The scrape URL node allows you to scrape content from a provided URL.

Node Inputs

  1. URL: The URL of the webpage you want scraped
    • Type: Text

Node Parameters

On the face of the node:

  1. Provider: The provider you want to use for scraping. The available providers are: Default (Combination of multiple providers), Jina and Apify.
  2. Recursive: This will enable the recursive scraping of URLs that have the same base URL. For example, https://vectorshift.ai/ and https://vectorshift.ai/enterprise all have the same based URL of https://vectorshift.ai/.
  3. URL Limit (if Recursive is set to true): The maximum limit for number URLs to scrape in recursion.

In the gear:

  1. Use Personal Api Key: This allows you to enter an API key (note APIFY requires API key).
  2. AI Enhance Content: Content from the website will be passed to an LLM to clean it up.

Node Outputs

  1. Content: The raw text from the website
    • Type: Text
    • Example usage: {{url_loader_0.content}}

Considerations

  • Click on the “+” button on the right of the node to create and connect the node to a semantic search node to enable semantic search on the content.
  • Do not share your API key with someone that you do not trust.

Example

The below example is a pipeline which answers questions about on the contents of a website (example is with VectorShift’s website).

  • Input Node: The query about the website.
  • Text Node: The URL for the website.
  • Scrape URL node: Scrape the website URL
    • URL: {{text_0.text}}
  • Semantic Search Node: Find semantically similar chunks to a question (input node) based on a website (Scrape URL node).
    • Search Query: {{input_0.text}}
    • Documents for Search: {{url_loader_0.content}}
  • LLM Node: Answer a user query (input node) based on relevant information (semantic search node).
    • Prompt: {{input_0.text}} and {{semantic_search_0.chunks}}
  • Output Node: Display the LLM’s response.
    • Output: {{openai_0.response}}