Read a whole site into spreadsheet rows
Finds the pages on a site from its sitemap or front page, reads each one, and adds a row per page to your sheet.
Apps it connects
Authenticate each one once and the workflow is ready to run.
What it does
Each integration step this workflow runs, in order, what it is for, and the conditions and loops that decide when it runs.
If
discoveredis empty- 1Jina AIRead urlReads the front page for its links when no sitemap is usable, then fetches each page found as clean text.
- 1
- 2Google SheetsGet column valuesReads the first column of your sheet so any page already recorded there is not read again.
For each
pageAddress- 3Jina AIRead url
If
pageTextis not empty- 4OpenAIQuery modelAsks the AI to pull your listed details out of each page's text as one line, writing 'n/a' for anything unstated.
- 5Google SheetsAppend rowAppends one row per page with the page address, its title and each extracted value in the order you listed.
- 4
- 3
How it works
What happens on each run, in plain English.
Give it one web address and run it. Its sitemap is read to find the pages, or, with no usable sitemap, the front page is read once and its links taken instead. Each page found is read as clean text, an AI step pulls out the details you asked for, and one row per page goes into your Google Sheet.
Each appended row holds the page address, the page title, then your details in the order you listed, with 'n/a' wherever the page does not say. Links on those pages are never followed, and every address must sit under the site you named, so a link to another site or a look-alike domain is dropped. One run reads a bounded number of pages, and any address already in the sheet's first column is skipped, so a second run picks up where the last one stopped. A page that will not load is named in the run log and the rest carry on.
Before the first run you need a sheet headed 'Page address', 'Page title' and then your fields in the same order, since the columns cannot be named for you.
You May Also Be Interested In
Turn a list of web pages into spreadsheet rowsReads every page you list, pulls out the details you asked for with AI, and adds one row per page to your sheet.Turn a ChatGPT answer into spreadsheet rowsEvery hour, asks ChatGPT for a list as JSON, splits it into items and adds one row per item to your Google Sheet.
Approve the outline, then the post, then publishTakes the next topic off your content plan, asks you to approve the outline, writes the post to it, and publishes only if you say so.
Ask a question about your sheet, get a chart backWrite a question about a tab of your spreadsheet and get back a chart of the numbers already in it, recorded on your answers tab.
Start from a workflow that already works.
Add "Read a whole site into spreadsheet rows" to your workspace, connect its apps, and make it yours. No credit card required.
Free plan available · No credit card required