AI Scraper icon

AI Scraper

Scrape any Website with just a URL and Data Description using Parsera API (10K+ downloads)

Actions5

Extractor → Parse HTML

AI-generated

Overview

The AI Scraper node with the 'Extractor' resource and 'Parse HTML' operation allows users to extract structured data from raw HTML or text content. It is useful for scenarios where you have HTML content and want to parse and extract specific data fields based on a defined schema or field list. For example, extracting product details, prices, or other information from HTML snippets without needing to scrape a live URL.

Use Case Examples

  1. Extract product names and prices from a block of HTML content.
  2. Parse HTML content from emails or saved web pages to extract structured data.

Properties

Name Meaning
Content Raw HTML or text content to extract data from, required for parsing.
Prompt (Optional) Optional context or general instructions to guide the extraction process.
Columns Input Mode Select how to define columns for extraction: either separate fields or a JSON schema.
Columns Define data fields to extract, each with a name and type, used when 'Fields' mode is selected.
Schema (JSON) Define columns as a JSON object with field names and optional descriptions and types, used when 'JSON' mode is selected.
Mode Extraction mode to balance speed and accuracy or to extract data hidden deeper in HTML structures.

Output

JSON

  • data - Extracted structured data as per the defined schema or fields.

Dependencies

  • Parsera API accessed via an API key credential

Troubleshooting

  • Ensure the HTML content provided in 'Content' is valid and complete for accurate extraction.
  • If extraction results are incomplete or inaccurate, try switching the 'Mode' to 'Precision' for deeper HTML parsing.
  • Verify that the column definitions or JSON schema correctly match the data structure expected in the HTML content.
  • Check API key credentials and network connectivity to the Parsera API endpoint.

Links

Discussion