# Scrape Web Page Action **URL:** \ **Category:** Actions\ **Created:** [May 20, 2025, 7:01pm UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857 "2025-05-20T19:01:48Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![thomasumstattd](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/thomasumstattd/32/2305_2.png) [@thomasumstattd](https://community.pickaxe.co/u/thomasumstattd)\ **Post date:** [May 20, 2025, 7:01pm UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857/1 "2025-05-20T19:01:48Z")
I am trying to build a tool that reviews web pages and gives feedback for improvement. I thought it was working with Claude 3.7 but one of my users reported that another website was coming up when he put his URL in. His site is is new and the website review tool I built was relying on Claude’s knowledge, not a scape of the website. I tried the same thing with Gemini with the same results. Is there an action that can scrape a single web page? ---
**Author:** ![thomasumstattd](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/thomasumstattd/32/2305_2.png) [@thomasumstattd](https://community.pickaxe.co/u/thomasumstattd)\ **Post date:** [August 5, 2025, 5:44pm UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857/2 "2025-08-05T17:44:20Z")
Pickaxe has a built in scraper if you toggle on “allow users to upload files” this will add a field where you can add a single page to scrape. ---
**Author:** ![Ned.Malki](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ned.malki/32/5918_2.png) [@Ned.Malki](https://community.pickaxe.co/u/Ned.Malki)\ **Post date:** [August 5, 2025, 6:50pm UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857/3 "2025-08-05T18:50:00Z")
@thomasumstattd check my post on this here: > [@How to implement a "deep research" mode for a Pickaxe?](https://community.pickaxe.co/t/how-to-implement-a-deep-research-mode-for-a-pickaxe/6280/4): > > @stephenbdiaz, The easiest way to implement deep research in your Pickaxe is by: Running an MCP server using a token from [Make.com](http://Make.com) Go to Google AI Studio and get a Gemini 2.5 Pro API key. Create a scenario in [Make.com](http://Make.com) with an HTTP module and add your Gemini API key. Inform your Pickaxe system prompt of when it should trigger the MCP server. An alternative route: Create a [Make.com](http://Make.com) scenario running a Perplexity Search module - Model: Sonar/Sonar-Pro. Hope that helps! Perplexity would be the easiest to implement. ---
**Author:** ![fractional\_breakthro](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/fractional_breakthro/32/4034_2.png) [@fractional\_breakthro](https://community.pickaxe.co/u/fractional_breakthro)\ **Post date:** [August 7, 2025, 3:25am UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857/4 "2025-08-07T03:25:41Z")
@Ned.Malki Would this return the searched data back to the pickaxe or simply allow for the scraped data to be passed down an automation chain though [Make.com](http://Make.com) such as sending an email with collected data to the user if they provided an email address. Pickaxe \> [Make.com](http://Make.com) \> Perplexity \> Gmail send email to user Basically just using Pickaxe like branded chat access to other tools. Thanks for your feedback ---
**Author:** ![Ned.Malki](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ned.malki/32/5918_2.png) [@Ned.Malki](https://community.pickaxe.co/u/Ned.Malki)\ **Post date:** [August 7, 2025, 8:24am UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857/5 "2025-08-07T08:24:11Z")
@fractional_breakthro, yes, the searched data will be fed back into the Pickaxe. But you have to control how it is fed back into the studio knowledge base using the Studio APIs ![image](https://canada1.discourse-cdn.com/flex004/uploads/pickaxeproject/original/2X/a/aaea1e155226c11cbd79ac76a6fb168f0a3b9382.png) ---
**Author:** ![Beckett](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/beckett/32/2046_2.png) [@Beckett](https://community.pickaxe.co/u/Beckett)\ **Post date:** [August 7, 2025, 6:05pm UTC](https://community.pickaxe.co/t/scrape-web-page-action/5857/6 "2025-08-07T18:05:56Z")
Hey @thomasumstattd I think the easiest way would be to add a custom MCP. You can use something like [Smithery](https://smithery.ai) to find some “actions” you could use. A quick search revealed [this one](https://smithery.ai/server/@browserbasehq/mcp-browserbase). Take that JSON code and paste into pickaxe. You can find a whole video about Pickaxe MCP’s [here](https://community.pickaxe.co/t/new-tutorial-connect-your-pickaxes-to-anything-with-mcps-and-apis/6308). Let me know if you have any other questions!