feat: cleanup unused code and enhance documentation for v0.7.1
- Remove unused StealthConfig from browser_manager.py
- Update LinkPreviewConfig import path in __init__.py and examples
- Fix infinity handling in content_scraping_strategy.py (use 0 instead of float('inf'))
- Remove sanitize_json_data functions from API endpoints
- Add comprehensive C4A Script documentation to release notes
- Update v0.7.0 release notes with improved code examples
- Create v0.7.1 release notes focusing on cleanup and documentation improvements
- Update demo files with corrected import paths and examples
- Fix virtual scroll and adaptive crawling examples across documentation
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
ntohidi
@@ -30,33 +30,40 @@ The Adaptive Crawler maintains a persistent state for each domain, tracking:
|
||||
|
||||
```python
|
||||
from crawl4ai import AsyncWebCrawler, AdaptiveCrawler, AdaptiveConfig
|
||||
import asyncio
|
||||
|
||||
# Initialize with custom adaptive parameters
|
||||
config = AdaptiveConfig(
|
||||
confidence_threshold=0.7, # Min confidence to stop crawling
|
||||
max_depth=5, # Maximum crawl depth
|
||||
max_pages=20, # Maximum number of pages to crawl
|
||||
top_k_links=3, # Number of top links to follow per page
|
||||
strategy="statistical", # 'statistical' or 'embedding'
|
||||
coverage_weight=0.4, # Weight for coverage in confidence calculation
|
||||
consistency_weight=0.3, # Weight for consistency in confidence calculation
|
||||
saturation_weight=0.3 # Weight for saturation in confidence calculation
|
||||
)
|
||||
|
||||
# Initialize adaptive crawler with web crawler
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
adaptive_crawler = AdaptiveCrawler(crawler, config)
|
||||
async def main():
|
||||
|
||||
# Crawl and learn patterns
|
||||
state = await adaptive_crawler.digest(
|
||||
start_url="https://news.example.com/article/12345",
|
||||
query="latest news articles and content"
|
||||
# Configure adaptive crawler
|
||||
config = AdaptiveConfig(
|
||||
strategy="statistical", # or "embedding" for semantic understanding
|
||||
max_pages=10,
|
||||
confidence_threshold=0.7, # Stop at 70% confidence
|
||||
top_k_links=3, # Follow top 3 links per page
|
||||
min_gain_threshold=0.05 # Need 5% information gain to continue
|
||||
)
|
||||
|
||||
# Access results and confidence
|
||||
print(f"Confidence Level: {adaptive_crawler.confidence:.0%}")
|
||||
print(f"Pages Crawled: {len(state.crawled_urls)}")
|
||||
print(f"Knowledge Base: {len(adaptive_crawler.state.knowledge_base)} documents")
|
||||
async with AsyncWebCrawler(verbose=False) as crawler:
|
||||
adaptive = AdaptiveCrawler(crawler, config)
|
||||
|
||||
print("Starting adaptive crawl about Python decorators...")
|
||||
result = await adaptive.digest(
|
||||
start_url="https://docs.python.org/3/glossary.html",
|
||||
query="python decorators functions wrapping"
|
||||
)
|
||||
|
||||
print(f"\n✅ Crawling Complete!")
|
||||
print(f"• Confidence Level: {adaptive.confidence:.0%}")
|
||||
print(f"• Pages Crawled: {len(result.crawled_urls)}")
|
||||
print(f"• Knowledge Base: {len(adaptive.state.knowledge_base)} documents")
|
||||
|
||||
# Get most relevant content
|
||||
relevant = adaptive.get_relevant_content(top_k=3)
|
||||
print(f"\nMost Relevant Pages:")
|
||||
for i, page in enumerate(relevant, 1):
|
||||
print(f"{i}. {page['url']} (relevance: {page['score']:.2%})")
|
||||
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
**Expected Real-World Impact:**
|
||||
@@ -141,53 +148,47 @@ async with AsyncWebCrawler() as crawler:
|
||||
|
||||
**My Solution:** I implemented a three-layer scoring system that analyzes links like a human would—considering their position, context, and relevance to your goals.
