0.3:L1A finished.

ETL/L1A.py

@@ -0,0 +1,69 @@
+import os
+import json
+import sqlite3
+import glob
+
+# Paths
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+OUTPUT_ARENA_DIR = os.path.join(BASE_DIR, 'output_arena')
+DB_DIR = os.path.join(BASE_DIR, 'database', 'L1A')
+DB_PATH = os.path.join(DB_DIR, 'L1A.sqlite')
+
+def init_db():
+    if not os.path.exists(DB_DIR):
+        os.makedirs(DB_DIR)
+    
+    conn = sqlite3.connect(DB_PATH)
+    cursor = conn.cursor()
+    cursor.execute('''
+        CREATE TABLE IF NOT EXISTS raw_iframe_network (
+            match_id TEXT PRIMARY KEY,
+            content TEXT,
+            processed_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        )
+    ''')
+    conn.commit()
+    return conn
+
+def process_files():
+    conn = init_db()
+    cursor = conn.cursor()
+    
+    # Pattern to match all iframe_network.json files
+    # output_arena/*/iframe_network.json
+    pattern = os.path.join(OUTPUT_ARENA_DIR, '*', 'iframe_network.json')
+    files = glob.glob(pattern)
+    
+    print(f"Found {len(files)} files to process.")
+    
+    count = 0
+    for file_path in files:
+        try:
+            # Extract match_id from directory name
+            # file_path is like .../output_arena/g161-xxx/iframe_network.json
+            parent_dir = os.path.dirname(file_path)
+            match_id = os.path.basename(parent_dir)
+            
+            with open(file_path, 'r', encoding='utf-8') as f:
+                content = f.read()
+            
+            # Upsert data
+            cursor.execute('''
+                INSERT OR REPLACE INTO raw_iframe_network (match_id, content)
+                VALUES (?, ?)
+            ''', (match_id, content))
+            
+            count += 1
+            if count % 100 == 0:
+                print(f"Processed {count} files...")
+                conn.commit()
+                
+        except Exception as e:
+            print(f"Error processing {file_path}: {e}")
+            
+    conn.commit()
+    conn.close()
+    print(f"Finished processing {count} files.")
+
+if __name__ == '__main__':
+    process_files()

ETL/README.md

@@ -0,0 +1,3 @@
+L1A output_arena/iframe_network.json -> L1A.sqlite(Primary Key: match_id)
+L1B
+L2 L1A.sqlite -> L2.sqlite

database/L1A/README.md

@@ -1,4 +1,16 @@
 L1A 5eplay平台网页爬虫原始数据。
-ETL Step 1:
+
+## ETL Step 1:
 从原始json数据库提取到L1A级数据库中。
-output_arena/*/iframe_network.json -> database/L1A/L1A.sqlite
+`output_arena/*/iframe_network.json` -> `database/L1A/L1A.sqlite`
+
+### 脚本说明
+- **脚本位置**: `ETL/L1A.py`
+- **功能**: 自动遍历 `output_arena` 目录下所有的 `iframe_network.json` 文件，提取原始内容并以 `match_id` (文件夹名) 为主键存入 `L1A.sqlite` 数据库的 `raw_iframe_network` 表中。
+
+### 运行方式
+使用项目指定的 Python 环境运行脚本：
+
+```bash
+C:/ProgramData/anaconda3/python.exe ETL/L1A.py
+```