The Scenario
The content audit has been on the roadmap for six weeks. You finally have clearance to run it this sprint. Seventy competitor blog post URLs are in column A. Column B is labeled "Body Text." The plan is to run readability scoring and keyword density analysis once the text is in the workbook.
The readability tool is ready. The keyword tool is ready. The text is not in the workbook.
The bad version:
- Open URL 1, select the article body, copy it — but you also accidentally copy the nav, the sidebar, and the related posts section because the page does not have clear content boundaries
- Paste into B2, then spend two minutes manually trimming the garbage from the beginning and end
- Open URL 2, same exercise, but this site has a cookie consent banner that covers 40 percent of the content until you click through it
The analysis you were hired to do is sitting behind seventy rounds of this.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It reads the URL list in column A and through its built-in ZenRows integration — which handles cookie banners, paywalls, and JavaScript rendering — it can extract clean, readable body text from each page and write it into column B.
Extract clean plain-text content from each URL in column A using ZenRows and populate column B with the scraped text in this Excel sheet
What You Get
- Column B: the clean body text of each article, stripped of navigation, ads, and sidebar content
- ZenRows plaintext mode returns human-readable text without HTML markup
- Rows where the page returns a paywall or no readable content get a note in column B rather than a blank
What If the Data Is Not Quite Ready
Some URLs are paywalled and only return a preview paragraph
For each URL in column A, use ZenRows plaintext extraction and write the body text into column B — if the extracted text is fewer than 200 words, flag it in column C as "likely paywalled"
You want word count alongside the extracted text
For each URL in column A, extract clean plaintext using ZenRows and write it into column B — count the words in the extracted text and write the word count into column C
Some pages are in a mix of English and Spanish and you want to identify the language
For each URL in column A, extract plaintext with ZenRows into column B, detect the language of the extracted text, and write the detected language code into column C
Full audit pass — extract text, count words, flag thin content, and note extraction failures
For each URL in column A, use ZenRows plaintext extraction to get the body text into column B — write the word count into column C, flag any article under 300 words as "thin content" in column D, and note any extraction failures in column E
The extraction, the word counting, and the content flagging happen in one pass.
Try It
Open an Excel workbook with your URL list in column A and get the 7-day free trial of SheetXAI. Ask it to extract the readable text from every page into column B. When you need structured fields instead of raw text, see the bulk auto-parse spoke.