Dumpling AI icon

Dumpling AI

Interact with Dumpling AI APIs (data, web scraping, document conversion, AI, etc.)
Join our community

Actions7

Overview

The node provides an interface to perform search queries using the Dumpling AI Data API. It allows users to execute customized searches with options to specify query text, location bias, language, date range, and pagination. Additionally, it supports scraping the content of top search results in various formats (Markdown, HTML, or Screenshot), optionally cleaning the scraped data.

This node is beneficial for scenarios such as:

  • Gathering search result data programmatically for analysis or reporting.
  • Extracting detailed content from top search results for research or content aggregation.
  • Filtering search results by time frame or geographic location to get more relevant data.

Practical examples include:

  • A marketing analyst automating competitor keyword research with location and language filters.
  • A researcher scraping summarized content from top news articles related to a specific topic.
  • A developer building a custom search dashboard that paginates through search results and extracts detailed snippets.

Properties

Name Meaning
Query The search query string to perform on Google.
Country Country code to bias the search location (e.g., "US" for United States).
Location Specific location name to focus the search (e.g., "New York, NY").
Language Language code for the search results (e.g., "en" for English).
Date Range Filter results by date range. Options: Any Time, Past Hour, Past Day, Past Week, Past Month, Past Year.
Page Page number for paginated search results (minimum 1).
Scrape Results Boolean flag indicating whether to scrape the content of the top search results.
Number of Results to Scrape Number of top search results to scrape (1 to 10).
Scrape Format Format for scraped content. Options: Markdown, HTML, Screenshot.
Clean Scraped Content Boolean flag indicating whether the scraped output should be cleaned (e.g., removing ads or clutter).

Output

The node outputs JSON data containing the search results returned by the Dumpling AI Data API. The structure typically includes metadata about the search and an array of individual search result items.

If scraping is enabled, the output will also include the scraped content of the specified number of top results in the chosen format. When the screenshot format is selected, binary data representing images may be included.

Summary of output fields:

  • results: Array of search result objects with details like title, URL, snippet, etc.
  • scrapedContent (optional): Content extracted from top results, formatted as Markdown, HTML, or screenshots.
  • If screenshots are used, binary data fields contain image data corresponding to each scraped result.

Dependencies

  • Requires an API key credential for authenticating with the Dumpling AI service.
  • Network access to https://app.dumplingai.com/api/v1 endpoint.
  • No additional environment variables are explicitly required beyond the API key.

Troubleshooting

  • Common issues:

    • Invalid or missing API key will cause authentication errors.
    • Exceeding rate limits or quota restrictions from the Dumpling AI service.
    • Providing invalid country or language codes may result in no or unexpected results.
    • Requesting to scrape more than 10 results will be rejected due to max limit.

  • Error messages:

    • Authentication failures: Check that the API key credential is correctly configured.
    • Validation errors on input parameters: Ensure all required fields are provided and within allowed ranges.
    • Network errors: Verify internet connectivity and that the Dumpling AI API endpoint is reachable.

  • Resolutions:

    • Double-check API credentials and permissions.
    • Validate input parameters before execution.
    • Reduce the number of results to scrape if hitting limits.
    • Retry after some time if rate-limited.

Links and References

Discussion