--- title: "News posts summarized by AI each week and saved to NocoDB" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/f86728df-dfea-4f8d-9b4b-b6f88c82d7ea" updated: "2026-11-12" --- # News posts summarized by AI each week and saved to NocoDB > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that reads a news page with no feed once a week. It keeps the posts of the last 7 days, has OpenAI summarize each one, and saves a row for each in NocoDB. News posts summarized by AI each week and saved to NocoDB is an n8n workflow in the Research category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow reads a news page that has no feed. Every week it collects the links and the dates of the posts, keeps the ones from the last 7 days, and fetches each one. An OpenAI model writes a short summary and three keywords for every post. Each post then lands as a row in a NocoDB table. Eighteen nodes do the work, beside eighteen sticky notes. ### Who it suits Researchers, analysts and small teams who follow a few news pages and want a running log of what they publish. It also suits anyone learning how to read a page and process each post with a model. Skip it if the site’s terms do not let a program read its pages. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Market research | Analysts | Track what competitors announce | An analyst logs each announcement from a rival’s news page as a row with its summary. | | Communications | PR teams | Watch industry news pages that offer no feed | A PR lead reads one table of summaries each Monday. | | Product | Product managers | Keep a database of vendor announcements | A manager filters the table by keyword before a roadmap meeting. | | Education | Students | Build a dataset of news posts for a project | A student collects a month of posts with their summaries. | You need some n8n and a little CSS: import a file, set an address, find four selectors and connect two accounts. Nothing in the file states a setup time. ### Where to use it Any n8n that can reach your news page, NocoDB and OpenAI will run it. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Another page: change the address and the selectors, and nothing else - Another output: swap \`NocoDB news database\` for an email, a spreadsheet or another database ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Three things cover every step: your page and its selectors, a NocoDB table and an OpenAI key. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | A news page | One that lists posts with a link and a date, and that you may read with a program | | NocoDB | A table with the columns News\_Source, Title, Date, Link, Summary and Keywords, and an API token | | OpenAI | An API key for the two summary nodes | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. In `Retrieve the web page for further processsing`, replace `` with the address of your news page. 3. In your browser, right click a post link, choose Inspect and copy a selector that matches every post link. Put it in `Extract the HTML with the right css class`. Do the same for the dates in `Extract date`. 4. Open one post and copy a selector for its title and one for its text. Put them in `Extract individual posts`. 5. If your links are relative, put the site’s address in front in `HTTP Request1`. 6. Add a NocoDB credential. In `NocoDB news database`, pick your base and table, and replace `` with the name of the site. 7. Add an OpenAI credential and select it in `Summary` and `Keywords`. 8. Run the workflow once by hand, check the rows in NocoDB, and then publish it. ### How to use it Publish the workflow and leave it running. Each week it adds the new posts to your table. Read the first rows to check the selectors. What to change for a different result | To change | Where | | --- | --- | | How far back it looks | The number in the code of \`Select posts of last 7 days\` | | The day and time | The options of \`Schedule Trigger each week\` | | What the model writes | The prompts in \`Summary\` and \`Keywords\` | | The columns | The field values in \`NocoDB news database\` | | The output | Swap \`NocoDB news database\` for another node | ### Example A news page lists five posts, and two are from the last 7 days. The workflow fetches those two posts. For each one, OpenAI writes a summary of under 70 words and three keywords. Two rows appear in NocoDB, each with the title, the date, the link, the summary and the keywords. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. The first half finds the posts. The second half summarizes them and saves them. A CSS selector is a short pattern that tells n8n which part of a page to copy. **For experts.** The list page is read twice, once for the links and once for the dates, and the two lists are joined by position. The selectors must return the same number of items in the same order. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`Extract the HTML with the right css class\` | An HTML node that returns the \`href\` of every match as an array | \`Create single link items\` turns the array into one item for each link | | \`Merge date \& links\` | A Merge node 2.1 that combines the two lists by position | A missing date shifts every pair after it | | \`Select posts of last 7 days\` | A Code node that keeps the items whose \`Date\` falls in the last 7 days | A date that JavaScript cannot read drops the item | | \`Summary\` and \`Keywords\` | Two OpenAI chat nodes on \`gpt-5.6-sol\` | They run side by side on the same post text | | \`NocoDB news database\` | A NocoDB node 2 that creates a row | Its API Version is v0.200.0 Onwards | ### Good to know It needs your own page and selectors. - Your page: the original copy was written for one company’s news page that answers 404 today, read on 12 November 2026. Mindket’s copy leaves the address and the four selectors for you - A repair: the date filter went back 70 days under a name that says 7 days, on a weekly schedule. Mindket’s copy goes back 7 days - Politeness: it reads one list page and one page for each new post, once a week. Check the site’s terms and robots rules before you use it on a site you do not own - Models: the original copy named \`gpt-4-1106-preview\`, which OpenAI shut down on 23 October 2026. OpenAI’s deprecations page, read on 12 November 2026, names \`gpt-5.6-sol\` as the replacement, so Mindket’s copy uses it - Billing: each post costs two OpenAI calls, one for the summary and one for the keywords - Your data: the text of each kept post goes to OpenAI, and the results go to your NocoDB - NocoDB: Mindket set the node’s API Version to v0.200.0 Onwards. If your NocoDB is older, set it back - Credentials: the JSON holds none, and the ids in it are placeholders ## README ```markdown # News posts summarized by AI each week and saved to NocoDB An n8n workflow for a news page that has no RSS feed. Once a week it fetches the page, collects the link and the date of every post, and keeps the posts from the last 7 days. It fetches each of those posts, and an OpenAI model writes a short summary and three keywords for it. Each post lands as a row in a NocoDB table. The file is a pattern, not a ready-made feed. You give it the address of your own news page and four CSS selectors, so it knows where the links, dates, titles and texts sit. ## What is inside - `workflow.json`: the workflow as n8n exports it, 18 nodes beside 18 sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy Mindket repaired and cleaned the copy: - The original copy was written for one company's news page. That page answers 404 today (read on 12 November 2026), so its address and its four CSS selectors are now the placeholders ``, ``, ``, `` and ``. The source name written to NocoDB is now ``. - The date filter went back 70 days, although the node's name says 7 days and the schedule runs weekly. Mindket's copy goes back 7 days. - Both OpenAI nodes named `gpt-4-1106-preview`, which OpenAI shut down on 23 October 2026. OpenAI's deprecations page, read on 12 November 2026, names `gpt-5.6-sol` as the replacement, so Mindket's copy uses it. The nodes are n8n's older OpenAI node, which n8n hides from its node list but still runs. They send no temperature or token limit, so nothing else needed to change. - The NocoDB base and table ids were the previous owner's. They are now `` and ``, and the node's API Version is set to v0.200.0 Onwards, the newest of the three it offers. - Six sticky notes were reworded, and the links and contact details in them are gone. - No credential is inside. ## Before you start - An n8n instance, on n8n Cloud or your own server. - A news page that lists its posts with a link and a date for each, and that you are allowed to read with a program. Read its terms first. - A NocoDB table with six columns: `News_Source`, `Title`, `Date`, `Link`, `Summary` and `Keywords`, and a NocoDB API token. - An OpenAI API key. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. In `Retrieve the web page for further processsing`, replace `` with the address of your news page. 3. Open the news page in a browser, right click a post link, choose Inspect and copy a CSS selector that matches every post link. Put it in `Extract the HTML with the right css class`. Do the same for the dates in `Extract date`, with one date for each post and in the same order as the links. 4. Open one post, and copy a selector for its title and one for its text. Put them in `Extract individual posts`. 5. If the links on your page are relative, such as `/news/post-1`, put the site's address in front in the address of `HTTP Request1`. 6. Add a NocoDB credential with your API token. In `NocoDB news database`, pick your base and table in place of the two placeholders, and replace `` with the name of the site. 7. Add an OpenAI credential and select it in `Summary` and `Keywords`. 8. Run the workflow once by hand and check the rows in NocoDB. Then publish it. ## How a run goes 1. `Schedule Trigger each week` starts a run every week on Wednesday at 4:32, in the time zone of your n8n. 2. `Retrieve the web page for further processsing` fetches your page as text. 3. `Extract the HTML with the right css class` picks the post links, and `Create single link items` turns the list into one item for each link, in a field named `Link`. 4. `Extract date` picks the dates, and `Create single date items` makes one item for each date, in a field named `Date`. 5. `Merge date & links` joins the two lists by position, and `Select posts of last 7 days` keeps the items whose `Date` falls in the last 7 days. A date that JavaScript cannot read drops the item. 6. `HTTP Request1` fetches each kept post, and `Extract individual posts` picks its `title` and its `content`. `Merge Content with Date & Link` adds the date and the link back. 7. `Summary` asks OpenAI for a summary of under 70 words. `Keywords` asks for the three most important technical keywords. `Rename Summary` and `Rename keywords` keep one field each, and `Merge` joins them. 8. `Merge ChatGPT output with Date & Link` joins them with the title, date and link, and `NocoDB news database` creates one row for each post. ## Change the look - How far back it looks: the number in the code of `Select posts of last 7 days`. Keep it equal to the schedule. - The day and time: the options of `Schedule Trigger each week`. - What the model writes: the prompts in `Summary` and `Keywords`, such as a different length or more keywords. - The columns: the six field values in `NocoDB news database`. Any other output works, such as an email or a spreadsheet. ## Good to know - Nothing runs until you fill in the address and the selectors. Each site is built differently, so expect to adjust them. - It reads one list page and one page for each new post, once a week. Check the site's terms and its robots rules before you use it on a site you do not own. - Each post costs two OpenAI calls, one for the summary and one for the keywords. - The text of every kept post goes to OpenAI, and the results go to your NocoDB. - If your NocoDB is older than v0.200.0, set API Version in `NocoDB news database` back to the older choice. - The JSON holds no credential. ``` ## What is in it 3 files, 28 KB, downloaded as a zip. ```text NOTICE.md 680 B README.md 6 KB workflow.json 22 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 18 steps, starting on a schedule - AI: 2 steps call an AI model: Summary and Keywords - Sign-ins: Signs in to: NocoDB - API keys: No API key is left in the file - Step types: Mindket’s checker reads 8 of its 9 step types. It does not read: Html ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/f86728df-dfea-4f8d-9b4b-b6f88c82d7ea) - [Its page on Mindket](https://mindket.com/p/f86728df-dfea-4f8d-9b4b-b6f88c82d7ea)