n8n News Monitoring With Screenshots: News Search + Website Screenshot Workflow
n8n News Monitoring With Screenshots: News Search + Website Screenshot Workflow A text digest tells you what was published. Sometimes you also want to see it: the headline as it ran, a competitor's pricing page on the day it changed, the launch page before it gets edited. That's a screenshot job, and until now it meant running your own headless browser next to n8n. Version 0.7 of the…
n8n now offers a new community node called AgentSearch, which enables users to perform news monitoring and take website screenshots. With this tool, it's possible to build a workflow that fetches recent articles on a specific topic, along with their headlines, URLs, snippets, source domains, and publish dates. Each article can then be captured as a screenshot using a real headless browser, returning the image in PNG or JPEG format.
The guide provides a step-by-step process to set up a daily news with screenshots workflow and a second pattern for visually monitoring any page. The first component involves importing the AgentSearch node into n8n (self-hosted or Cloud) and configuring it with a wallet API credential. This wallet is used solely for n8n and requires the purchase of USDC on Base to cover the per-call costs.
Once the wallet is set up, the news search operation can be configured to retrieve recent articles related to a given topic. Users can specify the maximum number of results, the freshness filter for the articles (e.g., past day), and other optional filters such as date range, country, language, and specific domains to include or exclude.
The resulting articles are then split into individual items using the Split Out node, allowing for a more manageable workflow when processing each article separately. Users can further limit the number of items processed by using the Limit node if they only want to capture screenshots of the top articles.
For the screenshot operation, users can specify the URL of the article they wish to capture, along with the desired image format (PNG or JPEG) and viewport settings. The screenshot is then stored as a binary in the data property of the output item, along with additional metadata such as the final URL, page title, status code, image dimensions, and payment details.
This information can be extracted and utilized for various purposes, such as sending screenshots via Slack, email, Google Drive, or using them as input for AI vision models to generate summaries of the webpage content.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
