ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(core): replace float('inf') with math.inf

Browse Source 
Replace float('inf') and float('-inf') with math.inf and -math.inf from the math module for better readability and performance. Also clean up imports and remove unused speed comparison code.

No breaking changes.
This commit is contained in:
UncleCode
2025-03-04 18:23:55 +08:00
parent f334daa979
commit 415c1c5bee
5 changed files with 16 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
docs/examples/quickstart_async.config.py
View File

@@ -416,6 +416,7 @@ async def crawl_dynamic_content_pages_method_2():
async def cosine_similarity_extraction():
from crawl4ai.extraction_strategy import CosineStrategy
crawl_config = CrawlerRunConfig(
cache_mode=CacheMode.BYPASS,
extraction_strategy=CosineStrategy(
@@ -507,6 +508,9 @@ async def ssl_certification():
if result.success and result.ssl_certificate:
cert = result.ssl_certificate
tmp_dir = os.path.join(__location__, "tmp")
os.makedirs(tmp_dir, exist_ok=True)
# 1. Access certificate properties directly
print("\nCertificate Information:")
print(f"Issuer: {cert.issuer.get('CN', '')}")
@@ -529,67 +533,6 @@ async def ssl_certification():
print(f"- DER: {os.path.join(tmp_dir, 'certificate.der')}")
# Speed Comparison
async def speed_comparison():
print("\n--- Speed Comparison ---")
# Firecrawl comparison
from firecrawl import FirecrawlApp
app = FirecrawlApp(api_key=os.environ["FIRECRAWL_API_KEY"])
start = time.time()
scrape_status = app.scrape_url(
"https://www.nbcnews.com/business", params={"formats": ["markdown", "html"]}
)
end = time.time()
print("Firecrawl:")
print(f"Time taken: {end - start:.2f} seconds")
print(f"Content length: {len(scrape_status['markdown'])} characters")
print(f"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}")
print()
# Crawl4AI comparisons
browser_config = BrowserConfig(headless=True)
# Simple crawl
async with AsyncWebCrawler(config=browser_config) as crawler:
start = time.time()
result = await crawler.arun(
url="https://www.nbcnews.com/business",
config=CrawlerRunConfig(
cache_mode=CacheMode.BYPASS, word_count_threshold=0
),
)
end = time.time()
print("Crawl4AI (simple crawl):")
print(f"Time taken: {end - start:.2f} seconds")
print(f"Content length: {len(result.markdown)} characters")
print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
print()
# Advanced filtering
start = time.time()
result = await crawler.arun(
url="https://www.nbcnews.com/business",
config=CrawlerRunConfig(
cache_mode=CacheMode.BYPASS,
word_count_threshold=0,
markdown_generator=DefaultMarkdownGenerator(
content_filter=PruningContentFilter(
threshold=0.48, threshold_type="fixed", min_word_threshold=0
)
),
),
)
end = time.time()
print("Crawl4AI (Markdown Plus):")
print(f"Time taken: {end - start:.2f} seconds")
print(f"Content length: {len(result.markdown.raw_markdown)} characters")
print(f"Fit Markdown: {len(result.markdown.fit_markdown)} characters")
print(f"Images found: {result.markdown.raw_markdown.count('cldnry.s-nbcnews.com')}")
print()
# Main execution
async def main():
# Basic examples