Web page
Your web page
Paste your web page. Nothing to upload.
←web page
Make a blog post
Turn a web page into a blog post
Reading three articles and writing a fourth is the job. Rewriting one of them is not.
Free to try, no card. Your web page opens in Ancher.
Readable content, declutteredTitle, author, published dateOutbound links
Kept in parts
Every one of these stays separately addressable instead of collapsing into one block of text.
The angleOpeningBody sectionsSpecifics and numbers
Blog post
A publishable article with its own argument, not a transcript rearranged into paragraphs.
A post built from a single source is that source with different adjectives, and readers can tell. Ancher pulls the readable body from every URL you paste, keeps each one's author and publication date, and follows what they link to — so the draft can be built on where the sources disagree, which is the only place a new post has anything to add.
The honest version
What a writer links to says more than what they claim
Outbound links are the part of an article that a text extractor throws away and a careful reader uses first. They show which sources a writer trusts, which claims they were unwilling to make in their own voice, and where several articles are quietly leaning on the same one. Ancher keeps them, so a draft can cite the origin instead of the third retelling.
One screen of one page, at fig. 2, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
Adoption has grown sharply across the sector, according to recent industry figures
Chart in the article body — not readThe specific never reaches the draft
Blog post
Chart in the article body
Survey n=140, self-selected
from fig. 2
Lands in the draft, with its timecode
- Every claim carries the URL, the author and the publication date it came from.
- Outbound links are preserved, so a chain of three articles citing each other is visible as a chain.
- Charts and diagrams in the body are kept, and they are usually the evidence the prose is only describing.
What comes out
Blog post, section by section
A publishable article with its own argument, not a transcript rearranged into paragraphs.
The angle
Your argument, which has to be something none of the sources already said.
Opening
An opening built on the tension between sources rather than on a definition.
Body sections
Sections organised by question, with each source appearing where it is relevant.
Specifics and numbers
Figures with the page they came from and the date that page was published.
Sources and credit
Every URL, its author and its date, with what each contributed.
Web-pages-to-blog-post prompt
The link on its own gets a summary. This is the instruction that produces the 5 sections above, in that order, with the rules that keep them honest. Paste it with your web page — in Ancher, or in whatever assistant you already use.
Write a blog post from these URLs. First identify where the sources disagree and build the angle from that rather than from what they all say. Open on the tension. Organise the body by question, not by source. Attach the URL, author and publication date to every figure you use, note where several sources are citing the same original, and list all sources at the end with what each contributed.
The detail, if you want it
How each part of a web page becomes a section
| From the web page | Into | Why |
|---|---|---|
| Many pages in one collection | The angle | An angle needs at least three pages, because a position is only interesting once you can see what it is a position against. |
| Outbound links | Sources and credit | Following what an article links to is how you find out whether four write-ups are four sources or one source repeated. |
| Title, author, published date | Specifics and numbers | A publication date is what stops a figure from 2019 being presented as the current state of anything. |
| Inline images | Specifics and numbers | The chart in an article usually carries the sample size and caveats the paragraph around it leaves out. |
| Readable content, decluttered | Body sections | Navigation, promo boxes and cookie banners are dropped, so the draft is built from the article rather than from the page. |
Everything Ancher keeps from a web page
Readable content, decluttered
Navigation, ads and cookie banners are dropped, so the collection holds the article rather than the page.
Title, author, published date
A date is what stops a three-year-old post from being read as current.
Outbound links
What a writer links to repeatedly reveals the sources they actually trust.
Inline images
Charts and diagrams in an article are usually the evidence the prose is describing.
Many pages in one collection
A single page is an anecdote; the value of this route appears once several are compared.
The four steps
- Add the web page. Paste any URL. Ancher fetches the readable content as clean markdown and keeps the title, author, publication date and outbound links — this is the route for articles, newsletters, forum threads and documentation.
- Nothing gets flattened. Readable content, decluttered, title, author, published date, outbound links, inline images, many pages in one collection stay separately addressable instead of collapsing into one block of text.
- Ask for a blog post. Ancher fills the angle, opening, body sections, specifics and numbers, sources and credit using the mapping above, not a generic summary pass.
- Check it before you use it. Every specific keeps a link back to where it came from in the web page, so a claim can be verified without reopening the source.
Where this goes wrong
- Building from one URL produces a rewrite. Three or more sources is what makes the difference between synthesis and paraphrase.
- Undated pages are common and dangerous. If a claim cannot be dated, it should not be presented as current.
- Reading an article does not transfer the right to reproduce it. Quote briefly, attribute clearly, and link to the original.
Questions people ask
How many URLs should I paste in?
Three to six for a post with an argument. One gives you a summary with better formatting; several let you build on the places where the sources contradict each other, which is where a new piece earns its existence.
Does it keep the links inside the articles?
Yes, and they are among the most useful things it keeps. They reveal whether apparently independent sources are all citing the same original, which changes how much weight a claim deserves.
What about paywalled sources?
They return very little, usually the headline and a teaser. If a source matters, read it yourself and paste in a page you can actually access, because a draft built on a teaser is built on nothing.
Bring your own web pages
Everything you save lives in one workspace, so the blog post is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a web page? The same blog post also comes from YouTube video, PDF, X thread.