Repository files navigation

ThePerplexity Scraper by Oxylabs allows developers to send prompts to Perplexity and automatically collect both AI-generated responses and structured metadata. Instead of just raw HTML, it can also provide results as parsed JSON, website PNG, XHR/Fetch requests, or Markdown output.

You can use theOxylabs’ Web Scraper API with Perplexity for AI content auditing, research tracking, and analyzing SEO performance. It handles dynamic AI-generated content, fully supports real-time SERP extraction, and integrates seamlessly with Oxylabs' global proxy infrastructure, without the need to manage proxies, browsers, or worry about anti-bot systems.

The Perplexity scraper handles the rendering, parsing, and delivery of results in any requested format. You need to provide your prompt, credentials, and a few optional parameters, as shown below.

importjsonimportrequests# API parameters.payload= {'source':'perplexity','prompt':'top 3 smartphones in 2025, compare pricing across US marketplaces','geo_location':'United States','parse':True}# Get a response.response=requests.post('https://realtime.oxylabs.io/v1/queries',auth=('USERNAME','PASSWORD'),json=payload)# Print response to stdout.print(response.json())# Save response to a JSON file.withopen('response.json','w')asfile:json.dump(response.json(),file,indent=2)

More request examples in different programming languages are availablehere.

Note: By default, all requests to Perplexity use JavaScript rendering. Make sure to set a sufficient timeout (e.g. 180s) when using the Realtime integration method.

* Mandatory parameters

Web Scraper API returns either an HTML document or a JSON object of Perplexity scraper output, which contains structured data from the results page.

HTML example:

Structured JSON output snippet:

{"results": [        {"content": {"url":"https://www.perplexity.ai/search/top-3-smartphones-in-2025-comp-wvA0dso7TgW3NpgF8Jd8tg","model":"turbo","top_images": ["url + title"],"top_sources": ["url + title + source"],"prompt_query":"top 3 smartphones in 2025, compare pricing across US marketplaces","answer_results": ["answer in JSON"],"displayed_tabs": ["search","images","sources"                ],"related_queries": ["How do the prices of the top 3 smartphones compare across US marketplaces","What features make the Galaxy S25 Ultra stand out as the best in 2025","Why is the Pixel 9a considered a top budget option despite its lower price","How does the iPhone 16 Pro Max's pricing differ from Samsung and Google models","What factors should I consider when choosing among these top smartphones in 2025"                ],"answer_results_md": ["answer in Markdown"],"parse_status_code":12000            },"created_at":"2025-07-16 12:14:32","updated_at":"2025-07-16 12:15:28","page":1,"url":"https://www.perplexity.ai/search/top-3-smartphones-in-2025-comp-wvA0dso7TgW3NpgF8Jd8tg","job_id":"7351222707934990337","is_render_forced":false,"status_code":200,"parser_type":"perplexity","parser_preset":null        }    ]}

You can find the full output example filehere in this repository.

Alternatively, you can extract the data in the Markdown format for easier data integration workflows involving AI tools.

Structured Perplexity scraper output includes fields such asurl,model,answer_results, and more. The table below breaks down the page elements we parse, along with descriptions, data types, and relevant metadata.

Note: The number of items and fields for a specific result type may vary depending on the submitted prompt.

Along with the main AI response, the Perplexity scraper can return extra data underadditional_results, such as:

• images_results
• sources_results
• shopping_results
• videos_results
• places_results
• hotels_results

These arrays are extracted from the tabs on the original results page and are included only if relevant content is available:

Moreover, theinline_products array contains products that are directly embedded in the response:

1. AI content auditing: Compare quality, consistency, and reliability of Perplexity-generated responses.
2. Research tracking: Monitor how Perplexity summarizes or interprets information across time.
3. SEO performance comparison: Track your brand mentions and content rankings to optimize your visibility strategies.

• Superior success rates: Experience the most reliable scraping even on high-profile and dynamic AI-driven sources.
• Maintenance-free: Our API handles all the infrastructure, from proxy management to IP rotation and anti-bot systems.
• Dedicated support: Get expert help whenever needed, from integration to debugging.

Perplexity does not provide a public API for all its features, so scraping falls into a gray area depending on its Terms of Service. We recommend reviewing their policies carefully and ensuring compliance. Oxylabs provides the technical capability, but it’s up to you to use it responsibly and in line with applicable regulations.

No, the Perplexity scraper can return multiple formats depending on your needs. The scraper can return results as raw HTML, structured JSON, Markdown output, website PNG, or capture XHR/Fetch requests.

Since Perplexity responses are dynamically generated, requests can take longer than standard web scraping. We recommend setting a timeout of at least 180 seconds when using the Realtime integration method to avoid incomplete results. For larger or more complex prompts, consider asynchronous methods like Push-Pull.

For a deeper dive into available parameters, advanced integrations, and additional examples, check out thePerplexity Scraper documentation.

If you have questions or need support, reach out to us athello@oxylabs.io or through ourlive chat.