feat: Add KB knowledge base series skills
- kb-link-parser: Multi-platform URL parser (Bilibili, YouTube, Zhihu) - kb-bilibili-metadata: Bilibili video/article/up主 metadata extractor - kb-zhihu-metadata: Zhihu question/answer/user metadata extractor - kb-bilibili-content: Bilibili video download and content extraction - kb-ocr-processor: OCR text extraction from video frames - kb-deep-analyzer: AI-powered deep content analysis - kb-workflow: Workflow orchestration (inbox, archive, subscriptions, report) Also add: - ARCHITECTURE_FLOWCHART.md: System architecture diagrams - DETAILED_DESIGN.md: Complete design documentation
This commit is contained in:
OpenClaw Agent
@@ -0,0 +1,43 @@
|
||||
# KB Link Parser Skill
|
||||
|
||||
**kb-link-parser** - Extract and resolve IDs from various platform URLs.
|
||||
|
||||
## Features
|
||||
|
||||
- Multi-platform support: Bilibili, YouTube, Zhihu
|
||||
- Short link detection: b23.tv and other short links
|
||||
- Multiple content types: video, article, up主, playlist, collection
|
||||
- Batch processing from file
|
||||
- JSON output format
|
||||
|
||||
## Commands
|
||||
|
||||
```bash
|
||||
# Parse single URL
|
||||
python link-parser.py --url "https://www.bilibili.com/video/BV1xx411c7mD"
|
||||
|
||||
# Batch processing
|
||||
python link-parser.py --batch urls.txt --output results.json
|
||||
|
||||
# Output format
|
||||
python link-parser.py --url "..." --format json
|
||||
```
|
||||
|
||||
## Output
|
||||
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"data": {
|
||||
"platform": "bilibili",
|
||||
"type": "video",
|
||||
"id": "BV1xx411c7mD"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
cp -r kb-link-parser/ ~/skills/
|
||||
```
|
||||
@@ -0,0 +1,387 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Link Parser - Extract and resolve IDs from various platform URLs.
|
||||
|
||||
Supports:
|
||||
- Bilibili (video, article, up主, collection, series)
|
||||
- YouTube (video, channel, playlist)
|
||||
- Zhihu (question, answer, user, collection)
|
||||
- Short links (b23.tv, etc.)
|
||||
|
||||
Usage:
|
||||
python link-parser.py --url "https://www.bilibili.com/video/BV1xx411c7mD"
|
||||
python link-parser.py --batch urls.txt --output results.json
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from typing import Optional, Dict, Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from link_parser_shortlink import ShortLinkResolver
|
||||
|
||||
|
||||
class LinkParser:
|
||||
"""Main link parser class"""
|
||||
|
||||
# Bilibili patterns
|
||||
BILIBILI_VIDEO_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/video/(BV[a-zA-Z0-9]+)')
|
||||
BILIBILI_VIDEO_SHORT_PATTERN = re.compile(r'https?://b23\.tv/([a-zA-Z0-9]+)')
|
||||
BILIBILI_ARTICLE_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/article/([a-zA-Z0-9]+)')
|
||||
BILIBILI_SPACE_PATTERN = re.compile(r'https?://(?:space\.)?bilibili\.com/(\d+)')
|
||||
BILIBILI_FAVEPATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/opus/(\d+)')
|
||||
BILIBILI_SERIES_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/series/([a-zA-Z0-9]+)')
|
||||
|
||||
# YouTube patterns
|
||||
YOUTUBE_VIDEO_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?(?:youtube\.com/watch\?v=|youtu\.be/)([a-zA-Z0-9_-]{11})')
|
||||
YOUTUBE_CHANNEL_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?youtube\.com/channel/([a-zA-Z0-9_-]+)')
|
||||
YOUTUBE_USER_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?youtube\.com/user/([a-zA-Z0-9_-]+)')
|
||||
YOUTUBE_PLAYLIST_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?youtube\.com/playlist\?list=([a-zA-Z0-9_-]+)')
|
||||
|
||||
# Zhihu patterns
|
||||
ZHIHAU_QUESTION_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/question/(\d+)')
|
||||
ZHIHAU_ANSWER_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/question/\d+/answer/(\d+)')
|
||||
ZHIHAU_USER_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/people/([a-zA-Z0-9_-]+)')
|
||||
ZHIHAU_COLUMN_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/column/([a-zA-Z0-9_-]+)')
|
||||
ZHIHAU_COLLECTION_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/collection/(\d+)')
|
||||
|
||||
def __init__(self):
|
||||
self.shortlink_resolver = ShortLinkResolver()
|
||||
|
||||
def resolve_shortlink(self, url: str) -> Optional[str]:
|
||||
"""
|
||||
Resolve short link to get final URL.
|
||||
|
||||
Args:
|
||||
url: Short URL to resolve
|
||||
|
||||
Returns:
|
||||
Final URL after resolution, or None if not resolvable
|
||||
"""
|
||||
# Check if it's a known short link pattern
|
||||
if self.shortlink_resolver.is_bilibili_short_link(url):
|
||||
# For b23.tv, we need Playwright to resolve
|
||||
# Return the short URL as-is with a note
|
||||
return url
|
||||
|
||||
# Return original URL for other cases
|
||||
return url
|
||||
|
||||
def extract_bilibili_id(self, url: str) -> Optional[Dict[str, str]]:
|
||||
"""
|
||||
Extract Bilibili ID from URL.
|
||||
|
||||
Args:
|
||||
url: Bilibili URL
|
||||
|
||||
Returns:
|
||||
Dict with platform, type, and id fields, or None if not matched
|
||||
"""
|
||||
# Try video
|
||||
match = self.BILIBILI_VIDEO_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "bilibili",
|
||||
"type": "video",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try article
|
||||
match = self.BILIBILI_ARTICLE_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "bilibili",
|
||||
"type": "article",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try space (UP主)
|
||||
match = self.BILIBILI_SPACE_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "bilibili",
|
||||
"type": "up主",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try collection
|
||||
match = self.BILIBILI_FAVEPATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "bilibili",
|
||||
"type": "collection",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try series
|
||||
match = self.BILIBILI_SERIES_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "bilibili",
|
||||
"type": "series",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
return None
|
||||
|
||||
def extract_youtube_id(self, url: str) -> Optional[Dict[str, str]]:
|
||||
"""
|
||||
Extract YouTube ID from URL.
|
||||
|
||||
Args:
|
||||
url: YouTube URL
|
||||
|
||||
Returns:
|
||||
Dict with platform, type, and id fields, or None if not matched
|
||||
"""
|
||||
# Try video
|
||||
match = self.YOUTUBE_VIDEO_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "youtube",
|
||||
"type": "video",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try channel
|
||||
match = self.YOUTUBE_CHANNEL_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "youtube",
|
||||
"type": "channel",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try user
|
||||
match = self.YOUTUBE_USER_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "youtube",
|
||||
"type": "user",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try playlist
|
||||
match = self.YOUTUBE_PLAYLIST_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "youtube",
|
||||
"type": "playlist",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
return None
|
||||
|
||||
def extract_zhihu_id(self, url: str) -> Optional[Dict[str, str]]:
|
||||
"""
|
||||
Extract Zhihu ID from URL.
|
||||
|
||||
Args:
|
||||
url: Zhihu URL
|
||||
|
||||
Returns:
|
||||
Dict with platform, type, and id fields, or None if not matched
|
||||
"""
|
||||
# Try question
|
||||
match = self.ZHIHAU_QUESTION_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "zhihu",
|
||||
"type": "question",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try answer
|
||||
match = self.ZHIHAU_ANSWER_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "zhihu",
|
||||
"type": "answer",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try user
|
||||
match = self.ZHIHAU_USER_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "zhihu",
|
||||
"type": "user",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try column
|
||||
match = self.ZHIHAU_COLUMN_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "zhihu",
|
||||
"type": "column",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
# Try collection
|
||||
match = self.ZHIHAU_COLLECTION_PATTERN.match(url)
|
||||
if match:
|
||||
return {
|
||||
"platform": "zhihu",
|
||||
"type": "collection",
|
||||
"id": match.group(1)
|
||||
}
|
||||
|
||||
return None
|
||||
|
||||
def parse(self, url: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Parse URL and extract platform-specific ID.
|
||||
|
||||
Args:
|
||||
url: URL to parse
|
||||
|
||||
Returns:
|
||||
Dict with platform, type, id, and original_url fields
|
||||
"""
|
||||
result = {
|
||||
"platform": None,
|
||||
"type": None,
|
||||
"id": None,
|
||||
"original_url": url,
|
||||
"resolved_url": None,
|
||||
"success": False,
|
||||
"error": None
|
||||
}
|
||||
|
||||
# First, resolve short links
|
||||
resolved = self.resolve_shortlink(url)
|
||||
if resolved:
|
||||
result["resolved_url"] = resolved
|
||||
url = resolved
|
||||
|
||||
# Try each platform
|
||||
bilibili_result = self.extract_bilibili_id(url)
|
||||
if bilibili_result:
|
||||
result.update(bilibili_result)
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
youtube_result = self.extract_youtube_id(url)
|
||||
if youtube_result:
|
||||
result.update(youtube_result)
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
zhihu_result = self.extract_zhihu_id(url)
|
||||
if zhihu_result:
|
||||
result.update(zhihu_result)
|
||||
result["success"] = True
|
||||
return result
|
||||
|
||||
# Check for short links that need resolution
|
||||
short_links = self.shortlink_resolver.detect_short_links(url)
|
||||
if short_links:
|
||||
result["error"] = "Short link detected. Please provide the full URL."
|
||||
return result
|
||||
|
||||
result["error"] = "Unsupported URL format"
|
||||
return result
|
||||
|
||||
|
||||
def format_output(data: Dict[str, Any], output_format: str = "json") -> str:
|
||||
"""Format output based on specified format."""
|
||||
if output_format == "json":
|
||||
return json.dumps(data, ensure_ascii=False, indent=2)
|
||||
elif output_format == "compact":
|
||||
return json.dumps(data, ensure_ascii=False, separators=(',', ':'))
|
||||
elif output_format == "text":
|
||||
lines = []
|
||||
for key, value in data.items():
|
||||
if value is not None:
|
||||
lines.append(f"{key}: {value}")
|
||||
return "\n".join(lines)
|
||||
else:
|
||||
return json.dumps(data, ensure_ascii=False, indent=2)
|
||||
|
||||
|
||||
def main():
|
||||
"""Main entry point."""
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Parse and extract IDs from various platform URLs",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog="""
|
||||
Examples:
|
||||
%(prog)s --url "https://www.bilibili.com/video/BV1xx411c7mD"
|
||||
%(prog)s --url "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
|
||||
%(prog)s --url "https://www.zhihu.com/question/266309957"
|
||||
%(prog)s --batch urls.txt --output results.json
|
||||
"""
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--url", "-u",
|
||||
help="Single URL to parse"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--batch", "-b",
|
||||
help="File containing URLs to parse (one per line)"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--output", "-o",
|
||||
help="Output file path (for batch mode)"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--format", "-f",
|
||||
choices=["json", "compact", "text"],
|
||||
default="json",
|
||||
help="Output format (default: json)"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# Check if we're in shortlink help mode
|
||||
if len(sys.argv) == 2 and sys.argv[1] in ['--help', '-h']:
|
||||
parser.print_help()
|
||||
return 0
|
||||
|
||||
if not args.url and not args.batch:
|
||||
parser.print_help()
|
||||
print("\nError: Please provide --url or --batch")
|
||||
return 1
|
||||
|
||||
link_parser = LinkParser()
|
||||
|
||||
if args.url:
|
||||
# Single URL mode
|
||||
result = link_parser.parse(args.url)
|
||||
print(format_output(result, args.format))
|
||||
return 0 if result["success"] else 1
|
||||
|
||||
elif args.batch:
|
||||
try:
|
||||
with open(args.batch, 'r', encoding='utf-8') as f:
|
||||
urls = [line.strip() for line in f if line.strip()]
|
||||
except Exception as e:
|
||||
print(f"Error reading file: {e}", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
results = []
|
||||
for url in urls:
|
||||
result = link_parser.parse(url)
|
||||
results.append(result)
|
||||
|
||||
if args.output:
|
||||
with open(args.output, 'w', encoding='utf-8') as f:
|
||||
json.dump(results, f, ensure_ascii=False, indent=2)
|
||||
print(f"Results written to {args.output}")
|
||||
else:
|
||||
for result in results:
|
||||
print(format_output(result, args.format))
|
||||
print("-" * 40)
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,296 @@
|
||||
#!/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()
|
||||
Reference in New Issue
Block a user