ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update web_crawler.py

Browse Source 
Set all extraction strategies default to NoExtractionStrategy
This commit is contained in:
UncleCode
2024-05-16 21:58:11 +08:00
committed by GitHub
parent ea16dec587
commit 5ce1dc1622
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
crawl4ai/web_crawler.py
View File

@@ -63,7 +63,7 @@ class WebCrawler:
extract_blocks_flag: bool = True, extract_blocks_flag: bool = True,
word_count_threshold=MIN_WORD_THRESHOLD, word_count_threshold=MIN_WORD_THRESHOLD,
use_cached_html: bool = False, use_cached_html: bool = False,
extraction_strategy: ExtractionStrategy = LLMExtractionStrategy(), extraction_strategy: ExtractionStrategy = NoExtractionStrategy(),
chunking_strategy: ChunkingStrategy = RegexChunking(), chunking_strategy: ChunkingStrategy = RegexChunking(),
**kwargs, **kwargs,
) -> CrawlResult: ) -> CrawlResult: