{
  "openapi": "3.0.1",
  "info": {
    "title": "🔓 Universal Web Unblocker | AI Web Scraper Engine",
    "description": "Unblock any website and extract clean AI Markdown, HTML, and structured schemas from $1.20/1k results.",
    "version": "0.0",
    "x-build-id": "iTcxOIKlOtFT83Nm6"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/misterkhan~universal-web-unblocker-extractor/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-misterkhan-universal-web-unblocker-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/misterkhan~universal-web-unblocker-extractor/runs": {
      "post": {
        "operationId": "runs-sync-misterkhan-universal-web-unblocker-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/misterkhan~universal-web-unblocker-extractor/run-sync": {
      "post": {
        "operationId": "run-sync-misterkhan-universal-web-unblocker-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "required": [
          "startUrls"
        ],
        "properties": {
          "startUrls": {
            "title": "Target URLs",
            "minItems": 1,
            "type": "array",
            "description": "List of webpage URLs to unblock and extract. Works on any e-commerce store, category/search listing page, real estate portal, job board, review site, directory, news article, or Single-Page Application (SPA).",
            "items": {
              "type": "object",
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL",
                  "description": "Target HTTPS URL",
                  "pattern": "^https://[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}(/.*)?$"
                }
              }
            },
            "default": [
              {
                "url": "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html"
              }
            ]
          },
          "maxItems": {
            "title": "Max Results Limit",
            "minimum": 1,
            "type": "integer",
            "description": "Maximum number of dataset items to output in this run. Free plan runs are capped at 20 items per run; paid Apify plans support unlimited extraction.",
            "default": 25
          },
          "includeMarkdown": {
            "title": "Include Clean AI Markdown (Included in Base Rate)",
            "type": "boolean",
            "description": "Convert the unblocked webpage into clean, token-efficient Markdown with navigation menus, cookie banners, and scripts stripped out. Included in the base result-item rate.",
            "default": true
          },
          "includeHtml": {
            "title": "Include Raw Unblocked HTML (Included in Base Rate)",
            "type": "boolean",
            "description": "Include the full unblocked HTML document string (`html`) in the output dataset. Disabled by default to keep dataset files compact and fast to download.",
            "default": false
          },
          "includeHydration": {
            "title": "Include Hydration & JSON-LD State (`__NEXT_DATA__`, Schema.org)",
            "type": "boolean",
            "description": "Extract embedded Next.js (`__NEXT_DATA__`), Nuxt (`__NUXT_DATA__`), Apollo State, and Schema.org `application/ld+json` objects.",
            "default": false
          },
          "httpResponseHeaders": {
            "title": "Include HTTP Response Headers (`httpResponseHeaders`)",
            "type": "boolean",
            "description": "Include the target server's HTTP response headers in the output.",
            "default": false
          },
          "networkCapture": {
            "title": "Capture Background XHR / GraphQL API Calls (`networkCapture`)",
            "type": "boolean",
            "description": "Capture background XHR, Fetch, and GraphQL JSON network requests fired by the page during browser rendering.",
            "default": false
          },
          "screenshot": {
            "title": "Capture Page Screenshot (`screenshot`)",
            "type": "boolean",
            "description": "Capture a base64-encoded JPEG screenshot of the rendered webpage.",
            "default": false
          },
          "autoExtract": {
            "title": "⚡ Auto-Detect & Extract Structured Schema (+Add-On Event)",
            "type": "boolean",
            "description": "Automatically classify the page and extract structured JSON (Product, Product List, Job Posting, Real Estate, Reviews, Article, or Page Content). Triggers the `structured-extraction` add-on event only when non-empty structured data is extracted.",
            "default": false
          },
          "product": {
            "title": "Extract Product Details (`product`)",
            "type": "boolean",
            "description": "Extract e-commerce product schema: name, price, currency, SKU/ASIN, brand, availability, high-res images, feature bullets, technical specifications table, breadcrumbs, and aggregate rating.",
            "default": false
          },
          "productList": {
            "title": "Extract Product Listing Grid (`productList`)",
            "type": "boolean",
            "description": "Extract all product cards from a category, search, or collection page, plus `nextPage` link.",
            "default": false
          },
          "productNavigation": {
            "title": "Extract Product Category Navigation (`productNavigation`)",
            "type": "boolean",
            "description": "Extract category name, detail item links (`items`), sub-category/filter links (`subCategories`), breadcrumbs, and `nextPage` URL.",
