v1.0.12: crawl_results 合并 html_file/txt_file/meta_file 为单一 base_file(同前缀不同后缀), 含存量数据自动迁移

backfill.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+历史爬取记录回填数据库 (幂等, 可重复执行)
+
+用法:
+    python backfill.py                  # 回填所有任务的历史记录
+    python backfill.py <task_id> ...    # 只回填指定任务
+
+说明:
+    - 将本地 data/ 中的任务/运行/爬取结果(含成功与失败)全量写入 MySQL
+    - 网页内容不入库, 只写元数据; 重复执行不会产生重复记录
+"""
+import sys
+
+import db
+import store
+
+if __name__ == "__main__":
+    ids = [a for a in sys.argv[1:] if a.strip()] or None
+    db.init_db()
+    stats = db.sync_all_history(ids)
+    if ids:
+        print(f"[backfill] 已回填 {len(ids)} 个任务: {stats}")
+    else:
+        print(f"[backfill] 已回填全部任务: {stats}")

db.py

@@ -67,9 +67,7 @@ DDL = [
       source_url VARCHAR(2000),
       depth INT,
       attempts INT DEFAULT 1,
-      html_file VARCHAR(500),
+      base_file VARCHAR(500),
-      txt_file VARCHAR(500),
-      meta_file VARCHAR(500),
       image_count INT DEFAULT 0,
       image_files TEXT,
       UNIQUE KEY uk_run_url (run_id, url(500))
@@ -78,6 +76,17 @@ DDL = [
 ]
 
 
+def _migrate(conn):
+    """存量表结构迁移: 合并 html_file/txt_file/meta_file 为 base_file"""
+    with conn.cursor() as cur:
+        cur.execute("SHOW COLUMNS FROM crawl_results LIKE 'html_file'")
+        if cur.fetchone():
+            cur.execute("ALTER TABLE crawl_results ADD COLUMN base_file VARCHAR(500) NULL AFTER meta_file")
+            cur.execute("UPDATE crawl_results SET base_file = REPLACE(html_file, '.html', '') WHERE base_file IS NULL")
+            cur.execute("ALTER TABLE crawl_results DROP COLUMN html_file, DROP COLUMN txt_file, DROP COLUMN meta_file")
+            print("[db] 表结构迁移完成: html_file/txt_file/meta_file -> base_file")
+
+
 def _conn():
     cfg = dict(DB_CONFIG)
     cfg["database"] = DB_NAME
@@ -100,6 +109,7 @@ def init_db():
             cur.execute(f"CREATE DATABASE IF NOT EXISTS `{DB_NAME}` DEFAULT CHARACTER SET utf8mb4")
         conn.close()
         conn = _conn()
+        _migrate(conn)
         with conn.cursor() as cur:
             for ddl in DDL:
                 cur.execute(ddl)
@@ -219,8 +229,21 @@ def upsert_run(run):
 
 # ---------------- 爬取结果 (每页一条, 成功失败均记录) ----------------
 
+def _base_of(entry):
+    """从结果条目提取基础文件名 (html/txt/meta 三个后缀共用同一前缀)"""
+    for f in (entry.get("meta_file"), entry.get("html_file"), entry.get("txt_file")):
+        f = f or ""
+        if f.endswith(".meta.json"):
+            return f[:-10]
+        if f.endswith(".html"):
+            return f[:-5]
+        if f.endswith(".txt"):
+            return f[:-4]
+    return ""
+
+
 def insert_results(run, results):
-    """批量插入爬取结果 (增量)"""
+    """批量插入爬取结果 (增量); 文件只记基础名 base_file"""
     if not results:
         return
 
@@ -234,7 +257,7 @@ def insert_results(run, results):
                 r.get("status", "FAIL"), r.get("error"),
                 _dt(r.get("crawl_time")), (r.get("source_url") or "")[:2000],
                 r.get("depth"), r.get("attempts", 1),
-                r.get("html_file", ""), r.get("txt_file", ""), r.get("meta_file", ""),
+                _base_of(r),
                 len(r.get("images", []) or []),
                 _j([im.get("file") for im in (r.get("images") or [])]),
             ))
@@ -243,8 +266,8 @@ def insert_results(run, results):
                 """INSERT IGNORE INTO crawl_results
                    (run_id, task_id, mode, url, title, status, error,
                     crawl_time, source_url, depth, attempts,
-                    html_file, txt_file, meta_file, image_count, image_files)
+                    base_file, image_count, image_files)
-                   VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)""",
+                   VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)""",
                 rows,
             )
         conn.close()
@@ -262,3 +285,30 @@ def sync_run(run, persist):
         insert_results(run, results[synced:])
         run["_db_count"] = len(results)
         persist(run.get("task_id"), run)
+
+
+# ---------------- 历史数据回填 (幂等) ----------------
+
+def sync_all_history(task_ids=None):
+    """把本地 JSON 中的历史任务/运行/结果全量回填数据库
+    可重复执行 (INSERT IGNORE + 唯一键去重)
+    task_ids: 指定只回填的任务ID列表, 默认全部
+    返回统计 dict
+    """
+    import store as _store
+    stats = {"tasks": 0, "runs": 0, "results": 0}
+    for task in _store.load_tasks():
+        if task_ids and task["id"] not in task_ids:
+            continue
+        upsert_task(task)
+        stats["tasks"] += 1
+        for run in _store.get_runs(task["id"]):
+            upsert_run(run)
+            stats["runs"] += 1
+            results = run.get("results", [])
+            if results:
+                insert_results(run, results)
+                stats["results"] += len(results)
+                run["_db_count"] = len(results)
+                _store.save_run(task["id"], run)   # 记录已同步标记, 避免运行中重复插入
+    return stats