Perplexity AI Scraper avatar

Perplexity AI Scraper

Pricing

from $9.00 / 1,000 results

Go to Apify Store
Perplexity AI Scraper

Perplexity AI Scraper

Asks Perplexity AI questions and returns the answer with its cited sources.

Pricing

from $9.00 / 1,000 results

Rating

0.0

(0)

Developer

Anyx Solutions

Anyx Solutions

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

2 days ago

Last modified

Share

banner

Perplexity Scraper

Ask Perplexity AI a question and get the answer with its cited sources.

Give this scraper a list of questions and it returns Perplexity's AI answer for each, along with the sources it cited — full source URLs, their domains, and the cited-domain list. It waits for each answer to finish generating, expands the sources panel, and returns clean structured JSON. It suits research automation, source discovery, competitive and market monitoring, and feeding AI-answer data with citations into your own pipelines.

⚡ Quick start

{
"queries": [
"When was OpenAI founded and by whom?",
"What are the latest James Webb telescope discoveries?"
],
"maxItems": 10
}

🧩 Input

FieldTypeRequiredDefaultDescription
queriesarrayyes*Questions to ask Perplexity. One entry per question.
startUrlsarraynoPerplexity search URLs to scrape directly, e.g. https://www.perplexity.ai/search?q=example. Use instead of queries for full control.
maxItemsintegeryes10Maximum number of questions to answer in this run.
proxyConfigurationobjectnoResidentialProxy settings. Perplexity sits behind Cloudflare, so residential proxies are the default.

* Provide either queries or startUrls.

📤 Output

Each question becomes one dataset item: the answer text, the list of cited sources with their URLs and domains, and the flat list of cited domains. Perplexity's answer is an AI synthesis, so treat answer as a summary and use the sources for anything you need to verify or process further. Fields a question does not produce are returned as null or an empty array rather than omitted.

Fields

FieldTypeDescription
querystringThe question that was asked.
urlstringThe Perplexity thread URL for the answer.
answerstringPerplexity's AI answer text.
sourcesarrayCited sources, each { url, domain, snippet }.
citedDomainsarrayFlat list of unique domains Perplexity cited.
sourceCountnumberNumber of sources returned.
fetchedAtstringWhen the answer was scraped, ISO 8601.

💡 Use cases

  • Automate research on a topic and keep the sources Perplexity cited.
  • Discover authoritative pages for a company or subject, then fetch them for full detail.
  • Monitor how questions about a brand or product are answered over time.
  • Feed AI answers with citations into knowledge bases and LLM pipelines.
  • Collect a domain list of what Perplexity considers credible for a topic.

❓ FAQ

  • Do I need a proxy? Yes. Perplexity sits behind Cloudflare and blocks datacenter traffic, so residential proxies are the default and strongly recommended.
  • Are the answers reliable? The answer is an AI synthesis and can be incomplete or wrong, so use it as a summary. The sources are the pages Perplexity cited — use those to verify or to fetch full content.
  • Why are source snippets a mix of title and description? They are taken from the source cards as Perplexity displays them. The url and domain are always clean; fetch the page itself for a precise title and body.
  • What happens if Perplexity shows a Cloudflare challenge? The scraper detects it, retires that session, and retries on a fresh one. If every attempt is blocked it fails with a clear error rather than returning the challenge page as an answer.
  • Can I control the AI model or mode? No. It uses Perplexity's default search answer, the same one an anonymous visitor sees.

🔗 More scrapers by Anyx

🤝 Anyx Solutions

We build custom scrapers and data-extraction pipelines.

🖼 Image credit

Image credit: www.perplexity.ai