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

feat(browser): add standalone CDP browser launch and lxml extraction strategy

Browse Source 
Add new features to enhance browser automation and HTML extraction:
- Add CDP browser launch capability with customizable ports and profiles
- Implement JsonLxmlExtractionStrategy for faster HTML parsing
- Add CLI command 'crwl cdp' for launching standalone CDP browsers
- Support connecting to external CDP browsers via URL
- Optimize selector caching and context-sensitive queries

BREAKING CHANGE: LLMConfig import path changed from crawl4ai.types to crawl4ai
This commit is contained in:
UncleCode
2025-03-07 20:55:56 +08:00
parent f78c46446b
commit a68cbb232b
22 changed files with 745 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/md_v2/blog/releases/0.5.0.md
View File

@@ -305,7 +305,7 @@ asyncio.run(main())
```python
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, DefaultMarkdownGenerator
from crawl4ai.content_filter_strategy import LLMContentFilter
from crawl4ai.types import LLMConfig
from crawl4ai import LLMConfig
import asyncio
llm_config = LLMConfig(provider="gemini/gemini-1.5-pro", api_token="env:GEMINI_API_KEY")
@@ -335,7 +335,7 @@ asyncio.run(main())
```python
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai.types import LLMConfig
from crawl4ai import LLMConfig
llm_config = LLMConfig(provider="gemini/gemini-1.5-pro", api_token="env:GEMINI_API_KEY")
@@ -401,7 +401,7 @@ print(schema)
experimentation between different LLM configurations.
```python
from crawl4ai.types import LLMConfig
from crawl4ai import LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig