mirror of
https://github.com/unclecode/crawl4ai.git
synced 2025-12-09 17:40:49 +00:00
91a5fea11f
Implements a full-featured CLI for Crawl4AI with the following capabilities: - Basic and advanced web crawling - Configuration management via YAML/JSON files - Multiple extraction strategies (CSS, XPath, LLM) - Content filtering and optimization - Interactive Q&A capabilities - Various output formats - Comprehensive documentation and examples Also includes: - Home directory setup for configuration and cache - Environment variable support for API tokens - Test suite for CLI functionality
13 lines
302 B
YAML
13 lines
302 B
YAML
cache_mode: "bypass"
|
|
wait_until: "networkidle"
|
|
page_timeout: 30000
|
|
delay_before_return_html: 0.5
|
|
word_count_threshold: 100
|
|
scan_full_page: true
|
|
scroll_delay: 0.3
|
|
process_iframes: false
|
|
remove_overlay_elements: true
|
|
magic: true
|
|
verbose: true
|
|
exclude_external_links: true
|
|
exclude_social_media_links: true |