Back

Scrape a website's text into a document

A Google Doc with the full text of the pages you chose, in page order

AnalystsEAsEveryone
Prompt

Go to [starting URL, e.g. an article, blog, web novel index, or portal home page] and capture [what to grab, e.g. the full article, the 20 most recent posts, or every chapter]. Follow next-page links, chapter lists, pagination, or infinite scroll in order until you reach [stopping point, e.g. the last chapter or 20 posts]. Keep only the main content: titles, headings, body text, lists, and image captions. Skip menus, ads, cookie banners, comments, and related-post widgets. Put everything into a new Google Doc named [doc name, e.g. the site name], in page order, with each page's title as a heading and its source URL underneath. Keep the original wording and formatting; don't summarize or rewrite. If a page needs a login, hits a paywall or captcha, or won't load, skip it and note it. Send me the doc link and a short summary: pages captured, approximate word count, and pages skipped and why.

Works withdocs.google.com