{"uid":"cap_lKOZREbzBV118HkG5b8MD","slug":"olostep-web-page-scraper-7b766785","name":"Olostep Web Page Scraper","description":"Initiate a web page scrape","url":"https://x402.orth.sh/olostep/v1/scrapes","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"parser":{"type":"object","properties":{"id":{"type":"string"}},"description":"When defining json as a format, you can use this parameter to specify the parser to use. Parsers are useful to extract structured content from web pages. Olostep has a few parsers built in for most common web pages, and you can also create your own parsers."},"actions":{"type":"object","properties":{"type":{"type":"string"},"milliseconds":{"type":"number"}},"description":"Actions to perform on the page before getting the content."},"country":{"type":"string","description":"Residential country to load the request from. Supported values are: * US (United States) * CA (Canada) * IT (Italy) * IN (India) * GB (England) * JP (Japan) * MX (Mexico) * AU (Australia) * ID (Indonesia) * UA (UAE) * RU (Russia) * RANDOM Some operations, like scraping Google Search and Google News, support all countries."},"formats":{"type":"array","items":{"type":"string"},"description":"Formats in which you want the content."},"metadata":{"type":"object","description":"User-defined metadata. Not supported yet"},"llm_extract":{"type":"object","properties":{"schema":{"type":"object"}}},"screen_size":{"type":"object","properties":{"screen_type":{"type":"string"},"screen_width":{"type":"number"},"screen_height":{"type":"number"}},"description":"Configuration for screen size. Preset dimensions are available through screen_type: desktop (1920x1080), mobile (414x896), or default (768x1024)."},"transformer":{"type":"string","description":"Specify the HTML transformer to use, if any. Postlight's Mercury Parser library is used to remove ads and other unwanted content from the scraped content. Available options: `postlight`, `none`"},"links_on_page":{"type":"object","properties":{"exclude_links":{"type":"array","items":{"type":"string"}},"include_links":{"type":"array","items":{"type":"string"}},"absolute_links":{"type":"boolean"},"query_to_order_links_by":{"type":"string"}},"description":"With this option, you can get all the links present on the page you scrape."},"remove_images":{"type":"boolean","description":"Option to remove images from the scraped content. Defaults to false."},"url_to_scrape":{"type":"string","description":"The URL to start scraping from."},"remove_class_names":{"type":"array","items":{"type":"string"},"description":"List of class names to remove from the content."},"remove_css_selectors":{"type":"string","description":"Option to remove certain CSS selectors from the content. Optionally, you can also pass a JSON stringified array of specific selectors you want to remove. The CSS selectors removed when this option is set to default are ['nav','footer','script','style','noscript','svg',[role=alert],[role=banner],[role=dialog],[role=alertdialog],[role=region][aria-label*=skip i],[aria-modal=true]] Available options: `default`, `none`, `array`"},"wait_before_scraping":{"type":"integer","description":"Time to wait in milliseconds before starting the scraping."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_E28EqalKmw8Y30zAeJBLV","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Initiates a web page scrape via Olostep, returning page content in configurable formats (markdown, HTML, JSON, links, images, etc.) with optional actions, transformers, and LLM extraction","exampleAgentPrompt":"Scrape the URL https://example.com/article and give me the content in markdown format, loaded from a US residential proxy, with ads removed using the postlight transformer.","exampleUseCases":[{"title":"Competitor pricing intelligence","prompt":"Scrape https://competitor.com/pricing and return the page content as markdown so I can see their current pricing plans — use a US residential proxy and strip out ads."},{"title":"LLM-powered structured data extraction","prompt":"Fetch https://techcrunch.com/latest and use LLM extraction to pull out the article title, author, and publication date as structured JSON fields."},{"title":"Mobile-view page scraping","prompt":"Scrape https://shop.example.com/product/123 with a mobile screen size so I can see what the page looks like on a phone, and return the full HTML along with all links on the page."}],"resultDescription":"Returns the scraped page content in one or more requested formats (markdown, HTML, JSON, links, images, etc.), along with any structured data from parsers or LLM extraction, and page metadata.","failureModes":["URL is unreachable or returns non-200 status","Unsupported country code provided for residential proxy","Page requires JavaScript execution beyond configured actions","LLM extraction schema does not match page content structure","Payment fails or insufficient USDC balance for x402 transaction","Rate limiting or bot detection by target website"],"whenToPreferThis":"Choose this endpoint when you need flexible, feature-rich web scraping with options for residential proxies by country, ad-stripping transformers, LLM-based structured extraction, screen size emulation, and multiple output formats. It is backed by Olostep and is ideal for agents that need more than raw HTML — e.g. clean markdown, structured JSON, or link lists — from a single page. Prefer sibling crawl endpoints if you need to traverse multiple pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T06:30:51.718Z","isFirstParty":false}