Merge branch 'main' of https://github.com/unclecode/crawl4ai

README.md

@@ -1,4 +1,4 @@
-# 🔥🕷️ Crawl4AI: Crawl Smarter, Faster, Freely. For AI.
+# Crawl4AI: Crawl Smarter, Faster, Freely. For AI.
 
 <a href="https://trendshift.io/repositories/11716" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11716" alt="unclecode%2Fcrawl4ai | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 

crawl4ai/async_webcrawler.py

@@ -132,6 +132,11 @@ class AsyncWebCrawler:
         # if self.verbose:
         #     print(f"{Fore.GREEN}{self.tag_format('READY')} {self.log_icons['READY']} AsyncWebCrawler initialized{Style.RESET_ALL}")
 
+    @asynccontextmanager
+    async def nullcontext(self):
+        """异步空上下文管理器"""
+        yield
+    
     async def arun(
         self,
         url: str,

crawl4ai/extraction_strategy.py

@@ -92,8 +92,10 @@ class LLMExtractionStrategy(ExtractionStrategy):
         
             
     def extract(self, url: str, ix:int, html: str) -> List[Dict[str, Any]]:
-        # print("[LOG] Extracting blocks from URL:", url)
-        print(f"[LOG] Call LLM for {url} - block index: {ix}")
+        if self.verbose:
+            # print("[LOG] Extracting blocks from URL:", url)
+            print(f"[LOG] Call LLM for {url} - block index: {ix}")
+
         variable_values = {
             "URL": url,
             "HTML": escape_json_string(sanitize_html(html)),
@@ -868,4 +870,4 @@ class JsonXPATHExtractionStrategy(ExtractionStrategy):
 
     def run(self, url: str, sections: List[str], *q, **kwargs) -> List[Dict[str, Any]]:
         combined_html = self.DEL.join(sections)
-        return self.extract(url, combined_html, **kwargs)
+        return self.extract(url, combined_html, **kwargs)

docs/md_v2/basic/quickstart.md

@@ -8,7 +8,7 @@ First, let's import the necessary modules and create an instance of `AsyncWebCra
 
 ```python
 import asyncio
-from crawl4ai import AsyncWebCrawler, CasheMode
+from crawl4ai import AsyncWebCrawler, CacheMode
 
 async def main():
     async with AsyncWebCrawler(verbose=True) as crawler: