fix

.github/organize_files.py

@@ -0,0 +1,76 @@
+import os
+import re
+import yaml
+import shutil
+from urllib.parse import urlparse
+
+def load_config():
+    with open('.github/url_dir_map_config.yml', 'r', encoding='utf-8') as f:
+        return yaml.safe_load(f)
+
+def extract_original_url(content):
+    match = re.search(r'<!--\s*tcd_original_link\s+(.*?)\s*-->', content)
+    return match.group(1) if match else None
+
+def get_target_dir(url, config):
+    if not url:
+        return "未分类"
+
+    domain = urlparse(url).netloc
+    for mapping in config['url_mappings']:
+        if mapping['domain'] in domain:
+            return mapping['dir']
+    return "未分类"
+
+def get_unique_filename(target_path, filename):
+    base, ext = os.path.splitext(filename)
+    counter = 1
+    new_path = os.path.join(target_path, filename)
+
+    while os.path.exists(new_path):
+        new_filename = f"{base}_{counter}{ext}"
+        new_path = os.path.join(target_path, new_filename)
+        counter += 1
+
+    return new_path
+
+def main():
+    config = load_config()
+    workspace_dir = 'workspace'
+
+    # Create target directories if they don't exist
+    for mapping in config['url_mappings']:
+        dir_path = os.path.join(workspace_dir, mapping['dir'])
+        os.makedirs(dir_path, exist_ok=True)
+
+    # Process markdown files
+    for root, _, files in os.walk(workspace_dir):
+        for file in files:
+            if not file.endswith('.md'):
+                continue
+
+            file_path = os.path.join(root, file)
+
+            # Skip files that are already in target directories
+            if any(mapping['dir'] in file_path for mapping in config['url_mappings']):
+                continue
+
+            with open(file_path, 'r', encoding='utf-8') as f:
+                content = f.read()
+
+            url = extract_original_url(content)
+            target_dir = get_target_dir(url, config)
+            target_dir_path = os.path.join(workspace_dir, target_dir)
+
+            # Create target directory if it doesn't exist
+            os.makedirs(target_dir_path, exist_ok=True)
+
+            # Get unique filename in target directory
+            new_file_path = get_unique_filename(target_dir_path, file)
+
+            # Move file
+            shutil.move(file_path, new_file_path)
+            print(f"Moved {file} to {target_dir}")
+
+if __name__ == "__main__":
+    main()

.github/record/2024-12-24/downloads/page.yml

@@ -489,7 +489,7 @@ www_特朗普称上任第一天就要阻止_“变性妄想”.html:
   title: 特朗普称上任第一天就要阻止 “变性妄想”
   snippet: 这位将在1月20日就职的美国总统称：“我将签署行政命令，结束切割儿童生殖器的做法，将跨性别者排除在军队之外，并将他们排除在小学、初中和高中之外”。
   visited_date: '2025-01-12 18:20:42'
-www_12岁时被“快速”接受性别转换_加州医生遭起诉(图).html:
+www_12岁时被“快速”接受性别转换_加州医生遭起诉_图_.html:
   link: https://www.secretchina.com/news/gb/2024/12/10/1074181.html
   md5: 3f3e6d895f11891233c0dd15848970dc
   title: 12岁时被“快速”接受性别转换 加州医生遭起诉(图)

.github/url_dir_map_config.yml

@@ -0,0 +1,19 @@
+url_mappings:
+  - domain: "sina.com"
+    dir: "新浪新闻"
+  - domain: "sina.cn"
+    dir: "新浪新闻"
+  - domain: "news.qq.com"
+    dir: "腾讯新闻"
+  - domain: "163.com"
+    dir: "网易新闻"
+  - domain: "thepaper.cn"
+    dir: "澎湃新闻"
+  - domain: "sohu.com"
+    dir: "搜狐新闻"
+  - domain: "ifeng.com"
+    dir: "凤凰网"
+  - domain: "chinanews.com"
+    dir: "中国新闻网"
+  - domain: "*"
+    dir: "未分类"

新浪新闻/bj_我与泰国人妖的3次亲密接触_组图__新浪生活.md

@@ -47,6 +47,8 @@
 
 版权 © 1996 - 2006 SINA Corporation, All Rights Reserved.
 
+<!-- tcd_original_link http://bj.sina.com.cn/t/2006-07-26/104298745.shtml -->
+
 ## 摘要与附加信息
 
 <!-- tcd_abstract -->