The Scenario
You are a content strategist and someone on your team just dropped 40 competitor blog post URLs into an Excel workbook and said "I need a content matrix by Thursday." You open the workbook. Column A is full of URLs. Columns B through E are empty. The ask: title, author, publish date, and primary topic for each one.
The bad version:
- Open the first URL, find the author byline buried in the header, copy it into column C.
- Scroll to find the publish date, which is formatted differently on every site, copy it into column D.
- Skim the article to decide the primary topic, write something into column E, and repeat for 39 more URLs.
Nobody hired you to build a content spreadsheet by hand. Your job is to decide what to create next — not to spend a Thursday morning as a human web scraper.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It reads the layout and the URLs, and through its built-in Parallel integration it runs an extraction task on each page and writes the structured results back into the workbook.
For every URL in column A of this workbook, use Parallel to extract the page title, author name, publish date, and primary topic. Write the page title into column B, the author name into column C, the publish date into column D, and the primary topic into column E.
What You Get
- Column B filled with the extracted page title from each URL.
- Column C showing the author name as it appears on the page.
- Column D containing the publish date in the format Parallel found it.
- Column E with the primary topic Parallel identified from the page content.
- Rows where Parallel could not extract a field left blank, so the gaps are visible rather than filled with guesses.
What If the Data Is Not Quite Ready
Some URLs redirect or return a 404 — you want to flag those before running extraction
Before running the Parallel extraction, check whether each URL in column A is reachable. Write OK into column F if the URL resolves and Error into column F if it does not. Then run Parallel extraction only on rows where column F is OK, writing title into column B, author into column C, publish date into column D, and primary topic into column E.
Publish dates come back in different formats across sites and you need them normalized to YYYY-MM-DD
For every URL in column A, use Parallel to extract the page title, author, publish date, and primary topic. Write title into column B, author into column C, and primary topic into column E. For column D, normalize the publish date Parallel returns to YYYY-MM-DD format regardless of how the site formatted it.
You only want posts published in the last 12 months
For every URL in column A, use Parallel to extract the page title, author, publish date, and primary topic. Write all four fields into columns B through E. Then check whether the publish date in column D is within the last 12 months. If it is not, write Exclude in column F and leave the row in place.
You want extraction plus topic categorization plus age filtering in one shot
For each URL in column A, run a Parallel extraction task to get title, author, publish date, and primary topic. Write the title into column B, author into column C, publish date (normalized to YYYY-MM-DD) into column D, and primary topic into column E. Classify the topic into one of three categories — SEO, Product, or Thought Leadership — and write the category into column F. Mark any post older than 12 months as Stale in column G.
The pattern: extraction, normalization, classification, and filtering all in one prompt — describe the full pipeline and let SheetXAI coordinate the steps.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook with a column of URLs, then ask it to extract structured metadata from every page using Parallel. You can also look at how to run bulk semantic searches or return to the Parallel overview.