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/media_platform/douyin/help.py

@@ -16,10 +16,15 @@
 # @Desc    : 获取 a_bogus 参数, 学习交流使用，请勿用作商业用途，侵权联系作者删除
 
 import random
+import re
+from typing import Optional
 
 import execjs
 from playwright.async_api import Page
 
+from model.m_douyin import VideoUrlInfo, CreatorUrlInfo
+from tools.crawler_util import extract_url_params_to_dict
+
 douyin_sign_obj = execjs.compile(open('libs/douyin.js', encoding='utf-8-sig').read())
 
 def get_web_id():
@@ -83,3 +88,103 @@ async def get_a_bogus_from_playright(params: str, post_data: dict, user_agent: s
 
     return a_bogus
 
+
+def parse_video_info_from_url(url: str) -> VideoUrlInfo:
+    """
+    从抖音视频URL中解析出视频ID
+    支持以下格式:
+    1. 普通视频链接: https://www.douyin.com/video/7525082444551310602
+    2. 带modal_id参数的链接:
+       - https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?modal_id=7525082444551310602
+       - https://www.douyin.com/root/search/python?modal_id=7471165520058862848
+    3. 短链接: https://v.douyin.com/iF12345ABC/ (需要client解析)
+    4. 纯ID: 7525082444551310602
+
+    Args:
+        url: 抖音视频链接或ID
+    Returns:
+        VideoUrlInfo: 包含视频ID的对象
+    """
+    # 如果是纯数字ID,直接返回
+    if url.isdigit():
+        return VideoUrlInfo(aweme_id=url, url_type="normal")
+
+    # 检查是否是短链接 (v.douyin.com)
+    if "v.douyin.com" in url or url.startswith("http") and len(url) < 50 and "video" not in url:
+        return VideoUrlInfo(aweme_id="", url_type="short")  # 需要通过client解析
+
+    # 尝试从URL参数中提取modal_id
+    params = extract_url_params_to_dict(url)
+    modal_id = params.get("modal_id")
+    if modal_id:
+        return VideoUrlInfo(aweme_id=modal_id, url_type="modal")
+
+    # 从标准视频URL中提取ID: /video/数字
+    video_pattern = r'/video/(\d+)'
+    match = re.search(video_pattern, url)
+    if match:
+        aweme_id = match.group(1)
+        return VideoUrlInfo(aweme_id=aweme_id, url_type="normal")
+
+    raise ValueError(f"无法从URL中解析出视频ID: {url}")
+
+
+def parse_creator_info_from_url(url: str) -> CreatorUrlInfo:
+    """
+    从抖音创作者主页URL中解析出创作者ID (sec_user_id)
+    支持以下格式:
+    1. 创作者主页: https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?from_tab_name=main
+    2. 纯ID: MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE
+
+    Args:
+        url: 抖音创作者主页链接或sec_user_id
+    Returns:
+        CreatorUrlInfo: 包含创作者ID的对象
+    """
+    # 如果是纯ID格式(通常以MS4wLjABAAAA开头),直接返回
+    if url.startswith("MS4wLjABAAAA") or (not url.startswith("http") and "douyin.com" not in url):
+        return CreatorUrlInfo(sec_user_id=url)
+
+    # 从创作者主页URL中提取sec_user_id: /user/xxx
+    user_pattern = r'/user/([^/?]+)'
+    match = re.search(user_pattern, url)
+    if match:
+        sec_user_id = match.group(1)
+        return CreatorUrlInfo(sec_user_id=sec_user_id)
+
+    raise ValueError(f"无法从URL中解析出创作者ID: {url}")
+
+
+if __name__ == '__main__':
+    # 测试视频URL解析
+    print("=== 视频URL解析测试 ===")
+    test_urls = [
+        "https://www.douyin.com/video/7525082444551310602",
+        "https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?from_tab_name=main&modal_id=7525082444551310602",
+        "https://www.douyin.com/root/search/python?aid=b733a3b0-4662-4639-9a72-c2318fba9f3f&modal_id=7471165520058862848&type=general",
+        "7525082444551310602",
+    ]
+    for url in test_urls:
+        try:
+            result = parse_video_info_from_url(url)
+            print(f"✓ URL: {url[:80]}...")
+            print(f"  结果: {result}\n")
+        except Exception as e:
+            print(f"✗ URL: {url}")
+            print(f"  错误: {e}\n")
+
+    # 测试创作者URL解析
+    print("=== 创作者URL解析测试 ===")
+    test_creator_urls = [
+        "https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?from_tab_name=main",
+        "MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE",
+    ]
+    for url in test_creator_urls:
+        try:
+            result = parse_creator_info_from_url(url)
+            print(f"✓ URL: {url[:80]}...")
+            print(f"  结果: {result}\n")
+        except Exception as e:
+            print(f"✗ URL: {url}")
+            print(f"  错误: {e}\n")
+