The Scenario
You've inherited a content analysis project from someone who left the team three weeks ago. There's a Google Sheet with 40 competitor blog post URLs in column A and a note in the header that says "need full text extracted for keyword analysis." No other instructions.
Your job is to get the text content out of each URL so you can run it through a keyword density tool and feed the findings into an upcoming content strategy deck. The deck is due to the content director by end of week.
The bad version:
- Open URL 1, use your browser's reader mode or dev tools to isolate the article text, copy it, paste it into column B
- Repeat this for 39 more URLs, some of which load slowly, one of which redirects to a gated page that requires a login, and three of which have JavaScript-heavy rendering that breaks the copy
- Realize on Thursday that six of the extracted texts are truncated because you grabbed the preview rather than the full article body, meaning you have to re-do those rows
You're supposed to be doing strategy work. The hours it takes to manually scrape 40 URLs is not something your role was designed to absorb — and every hour you spend on it is an hour that isn't going into the actual analysis.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Google Sheet. It reads the sheet, understands your data layout, and through its built-in Exa integration it can fetch the full text content of each URL in your list and write the extracted text back to the adjacent column.
Read the URLs in column A of my Google Sheet, fetch the full page text for each via Exa, and write the extracted content into column B
What You Get
- Column B fills with the full extracted text of each page
- Pages that Exa couldn't fully render are noted in column C so you know which ones need a manual fallback
- Extracted text is clean — no nav menus, footers, or sidebar content included
- Each row updates independently, so partial completions don't block the rest of the batch
What If the Data Is Not Quite Ready
Some URLs in the list are broken or redirect to gated pages
A handful of the 40 URLs are returning 404s or landing on login pages that block content extraction.
For each URL in column A, try to fetch the full text via Exa and write the result to column B — if Exa returns an error or no content, write "Extraction failed" to column B and the HTTP status code to column C
You want a word count alongside the extracted text
The keyword analysis tool requires a minimum of 500 words per article. You want to flag short articles before sending the batch to the tool.
Fetch the full text for each URL in column A using Exa, write the content to column B, count the words in each extracted text, and write the word count to column C — flag any row where the count is under 500 with "Short" in column D
Some URLs share a domain and you want them deduplicated first
Your URL list was compiled from several sources and has duplicates. Running Exa on duplicates wastes calls and clutters the output.
Before fetching content, check column A for duplicate URLs and mark duplicates with "Duplicate" in column B — then for all non-duplicate rows, use Exa to fetch the full page text and write it to column C
Full pipeline: deduplicate, fetch, count, flag, in one pass
Check column A for duplicate URLs and mark duplicates in column B, then for each unique URL fetch the full page text via Exa and write it to column C, count the words and write to column D, and flag any row with under 500 words as "Too short" in column E
One prompt handles the cleanup and the extraction together.
Try It
Get the 7-day free trial of SheetXAI and open any Google Sheet with a list of URLs you need content from — scraped, inherited, or otherwise — then ask it to fetch the full text for each row via Exa. For related workflows, see how to find similar pages for SEO targeting or build a news digest from a topic list.