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

crawl4ai/async_webcrawler.py

@@ -477,7 +477,7 @@ class AsyncWebCrawler:
                 word_count_threshold=word_count_threshold,
                 css_selector=css_selector,
                 only_text=kwargs.pop("only_text", False),
-                image_description_min_word_threshold=kwargs.get(
+                image_description_min_word_threshold=kwargs.pop(
                     "image_description_min_word_threshold", IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD
                 ),
                 content_filter = content_filter,

crawl4ai/crawler_strategy.py

@@ -283,7 +283,7 @@ class LocalSeleniumCrawlerStrategy(CrawlerStrategy):
                 print(f"[LOG] ✅ Crawled {url} successfully!")
             
             return html
-        except InvalidArgumentException:
+        except InvalidArgumentException as e:
             if not hasattr(e, 'msg'):
                 e.msg = sanitize_input_encode(str(e))
             raise InvalidArgumentException(f"Failed to crawl {url}: {e.msg}")