chore: import upstream snapshot with attribution

2026-07-13 12:12:13 +08:00
commit 0446c45d8e
898 changed files with 328024 additions and 0 deletions
@@ -0,0 +1,29 @@
+import asyncio
+from crawl4ai import (
+    AsyncWebCrawler,
+    BrowserConfig,
+    CrawlerRunConfig,
+    DefaultMarkdownGenerator,
+    PruningContentFilter,
+    CrawlResult
+)
+
+
+async def main():
+    browser_config = BrowserConfig(
+        headless=False,
+        verbose=True,
+    )
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        crawler_config = CrawlerRunConfig(
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=PruningContentFilter()
+            ),
+        )
+        result: CrawlResult = await crawler.arun(
+            url="https://www.helloworld.org", config=crawler_config
+        )
+        print(result.markdown.raw_markdown[:500])
+
+if __name__ == "__main__":
+    asyncio.run(main())