openclaw-skills/skills/kb-link-parser/link_parser_shortlink.py

#!/usr/bin/env python3
"""
Short link resolver for link-parser skill.

Provides utilities for detecting and resolving short links, particularly
Bilibili short links (b23.tv) which may be blocked by anti-scraping measures.

Supported short link services:
- Bilibili: b23.tv
- Generic URL shorteners (detection only)
"""

import re
from typing import Optional, Dict, List, Tuple
from urllib.parse import urlparse


class ShortLinkResolver:
    """Short link detection and resolution handler"""

    # Pattern for Bilibili short links
    BILIBILI_SHORT_PATTERN = re.compile(r'https?://b23\.tv/([a-zA-Z0-9]+)')

    # Pattern for other short link services
    OTHER_SHORT_PATTERNS = {
        'bit.ly': re.compile(r'https?://bit\.ly/\w+'),
        't.cn': re.compile(r'https?://t\.cn/\w+'),
        'dwz.cn': re.compile(r'https?://dwz\.cn/\w+'),
        'goo.gl': re.compile(r'https?://goo\.gl/\w+'),
        'tinyurl.com': re.compile(r'https?://tinyurl\.com/\w+'),
    }

    @staticmethod
    def detect_short_links(text: str) -> List[Dict[str, str]]:
        """
        Detect short links in text.

        Args:
            text: Input text to search

        Returns:
            List of detected short links with metadata:
            [
                {
                    'url': 'https://b23.tv/xxxxx',
                    'platform': 'bilibili',
                    'is_short': True
                },
                ...
            ]
        """
        detected = []

        # Check for Bilibili short links
        for match in ShortLinkResolver.BILIBILI_SHORT_PATTERN.finditer(text):
            detected.append({
                'url': match.group(0),
                'code': match.group(1),
                'platform': 'bilibili',
                'is_short': True
            })

        # Check for other short link services
        for platform, pattern in ShortLinkResolver.OTHER_SHORT_PATTERNS.items():
            for match in pattern.finditer(text):
                detected.append({
                    'url': match.group(0),
                    'platform': platform,
                    'is_short': True
                })

        return detected

    @staticmethod
    def is_bilibili_short_link(url: str) -> bool:
        """
        Check if URL is a Bilibili short link.

        Args:
            url: URL to check

        Returns:
            True if URL is a b23.tv short link
        """
        return bool(ShortLinkResolver.BILIBILI_SHORT_PATTERN.match(url))

    @staticmethod
    def format_short_link_help(short_link: Optional[str] = None) -> str:
        """
        Format help message for short links.

        Args:
            short_link: Optional short link URL to mention

        Returns:
            Help message
        """
        lines = [
            "Detection: Short link",
            ""
        ]

        if short_link:
            lines.append(f"Short link: {short_link}")
            lines.append("")

        lines.extend([
            "Due to anti-scraping protection, short links cannot be automatically resolved.",
            "Please provide the full URL or the content ID (e.g., BV号 for Bilibili).",
            "",
            "Full URL format: https://www.bilibili.com/video/BVxxxxx"
        ])

        return "\n".join(lines)

    @staticmethod
    def format_short_link_warning(short_links: List[Dict[str, str]]) -> str:
        """
        Format warning message for multiple short links.

        Args:
            short_links: List of short link metadata

        Returns:
            Warning message
        """
        if not short_links:
            return ""

        lines = [
            "Short links detected:",
            ""
        ]

        for i, link in enumerate(short_links, 1):
            platform = link.get('platform', 'unknown')
            url = link['url']

            if platform == 'bilibili':
                lines.append(f"  [{i}] Bilibili short link: {url}")
                lines.append("      Full URL or BV ID required")
            else:
                lines.append(f"  [{i}] {platform}: {url}")

            lines.append("")

        return "\n".join(lines)


class PlaywrightResolver:
    """
    Browser-based short link resolver using Playwright.

    This is an optional implementation for environments where Playwright
    is available. It can bypass anti-scraping measures by simulating
    a real browser.

    Requirements:
        pip install playwright
        playwright install chromium
    """

    def __init__(self, headless: bool = True, timeout: int = 10000):
        """
        Initialize Playwright resolver.

        Args:
            headless: Whether to run browser in headless mode
            timeout: Page navigation timeout in milliseconds
        """
        self.headless = headless
        self.timeout = timeout
        self._playwright = None

    def _check_playwright_available(self) -> bool:
        """Check if Playwright is installed and available"""
        try:
            from playwright.sync_api import sync_playwright
            return True
        except ImportError:
            return False

    def resolve(self, short_url: str) -> Optional[str]:
        """
        Resolve short link using Playwright browser automation.

        Args:
            short_url: Short URL to resolve

        Returns:
            Final URL after redirects, or None if resolution fails
        """
        if not self._check_playwright_available():
            raise ImportError(
                "Playwright not installed. Install with: pip install playwright && playwright install chromium"
            )

        from playwright.sync_api import sync_playwright

        try:
            with sync_playwright() as p:
                # Launch browser
                browser = p.chromium.launch(headless=self.headless)
                context = browser.new_context(
                    user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
                    viewport={'width': 1920, 'height': 1080}
                )
                page = context.new_page()

                # Navigate to short URL
                page.goto(short_url, timeout=self.timeout, wait_until='networkidle')

                # Get final URL
                final_url = page.url

                # Close browser
                browser.close()

                return final_url

        except Exception as e:
            print(f"Playwright resolution failed: {e}")
            return None

    def resolve_bilibili_short(self, short_url: str) -> Optional[str]:
        """
        Resolve Bilibili short link and extract BV ID.

        Args:
            short_url: Bilibili short URL (e.g., https://b23.tv/xxxxx)

        Returns:
            Full Bilibili URL with BV ID, or None if resolution fails
        """
        final_url = self.resolve(short_url)
        if not final_url:
            return None

        # Check if final URL contains BV ID
        if 'bilibili.com/video/' in final_url:
            return final_url

        # Extract BV ID if present in URL
        bv_pattern = re.compile(r'(BV[a-zA-Z0-9]{10})')
        match = bv_pattern.search(final_url)
        if match:
            return f"https://www.bilibili.com/video/{match.group(1)}"

        return None


def get_resolver() -> ShortLinkResolver:
    """
    Get the default resolver instance.

    Returns:
        ShortLinkResolver instance
    """
    return ShortLinkResolver()


def detect_short_links(text: str) -> List[Dict[str, str]]:
    """
    Detect short links in text.

    Args:
        text: Input text to search

    Returns:
        List of detected short links with metadata
    """
    resolver = ShortLinkResolver()
    return resolver.detect_short_links(text)


# CLI interface for testing
def main():
    """CLI for testing the short link resolver."""
    import sys

    if len(sys.argv) < 2:
        print("Usage: python3 link_parser_shortlink.py 'text to test'")
        print("\nExamples:")
        print('  python3 link_parser_shortlink.py "Check this: https://b23.tv/oLBZZfK"')
        print('  python3 link_parser_shortlink.py "https://bit.ly/xxxxx"')
        sys.exit(1)

    text = ' '.join(sys.argv[1:])
    short_links = detect_short_links(text)

    import json
    print(json.dumps(short_links, ensure_ascii=False, indent=2))


if __name__ == '__main__':
    main()