> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lyzr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Parse Website

> Crawl websites and parse content based on the provided URLs and crawl settings.



## OpenAPI

````yaml post /parse/website/
openapi: 3.0.3
info:
  title: Lyzr Knowledge Base - Parse Website
  version: 1.0.0
  description: Crawl and parse content from website URLs, preparing it for a RAG system.
servers:
  - url: https://rag-prod.studio.lyzr.ai/v3
security: []
paths:
  /parse/website/:
    post:
      summary: Parse Website
      description: >-
        Crawl websites and parse content based on the provided URLs and crawl
        settings.
      operationId: parseWebsite
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - urls
                - source
                - max_crawl_pages
                - max_crawl_depth
                - dynamic_content_wait_secs
                - actor
                - crawler_type
                - chunk_size
                - chunk_overlap
              properties:
                urls:
                  type: array
                  items:
                    type: string
                  description: List of website URLs to crawl
                  example:
                    - string
                source:
                  type: string
                  description: Data source identifier
                  example: website
                max_crawl_pages:
                  type: integer
                  description: Maximum number of pages to crawl
                  example: 1
                max_crawl_depth:
                  type: integer
                  description: Maximum crawl depth
                  example: 0
                dynamic_content_wait_secs:
                  type: integer
                  description: Time to wait for dynamic content to load (in seconds)
                  example: 5
                actor:
                  type: string
                  description: Apify actor used for crawling
                  example: apify/website-content-crawler
                crawler_type:
                  type: string
                  description: Type of crawler used
                  example: cheerio
                chunk_size:
                  type: integer
                  description: Size of the chunks for text splitting
                  example: 1000
                chunk_overlap:
                  type: integer
                  description: Overlap between consecutive text chunks
                  example: 100
      responses:
        '200':
          description: Website successfully parsed and documents returned
          content:
            application/json:
              schema:
                type: object
                properties:
                  documents:
                    type: array
                    description: List of parsed documents
                    example: []
        '422':
          description: Validation Error - Input format or missing fields
          content:
            application/json:
              schema:
                type: object
                properties:
                  detail:
                    type: array
                    items:
                      type: object
                      properties:
                        loc:
                          type: array
                          items:
                            oneOf:
                              - type: string
                              - type: integer
                        msg:
                          type: string
                        type:
                          type: string
      security:
        - ApiKeyAuth: []
components:
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key

````