feat(obsidian-kb): 实现短链接解析功能

- 新增 shortlink_resolver.py 模块
  * 检测 B站短链接(b23.tv)和其他短链接服务
  * 提供友好的用户引导信息
  * 支持 Playwright 浏览器自动化解析(可选)

- 集成到 handler.py
  * 短链接自动检测和提示
  * 智能区分短链接和完整 URL

- 更新 add_video.py
  * 支持短链接解析
  * 添加 --playwright 参数启用浏览器解析

- 新增 test_shortlink.py 测试脚本
  * 测试单个短链接检测
  * 测试多个短链接检测
  * 测试混合内容场景
  * 所有测试通过

- 更新文档
  * SKILL.md: 添加短链接说明
  * AUTO_TRIGGER.md: 添加短链接章节
  * obsidian-kb-improvements.md: 标记任务2为已完成

功能特点:
- 方案A(用户引导):已实现并作为默认行为
- 方案B(浏览器自动化):提供 PlaywrightResolver 类,可选使用
- 方案C(代理池):未实现(复杂度高,收益低)

验收标准达成:
✅ 短链接能够友好处理(显示引导信息)
✅ 用户不会感到困惑
✅ 支持 b23.tv 和其他短链接服务(检测)
✅ 集成到 handler.py
✅ 测试各种短链接场景
This commit is contained in:
OpenClaw Agent
2026-02-06 21:22:45 +08:00
parent 7a1ad6088a
commit fbcc3df2cf
7 changed files with 746 additions and 77 deletions
Regular → Executable
+45 -11
View File
@@ -13,16 +13,22 @@ sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), 'src
from sources.bilibili import BilibiliAdapter
from models import Content, ContentStatus
from storage import Storage
from shortlink_resolver import (
ShortLinkResolver,
PlaywrightResolver,
detect_and_format
)
def resolve_short_url(url: str) -> str:
def resolve_short_url(url: str, try_playwright: bool = False) -> str:
"""
解析短链接(如 b23.tv)到完整URL,或接受BV号
Args:
url: 可能是短链接的URL、完整URL或BV号
try_playwright: 是否尝试使用Playwright解析短链接
Returns:
str: 完整URL或BV号
str: 完整URL或BV号,如果失败返回None
"""
# 如果已经是完整URL,直接返回
if 'bilibili.com/video/' in url:
@@ -33,23 +39,42 @@ def resolve_short_url(url: str) -> str:
return url
# 如果是短链接,尝试解析
if 'b23.tv' in url:
resolver = ShortLinkResolver()
if resolver.is_bilibili_short_link(url):
print(f" ⚠️ 检测到短链接 {url}")
print(f" 💡 B站对短链接有反爬虫保护,请提供:")
print(f" 1. 完整URL: https://www.bilibili.com/video/BVxxxxx")
print(f" 2. 或BV号: BVxxxxx")
print(f"\n 提示: 可以在浏览器打开短链接,从地址栏复制完整URL")
# 尝试使用Playwright解析(如果启用)
if try_playwright:
print(f" 🔄 尝试使用浏览器解析...")
playwright_resolver = PlaywrightResolver(headless=True)
try:
resolved_url = playwright_resolver.resolve_bilibili_short(url)
if resolved_url:
print(f" ✅ 解析成功: {resolved_url}")
return resolved_url
else:
print(f" ❌ 浏览器解析失败")
except Exception as e:
print(f" ❌ Playwright不可用或解析失败: {e}")
# 显示用户引导
print("")
print(resolver.format_short_link_help(url))
print("")
return None
# 默认返回原URL
return url
def add_video_to_inbox(url: str) -> str:
def add_video_to_inbox(url: str, try_playwright: bool = False) -> str:
"""
添加B站视频到收件箱
Args:
url: B站视频URL
try_playwright: 是否尝试使用Playwright解析短链接
Returns:
str: Content ID
@@ -57,7 +82,7 @@ def add_video_to_inbox(url: str) -> str:
print(f"📥 正在处理视频: {url}")
# 解析短链接
resolved_url = resolve_short_url(url)
resolved_url = resolve_short_url(url, try_playwright=try_playwright)
if resolved_url is None:
return None
@@ -104,8 +129,17 @@ def add_video_to_inbox(url: str) -> str:
if __name__ == '__main__':
if len(sys.argv) < 2:
print("用法: python3 add_video.py <B站视频URL>")
print("示例: python3 add_video.py https://b23.tv/oLBZZfK")
print("示例:")
print(" python3 add_video.py https://www.bilibili.com/video/BV1xx411c7mD")
print(" python3 add_video.py BV1xx411c7mD")
print(" python3 add_video.py https://b23.tv/oLBZZfK")
print("\n选项:")
print(" --playwright 尝试使用浏览器解析短链接")
sys.exit(1)
url = sys.argv[1]
add_video_to_inbox(url)
try_playwright = '--playwright' in sys.argv
if try_playwright and url == '--playwright' and len(sys.argv) > 2:
url = sys.argv[2]
add_video_to_inbox(url, try_playwright=try_playwright)