1. 同步MediaCrawler为最新版本

2. 修复数据库not null错误
3. 支持PG数据库
4. 规范环境变量及配置使用
5. 规范为uv安装
6. 使用loggru

MindSpider/DeepSentimentCrawling/MediaCrawler/main.py

@@ -15,7 +15,7 @@ from typing import Optional
 
 import cmd_arg
 import config
-import db
+from database import db
 from base.base_crawler import AbstractCrawler
 from media_platform.bilibili import BilibiliCrawler
 from media_platform.douyin import DouYinCrawler
@@ -24,6 +24,8 @@ from media_platform.tieba import TieBaCrawler
 from media_platform.weibo import WeiboCrawler
 from media_platform.xhs import XiaoHongShuCrawler
 from media_platform.zhihu import ZhihuCrawler
+from tools.async_file_writer import AsyncFileWriter
+from var import crawler_type_var
 
 
 class CrawlerFactory:
@@ -50,20 +52,40 @@ class CrawlerFactory:
 crawler: Optional[AbstractCrawler] = None
 
 
+# persist-1<persist1@126.com>
+# 原因：增加 --init_db 功能，用于数据库初始化。
+# 副作用：无
+# 回滚策略：还原此文件。
 async def main():
     # Init crawler
     global crawler
 
     # parse cmd
-    await cmd_arg.parse_cmd()
+    args = await cmd_arg.parse_cmd()
 
     # init db
-    if config.SAVE_DATA_OPTION in ["db", "sqlite"]:
-        await db.init_db()
+    if args.init_db:
+        await db.init_db(args.init_db)
+        print(f"Database {args.init_db} initialized successfully.")
+        return  # Exit the main function cleanly
+
+
 
     crawler = CrawlerFactory.create_crawler(platform=config.PLATFORM)
     await crawler.start()
 
+    # Generate wordcloud after crawling is complete
+    # Only for JSON save mode
+    if config.SAVE_DATA_OPTION == "json" and config.ENABLE_GET_WORDCLOUD:
+        try:
+            file_writer = AsyncFileWriter(
+                platform=config.PLATFORM,
+                crawler_type=crawler_type_var.get()
+            )
+            await file_writer.generate_wordcloud_from_comments()
+        except Exception as e:
+            print(f"Error generating wordcloud: {e}")
+
 
 def cleanup():
     if crawler: