3048cc1ff9
This commit introduces AsyncUrlSeeder, a high-performance URL discovery system that enables intelligent crawling at scale by pre-discovering and filtering URLs before crawling. ## Core Features ### AsyncUrlSeeder Component - Discovers URLs from multiple sources: - Sitemaps (including nested and gzipped) - Common Crawl index - Combined sources for maximum coverage - Extracts page metadata without full crawling: - Title, description, keywords - Open Graph and Twitter Card tags - JSON-LD structured data - Language and charset information - BM25 relevance scoring for intelligent filtering: - Query-based URL discovery - Configurable score thresholds - Automatic ranking by relevance - Performance optimizations: - Async/concurrent processing with configurable workers - Rate limiting (hits per second) - Automatic caching with TTL - Streaming results for large datasets ### SeedingConfig - Comprehensive configuration for URL seeding: - Source selection (sitemap, cc, or both) - URL pattern filtering with wildcards - Live URL validation options - Metadata extraction controls - BM25 scoring parameters - Concurrency and rate limiting ### Integration with AsyncWebCrawler - Seamless pipeline: discover → filter → crawl - Direct compatibility with arun_many() - Significant resource savings by pre-filtering URLs ## Documentation - Comprehensive guide comparing URL seeding vs deep crawling - Complete API reference with parameter tables - Practical examples showing all features - Performance benchmarks and best practices - Integration patterns with AsyncWebCrawler ## Examples - url_seeder_demo.py: Interactive Rich-based demo with: - Basic discovery - Cache management - Live validation - BM25 scoring - Multi-domain discovery - Complete pipeline integration - url_seeder_quick_demo.py: Screenshot-friendly examples: - Pattern-based filtering - Metadata exploration - Smart search with BM25 ## Testing - Comprehensive test suite (test_async_url_seeder_bm25.py) - Coverage of all major features - Edge cases and error handling - Performance and consistency tests ## Implementation Details - Built on httpx with HTTP/2 support - Optional dependencies: lxml, brotli, rank_bm25 - Cache management in ~/.crawl4ai/seeder_cache/ - Logger integration with AsyncLoggerBase - Proper error handling and retry logic ## Bug Fixes - Fixed logger color compatibility (lightblack → bright_black) - Corrected URL extraction from seeder results for arun_many() - Updated all examples and documentation with proper usage This feature enables users to crawl smarter, not harder, by discovering and analyzing URLs before committing resources to crawling them.
170 lines
4.4 KiB
Python
170 lines
4.4 KiB
Python
# __init__.py
|
|
import warnings
|
|
|
|
from .async_webcrawler import AsyncWebCrawler, CacheMode
|
|
# MODIFIED: Add SeedingConfig here
|
|
from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig, SeedingConfig
|
|
|
|
from .content_scraping_strategy import (
|
|
ContentScrapingStrategy,
|
|
WebScrapingStrategy,
|
|
LXMLWebScrapingStrategy,
|
|
)
|
|
from .async_logger import (
|
|
AsyncLoggerBase,
|
|
AsyncLogger,
|
|
)
|
|
from .proxy_strategy import (
|
|
ProxyRotationStrategy,
|
|
RoundRobinProxyStrategy,
|
|
)
|
|
from .extraction_strategy import (
|
|
ExtractionStrategy,
|
|
LLMExtractionStrategy,
|
|
CosineStrategy,
|
|
JsonCssExtractionStrategy,
|
|
JsonXPathExtractionStrategy,
|
|
JsonLxmlExtractionStrategy,
|
|
RegexExtractionStrategy
|
|
)
|
|
from .chunking_strategy import ChunkingStrategy, RegexChunking
|
|
from .markdown_generation_strategy import DefaultMarkdownGenerator
|
|
from .content_filter_strategy import (
|
|
PruningContentFilter,
|
|
BM25ContentFilter,
|
|
LLMContentFilter,
|
|
RelevantContentFilter,
|
|
)
|
|
from .models import CrawlResult, MarkdownGenerationResult, DisplayMode
|
|
from .components.crawler_monitor import CrawlerMonitor
|
|
from .async_dispatcher import (
|
|
MemoryAdaptiveDispatcher,
|
|
SemaphoreDispatcher,
|
|
RateLimiter,
|
|
BaseDispatcher,
|
|
)
|
|
from .docker_client import Crawl4aiDockerClient
|
|
from .hub import CrawlerHub
|
|
from .browser_profiler import BrowserProfiler
|
|
from .deep_crawling import (
|
|
DeepCrawlStrategy,
|
|
BFSDeepCrawlStrategy,
|
|
FilterChain,
|
|
URLPatternFilter,
|
|
DomainFilter,
|
|
ContentTypeFilter,
|
|
URLFilter,
|
|
FilterStats,
|
|
SEOFilter,
|
|
KeywordRelevanceScorer,
|
|
URLScorer,
|
|
CompositeScorer,
|
|
DomainAuthorityScorer,
|
|
FreshnessScorer,
|
|
PathDepthScorer,
|
|
BestFirstCrawlingStrategy,
|
|
DFSDeepCrawlStrategy,
|
|
DeepCrawlDecorator,
|
|
)
|
|
# NEW: Import AsyncUrlSeeder
|
|
from .async_url_seeder import AsyncUrlSeeder
|
|
|
|
from .utils import (
|
|
start_colab_display_server,
|
|
setup_colab_environment
|
|
)
|
|
|
|
__all__ = [
|
|
"AsyncLoggerBase",
|
|
"AsyncLogger",
|
|
"AsyncWebCrawler",
|
|
"BrowserProfiler",
|
|
"LLMConfig",
|
|
"GeolocationConfig",
|
|
# NEW: Add SeedingConfig
|
|
"SeedingConfig",
|
|
# NEW: Add AsyncUrlSeeder
|
|
"AsyncUrlSeeder",
|
|
"DeepCrawlStrategy",
|
|
"BFSDeepCrawlStrategy",
|
|
"BestFirstCrawlingStrategy",
|
|
"DFSDeepCrawlStrategy",
|
|
"FilterChain",
|
|
"URLPatternFilter",
|
|
"ContentTypeFilter",
|
|
"DomainFilter",
|
|
"FilterStats",
|
|
"URLFilter",
|
|
"SEOFilter",
|
|
"KeywordRelevanceScorer",
|
|
"URLScorer",
|
|
"CompositeScorer",
|
|
"DomainAuthorityScorer",
|
|
"FreshnessScorer",
|
|
"PathDepthScorer",
|
|
"DeepCrawlDecorator",
|
|
"CrawlResult",
|
|
"CrawlerHub",
|
|
"CacheMode",
|
|
"ContentScrapingStrategy",
|
|
"WebScrapingStrategy",
|
|
"LXMLWebScrapingStrategy",
|
|
"BrowserConfig",
|
|
"CrawlerRunConfig",
|
|
"HTTPCrawlerConfig",
|
|
"ExtractionStrategy",
|
|
"LLMExtractionStrategy",
|
|
"CosineStrategy",
|
|
"JsonCssExtractionStrategy",
|
|
"JsonXPathExtractionStrategy",
|
|
"JsonLxmlExtractionStrategy",
|
|
"RegexExtractionStrategy",
|
|
"ChunkingStrategy",
|
|
"RegexChunking",
|
|
"DefaultMarkdownGenerator",
|
|
"RelevantContentFilter",
|
|
"PruningContentFilter",
|
|
"BM25ContentFilter",
|
|
"LLMContentFilter",
|
|
"BaseDispatcher",
|
|
"MemoryAdaptiveDispatcher",
|
|
"SemaphoreDispatcher",
|
|
"RateLimiter",
|
|
"CrawlerMonitor",
|
|
"DisplayMode",
|
|
"MarkdownGenerationResult",
|
|
"Crawl4aiDockerClient",
|
|
"ProxyRotationStrategy",
|
|
"RoundRobinProxyStrategy",
|
|
"ProxyConfig",
|
|
"start_colab_display_server",
|
|
"setup_colab_environment",
|
|
]
|
|
|
|
|
|
# def is_sync_version_installed():
|
|
# try:
|
|
# import selenium # noqa
|
|
|
|
# return True
|
|
# except ImportError:
|
|
# return False
|
|
|
|
|
|
# if is_sync_version_installed():
|
|
# try:
|
|
# from .web_crawler import WebCrawler
|
|
|
|
# __all__.append("WebCrawler")
|
|
# except ImportError:
|
|
# print(
|
|
# "Warning: Failed to import WebCrawler even though selenium is installed. This might be due to other missing dependencies."
|
|
# )
|
|
# else:
|
|
# WebCrawler = None
|
|
# # import warnings
|
|
# # print("Warning: Synchronous WebCrawler is not available. Install crawl4ai[sync] for synchronous support. However, please note that the synchronous version will be deprecated soon.")
|
|
|
|
# Disable all Pydantic warnings
|
|
warnings.filterwarnings("ignore", module="pydantic")
|
|
# pydantic_warnings.filter_warnings() |