c6d48080a4
Add AsyncLoggerBase abstract class to standardize logger interface and introduce AsyncFileLogger for file-only logging. Remove deprecated always_bypass_cache parameter and clean up AsyncWebCrawler initialization. BREAKING CHANGE: Removed deprecated 'always_by_pass_cache' parameter. Use BrowserConfig cache settings instead.
31 lines
862 B
Python
31 lines
862 B
Python
import asyncio
|
|
from crawl4ai import (
|
|
AsyncWebCrawler,
|
|
BrowserConfig,
|
|
CrawlerRunConfig,
|
|
CacheMode,
|
|
DefaultMarkdownGenerator,
|
|
PruningContentFilter,
|
|
)
|
|
|
|
|
|
async def main():
|
|
browser_config = BrowserConfig(headless=True, verbose=True)
|
|
async with AsyncWebCrawler(config=browser_config) as crawler:
|
|
crawler_config = CrawlerRunConfig(
|
|
cache_mode=CacheMode.BYPASS,
|
|
markdown_generator=DefaultMarkdownGenerator(
|
|
content_filter=PruningContentFilter(
|
|
threshold=0.48, threshold_type="fixed", min_word_threshold=0
|
|
)
|
|
),
|
|
)
|
|
result = await crawler.arun(
|
|
url="https://www.helloworld.org", config=crawler_config
|
|
)
|
|
print(result.markdown_v2.raw_markdown[:500])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|