crawl4ai icon indicating copy to clipboard operation
crawl4ai copied to clipboard

[MOD]CrawlerRunConfig json to object, (import crawl4ai)need import mo…

Open AlexYY0 opened this issue 6 months ago • 1 comments

…re Object

Summary

Fixes #1056

List of files changed and why

crawl4ai/init.py

How Has This Been Tested?

"crawler_config": {
            "type": "CrawlerRunConfig",
            "params": {
                "chunking_strategy": {
                     "type": "SlidingWindowChunking",
                     "params": {}
                 },
            }
        }

crawler_config json can deserialize to CrawlerRunConfig

Checklist:

  • [x] My code follows the style guidelines of this project
  • [x] I have performed a self-review of my own code
  • [x] I have commented my code, particularly in hard-to-understand areas
  • [x] I have made corresponding changes to the documentation
  • [x] I have added/updated unit tests that prove my fix is effective or that my feature works
  • [x] New and existing unit tests pass locally with my changes

Summary by CodeRabbit

  • New Features

    • Introduced several new chunking strategies, offering more options for processing and segmenting content.
    • Added a new naive JSON LXML extraction strategy for expanded extraction capabilities.
  • Refactor

    • Updated and reorganized the list of available extraction and chunking strategies for improved clarity and usability.

AlexYY0 avatar May 14 '25 15:05 AlexYY0