|
||||
|
||||
### The Three-Layer Scoring System
|
||||
### Intelligent Link Analysis and Scoring
|
||||
|
||||
```python
|
||||
from crawl4ai import LinkPreviewConfig, CrawlerRunConfig, CacheMode
|
||||
import asyncio
|
||||
from crawl4ai import CrawlerRunConfig, CacheMode, AsyncWebCrawler
|
||||
from crawl4ai.adaptive_crawler import LinkPreviewConfig
|
||||
|
||||
# Configure intelligent link analysis
|
||||
link_config = LinkPreviewConfig(
|
||||
include_internal=True,
|
||||
include_external=False,
|
||||
max_links=10,
|
||||
concurrency=5,
|
||||
query="python tutorial", # For contextual scoring
|
||||
score_threshold=0.3,
|
||||
verbose=True
|
||||
)
|
||||
|
||||
# Use in your crawl
|
||||
result = await crawler.arun(
|
||||
"https://tech-blog.example.com",
|
||||
config=CrawlerRunConfig(
|
||||
link_preview_config=link_config,
|
||||
score_links=True, # Enable intrinsic scoring
|
||||
cache_mode=CacheMode.BYPASS
|
||||
async def main():
|
||||
# Configure intelligent link analysis
|
||||
link_config = LinkPreviewConfig(
|
||||
include_internal=True,
|
||||
include_external=False,
|
||||
max_links=10,
|
||||
concurrency=5,
|
||||
query="python tutorial", # For contextual scoring
|
||||
score_threshold=0.3,
|
||||
verbose=True
|
||||
)
|
||||
)
|
||||
# Use in your crawl
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
result = await crawler.arun(
|
||||
"https://www.geeksforgeeks.org/",
|
||||
config=CrawlerRunConfig(
|
||||
link_preview_config=link_config,
|
||||
score_links=True, # Enable intrinsic scoring
|
||||
cache_mode=CacheMode.BYPASS
|
||||
)
|
||||
)
|
||||
|
||||
# Access scored and sorted links
|
||||
if result.success and result.links:
|
||||
# Get scored links
|
||||
internal_links = result.links.get("internal", [])
|
||||
scored_links = [l for l in internal_links if l.get("total_score")]
|
||||
scored_links.sort(key=lambda x: x.get("total_score", 0), reverse=True)
|
||||
# Access scored and sorted links
|
||||
if result.success and result.links:
|
||||
for link in result.links.get("internal", []):
|
||||
text = link.get('text', 'No text')[:40]
|
||||
print(
|
||||
text,
|
||||
f"{link.get('intrinsic_score', 0):.1f}/10" if link.get('intrinsic_score') is not None else "0.0/10",
|
||||
f"{link.get('contextual_score', 0):.2f}/1" if link.get('contextual_score') is not None else "0.00/1",
|
||||
f"{link.get('total_score', 0):.3f}" if link.get('total_score') is not None else "0.000"
|
||||
)
|
||||
|
||||
# Print scoring results
|
||||
print("Link Scoring Results:")
|
||||
print("=" * 50)
|
||||
for link in scored_links[:5]:
|
||||
text = link.get('text', 'No text')[:40]
|
||||
intrinsic = link.get('intrinsic_score', 0)
|
||||
contextual = link.get('contextual_score', 0)
|
||||
total = link.get('total_score', 0)
|
||||
|
||||
print(f"Link: {text}")
|
||||
print(f" Intrinsic Score: {intrinsic:.1f}/10")
|
||||
print(f" Contextual Score: {contextual:.2f}/1")
|
||||
print(f" Total Score: {total:.3f}")
|
||||
print("-" * 30)
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
**Scoring Components:**
|
||||
@@ -220,58 +221,34 @@ for link in scored_links[:5]:
|
||||
### Technical Architecture
|
||||
|
||||
```python
|
||||
import asyncio
|
||||
from crawl4ai import AsyncUrlSeeder, SeedingConfig
|
||||
|
||||
# Basic discovery - find all product pages
|
||||
seeder_config = SeedingConfig(
|
||||
# Discovery sources
|
||||
source="cc+sitemap", # Sitemap + Common Crawl
|
||||
|
||||
# Filtering
|
||||
pattern="*/product/*", # URL pattern matching
|
||||
|
||||
# Validation
|
||||
live_check=True, # Verify URLs are alive
|
||||
max_urls=50, # Stop at 50 URLs
|
||||
|
||||
# Performance
|
||||
concurrency=100, # Maximum concurrent requests for live checks/head extraction
|
||||
hits_per_sec=10 # Rate limit in requests per second to avoid overwhelming servers
|
||||
)
|
||||
async def main():
|
||||
async with AsyncUrlSeeder() as seeder:
|
||||
# Discover Python tutorial URLs
|
||||
config = SeedingConfig(
|
||||
source="sitemap", # Use sitemap
|
||||
pattern="*python*", # URL pattern filter
|
||||
extract_head=True, # Get metadata
|
||||
query="python tutorial", # For relevance scoring
|
||||
scoring_method="bm25",
|
||||
score_threshold=0.2,
|
||||
max_urls=10
|
||||
)
|
||||
|
||||
print("Discovering Python async tutorial URLs...")
|
||||
urls = await seeder.urls("https://www.geeksforgeeks.org/", config)
|
||||
|
||||
print(f"\n✅ Found {len(urls)} relevant URLs:")
|
||||
for i, url_info in enumerate(urls[:5], 1):
|
||||
print(f"\n{i}. {url_info['url']}")
|
||||
if url_info.get('relevance_score'):
|
||||
print(f" Relevance: {url_info['relevance_score']:.3f}")
|
||||
if url_info.get('head_data', {}).get('title'):
|
||||
print(f" Title: {url_info['head_data']['title'][:60]}...")
|
||||
|
||||
async with AsyncUrlSeeder() as seeder:
|
||||
console.print("Discovering URLs from Python docs...")
|
||||
urls = await seeder.urls("docs.python.org", seeding_config)
|
||||
console.print(f"\n✓ Discovered {len(urls)} URLs")
|
||||
|
||||
# Advanced: Relevance-based discovery
|
||||
research_config = SeedingConfig(
|
||||
source="sitemap+cc", # Sitemap + Common Crawl
|
||||
pattern="*/blog/*", # Blog posts only
|
||||
|
||||
# Content relevance
|
||||
extract_head=True, # Get meta tags
|
||||
query="quantum computing tutorials",
|
||||
scoring_method="bm25", # BM25 scoring method
|
||||
score_threshold=0.4, # High relevance only
|
||||
|
||||
# Smart filtering
|
||||
filter_nonsense_urls=True, # Remove .xml, .txt, etc.
|
||||
|
||||
force=True # Bypass cache
|
||||
)
|
||||
|
||||
# Discover with progress tracking
|
||||
discovered = []
|
||||
async with AsyncUrlSeeder() as seeder:
|
||||
discovered = await seeder.urls("https://physics-blog.com", research_config)
|
||||
console.print(f"\n✓ Discovered {len(discovered)} URLs")
|
||||
|
||||
# Results include scores and metadata
|
||||
for url_data in discovered[:5]:
|
||||
print(f"URL: {url_data['url']}")
|
||||
print(f"Score: {url_data['relevance_score']:.3f}")
|
||||
print(f"Title: {url_data['head_data']['title']}")
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
**Discovery Methods:**
|
||||
|
||||
Reference in New Issue
Block a user