feat(v0.3.6): Add screenshot capture, delayed content, and custom timeouts

- Implement screenshot capture functionality
- Add delayed content retrieval method
- Introduce custom page timeout parameter
- Enhance LLM support with multiple providers
- Improve database schema auto-updates
- Optimize image processing in WebScrappingStrategy
- Update error handling and logging
- Expand examples in quickstart_async.py
This commit is contained in:
unclecode
2024-10-12 13:42:42 +08:00
parent b99d20b725
commit ff3524d9b1
8 changed files with 127 additions and 22 deletions

View File

@@ -202,11 +202,11 @@ class AsyncWebCrawler:
)
if result is None:
raise ValueError(f"Failed to extract content from the website: {url}")
raise ValueError(f"Process HTML, Failed to extract content from the website: {url}")
except InvalidCSSSelectorError as e:
raise ValueError(str(e))
except Exception as e:
raise ValueError(f"Failed to extract content from the website: {url}, error: {str(e)}")
raise ValueError(f"Process HTML, Failed to extract content from the website: {url}, error: {str(e)}")
cleaned_html = sanitize_input_encode(result.get("cleaned_html", ""))
markdown = sanitize_input_encode(result.get("markdown", ""))