From a8563194994e4c6a06f8e7d174b8be077e2941bf Mon Sep 17 00:00:00 2001 From: UncleCode Date: Thu, 16 May 2024 22:06:33 +0800 Subject: [PATCH] Update web_crawler.py Set NoExtractionStrategy for FetchPages --- crawl4ai/web_crawler.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crawl4ai/web_crawler.py b/crawl4ai/web_crawler.py index 311ae351..4604279e 100644 --- a/crawl4ai/web_crawler.py +++ b/crawl4ai/web_crawler.py @@ -184,7 +184,7 @@ class WebCrawler: extract_blocks_flag: bool = True, word_count_threshold=MIN_WORD_THRESHOLD, use_cached_html: bool = False, - extraction_strategy: ExtractionStrategy = LLMExtractionStrategy(), + extraction_strategy: ExtractionStrategy = NoExtractionStrategy(), chunking_strategy: ChunkingStrategy = RegexChunking(), **kwargs, ) -> List[CrawlResult]: