ManyPI
Turn websites into APIs
489 followers
Turn websites into APIs
489 followers
Convert any website into a clean, type-safe API. Use natural-language or JSON-schema prompts to extract data and get usable JSON output for RAG pipelines, sales, content aggregation, or research.
Interactive
Free Options
Launch Team / Built With
ManyPI
Hi folks,
ManyPI has just launched, and whether it’s praise, criticism, or suggestions for improvement: Share anything that comes to mind. Also, redeem code “PHBONUS” on the billing page to get 40k extra credits. Valid until Xmas. ;)
Best,
Ole
Really Nice. Very useful, and I like the fact it is user initiated, so it may not appear to websites as a bot. I like the clean interface too. How are you handling scraper blockers? And is my assumption correct that it doesn't appear as a bot to websites?
@tade_odunlami That is also what I'm worried about. if that leads to the account be banned, then it would be somewhat counterproductive.
ManyPI
@tade_odunlami @joeyzhang We apply technical measures that reduce the likelihood of automated request detection while enabling controlled web data collection at scale.
ManyPI
@tade_odunlami Thank you for your questions.
We have several technical measures in place to significantly reduce the likelihood of being flagged as a bot. These include fingerprinting, intelligent rate limiting, proxies, and additional safeguards.
So far, we are not aware of ManyPI ever being flagged as a bot by a website. That said, this does not mean it can never happen. We continuously work on keeping ManyPI’s stealth, integrity and reliability top-notch.
DeepTagger
Great idea! What are some of the top use-cases you've found? Also, how do you combat captchas?
ManyPI
@avloss We’ve found ManyPI to be especially useful for researchers, RAG pipelines, and sales teams (e.g., for example, turning new Product Hunt launches into a structured API) - just to name a few. :)
Swytchcode
Amazing.
1. Where are the created APIs hosted or do you let them download it?
What if I need to edit my API manually or connect to db?
Which language is the API generated in?
ManyPI
@chilarai
APIs and scraped data records are stored in EU data centers.
You can edit the API (name, website and JSON schema) by clicking the three dots in the bottom-right corner of the scraper card and selecting “Edit.”
If you need further customization, please let me know. I’d be happy to add it to the roadmap.
The API is JavaScript-based.
ManyPI
@anishsharma Thank you! You're very welcome to give it a try :)
The abstraction layer here is smart - turning web scraping into API calls via NLP is clean. Perfect for data pipelines without maintaining scrapers. Key questions: How's the latency compared to direct scraping? What's your compliance strategy around website terms of service? Also, API pricing model - usage-based or flat? Enterprise buyers will ask about SLAs.
ManyPI
@imraju Thank you for the kind words and questions.
The duration of the scraping process depends heavily on the target website. Simple websites typically take around 5–15 seconds from run initiation to returning structured output data. Larger, data-heavy, or technically challenging websites may take up to 30 seconds to complete. We are continuously working on reducing execution times, as this is one of our main priorities.
We maintain a list of websites that are not allowed to be scraped. During the API creation process, our AI performs a risk assessment based on factors such as the website’s terms and the type of data requested (e.g., personal data). If a request is classified as medium risk, the user must confirm that they have written consent from the website owner to run a ManyPI scraper. If a request is classified as high risk, it is automatically blocked and requires manual review by a team member. In that case, we will request additional documentation (such as written consent) and an e-signature from the user before approving the API.
Regarding pricing, we offer a flat monthly fee that includes a monthly credit allowance. Additional credits can be purchased as add-ons and are valid for one year from the date of purchase.
Nice idea! Is there any chance that Cloudflare will block the scraper?
ManyPI
@zakiah_hashim
So far, we’ve been able to avoid Cloudflare blocks. While a 100% success rate can’t be guaranteed, we’re not aware of any cases where our scraping engines have been blocked by target sites yet. This is thanks to the many sophisticated technical measures we’ve put in place to reliably prevent bot flagging.
@olemai cool. Thanks!
ManyPI
@zakiah_hashim Sure, you're welcome to try our service any time you like. :)