Crawl4AI: Content Extractor icon

Crawl4AI: Content Extractor

Извлечение структурированных данных с помощью CSS селекторов, LLM или JSON схем

Crawl4AI: Content Extractor

AI-generated

Summary

Extract structured content from a web page via Crawl4AI. Supports CSS selector, LLM instruction, or JSON schema-based extraction methods.

Inputs

None.

Output shape

array

Each input row produces one result object with url, success, extracted_content, markdown, and optional error.

Examples

Example 1: CSS extraction

Set extractionType to css and provide a cssSchema JSON with baseSelector and fields.

Example 2: LLM extraction

Set extractionType to llm, provide llmInstruction, optionally llmSchema and llmTemperature.

Example 3: JSON Schema extraction

Set extractionType to jsonSchema and provide a jsonSchema JSON.

Discussion