Add Async Version, JsonCss Extrator

2024-09-03 01:27:00 +08:00
parent 3116f95c1a
commit c37614cbc8
17 changed files with 1922 additions and 2 deletions
--- a/crawl4ai/web_crawler.py
+++ b/crawl4ai/web_crawler.py
@@ -122,7 +122,7 @@ class WebCrawler:
                if not isinstance(chunking_strategy, ChunkingStrategy):
                    raise ValueError("Unsupported chunking strategy")
                
-                word_count_threshold = max(word_count_threshold, 0)
+                word_count_threshold = max(word_count_threshold, MIN_WORD_THRESHOLD)

                cached = None
                screenshot_data = None