# Reliably reading URL content

**URL:** <https://community.openai.com/t/reliably-reading-url-content/1062488>\
**Category:** API\
**Tags:** web-browsing, url\
**Created:** [December 19, 2024, 5:59pm UTC](https://community.openai.com/t/reliably-reading-url-content/1062488 "2024-12-19T17:59:16Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![deg](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/deg/32/157676_2.png) [@deg](https://community.openai.com/u/deg)\
**Post date:** [December 19, 2024, 5:59pm UTC](https://community.openai.com/t/reliably-reading-url-content/1062488/1 "2024-12-19T17:59:16Z")

</div>

I’m working on a Chrome extension in which I pass the current tab’s URL in my prompt and then query about it.  
I can see that the 4o model can read the URL content, while 4o-mini obviously can’t and hallucinates based on the URL itself.  
The problem is that 4o also sometimes seems to have the same problem. How can I tailor my prompt to minimize the occurrence of this problem?

My prompt already includes text “Do not guess based solely on the name, URL, or external cues; rely strictly on the page contents.” This seems to help a bit, but it is not enough.

---

<div class="post-metadata">

**Author:** ![platypus](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/platypus/32/759972_2.png) [@platypus](https://community.openai.com/u/platypus)\
**Post date:** [December 19, 2024, 6:15pm UTC](https://community.openai.com/t/reliably-reading-url-content/1062488/2 "2024-12-19T18:15:37Z")

</div>

Hi @deg and welcome to the community.

Currently it is not possible to do a web search or URL scrape using the API. So whatever results you have seen, they have been hallucinations or a fluke. Right now the only way to fetch/scrape contents from a URL using the API is if you perform your own web scraping using something like BeautifulSoup or an external service like Apify.

---

<div class="post-metadata">

**Author:** ![deg](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/deg/32/157676_2.png) [@deg](https://community.openai.com/u/deg)\
**Post date:** [January 6, 2025, 10:29am UTC](https://community.openai.com/t/reliably-reading-url-content/1062488/3 "2025-01-06T10:29:04Z")

</div>

Thanks.

It’s scarily impressive how often 4o was able to create plausible brief summaries of a page without seeing anything besides the URl – enough that it had me fooled for a while.

I guess that says something deep and philosophical about how much of what we see in this world is redundant. 🙂