSV:  {csv_path}")
         print(f"  日志: {log_path}")
 
@@ -517,12 +524,14 @@ def scrape(keyword="塘厦", cate_id="15", sort_field="11",
             item["_first_seen"] = now_str
             item["_last_seen"] = now_str
 
-        with open(json_path, "w", encoding="utf-8") as f:
-            json.dump(sorted_listings, f, indent=2, ensure_ascii=False)
+        if not csv_only:
+            with open(json_path, "w", encoding="utf-8") as f:
+                json.dump(sorted_listings, f, indent=2, ensure_ascii=False)
         save_csv(sorted_listings, csv_path)
 
         print(f"\n输出文件:")
-        print(f"  JSON: {json_path}")
+        if not csv_only:
+            print(f"  JSON: {json_path}")
         print(f"  CSV:  {csv_path}")
 
         print_stats(sorted_listings)
@@ -535,9 +544,11 @@ if __name__ == "__main__":
     parser.add_argument("--cate-id", default="15", help="类目ID (默认: 15=法拍房)")
     parser.add_argument("--sort-field", default="11", help="排序 (默认: 11=最新发布)")
     parser.add_argument("--max-scrolls", type=int, default=100, help="最大滚动次数")
-    parser.add_argument("--output-dir", default=".", help="输出目录")
+    parser.add_argument("--output-dir", default="output/法拍", help="输出目录 (默认: output/法拍)")
     parser.add_argument("--incremental", "-i", action="store_true",
                         help="增量更新：只下载新房源，遇到已知项即停止")
+    parser.add_argument("--csv-only", action="store_true",
+                        help="只输出 CSV，不保存 JSON（增量模式下 JSON 临时使用后删除）")
 
     args = parser.parse_args()
 
@@ -548,4 +559,5 @@ if __name__ == "__main__":
         max_scrolls=args.max_scrolls,
         output_dir=args.output_dir,
         incremental=args.incremental,
+        csv_only=args.csv_only,
     )