            "default": false
          },
          "jobPosting": {
            "title": "Extract Job Posting (`jobPosting`)",
            "type": "boolean",
            "description": "Extract job title, hiring organization, location, salary range, employment type, date posted, and job description.",
            "default": false
          },
          "jobPostingList": {
            "title": "Extract Job Search Listings (`jobPostingList`)",
            "type": "boolean",
            "description": "Extract multiple job postings from a job board search or company careers page.",
            "default": false
          },
          "jobPostingNavigation": {
            "title": "Extract Job Search Navigation (`jobPostingNavigation`)",
            "type": "boolean",
            "description": "Extract job detail links (`items`), filter links (`subCategories`), and `nextPage` pagination URL from a job board search page.",
            "default": false
          },
          "realEstate": {
            "title": "Extract Real Estate Property (`realEstate`)",
            "type": "boolean",
            "description": "Extract property price, address, bedrooms, bathrooms, square footage/living area, property type, latitude/longitude, and photos.",
            "default": false
          },
          "realEstateList": {
            "title": "Extract Real Estate Search Results (`realEstateList`)",
            "type": "boolean",
            "description": "Extract multiple property listings from a real estate search or directory page.",
            "default": false
          },
          "reviews": {
            "title": "Extract Customer Reviews & Rating Histogram (`reviews`)",
            "type": "boolean",
            "description": "Extract aggregate star rating, 5-star to 1-star rating histogram breakdown, and individual customer review cards.",
            "default": false
          },
          "reviewList": {
            "title": "Extract Paginated Review List (`reviewList`)",
            "type": "boolean",
            "description": "Extract customer review cards, rating histogram, and `nextPage` review pagination link.",
            "default": false
          },
          "contactInfo": {
            "title": "Extract Emails, Phones & Social Profiles (`contactInfo`)",
            "type": "boolean",
            "description": "Extract email addresses, phone numbers, and social media links (LinkedIn, X/Twitter, Instagram, YouTube, TikTok, Facebook, GitHub) found on the page.",
            "default": false
          },
          "businessLead": {
            "title": "Extract Local Business / Company Profile (`businessLead`)",
            "type": "boolean",
            "description": "Extract company name, address, phone number, website, opening hours, and aggregate rating.",
            "default": false
          },
          "socialProfile": {
            "title": "Extract Social Profile & Posts (`socialProfile`)",
            "type": "boolean",
            "description": "Extract public social media profile metadata and embedded post cards.",
            "default": false
          },
          "article": {
            "title": "Extract News / Blog Article (`article`)",
            "type": "boolean",
            "description": "Extract headline, author, publish/modified dates, publisher, main image, and clean article body text.",
            "default": false
          },
          "articleList": {
            "title": "Extract Article / Blog Index List (`articleList`)",
            "type": "boolean",
            "description": "Extract article cards and `nextPage` link from a news section or blog index page.",
            "default": false
          },
          "articleNavigation": {
            "title": "Extract Article Category Navigation (`articleNavigation`)",
            "type": "boolean",
            "description": "Extract article links (`items`), section links (`subCategories`), and `nextPage` URL.",
            "default": false
          },
          "forumThread": {
            "title": "Extract Forum / Discussion Thread (`forumThread`)",
            "type": "boolean",
            "description": "Extract discussion topic, original post, author, and replies/comments.",
            "default": false
          },
          "serp": {
            "title": "Extract Search Engine Results (`serp`)",
            "type": "boolean",
            "description": "Extract organic search result rankings, titles, URLs, and `nextPage` link.",
            "default": false
          },
          "pageContent": {
            "title": "Extract Universal Page Metadata & Links (`pageContent`)",
            "type": "boolean",
            "description": "Extract page title, meta description, canonical URL, language, headings (H1-H3), main text, and outbound links.",
            "default": false
          },
          "extractRules": {
            "title": "Custom CSS / Attribute Extraction Rules (`extractRules`)",
            "type": "object",
            "description": "Optional JSON object mapping custom field names to CSS selectors (e.g. `{\"price\": \".price_color\", \"bookUrls\": [\"article.product_pod h3 a @href\"]}`). Append `@attr` to extract an attribute or wrap selector in `[...]` to extract all matching elements."
          },
          "autoPaginate": {
            "title": "🔁 Auto-Paginate Listing Pages (`autoPaginate`)",
            "type": "boolean",
            "description": "Automatically follow `nextPage` links across multiple listing/category/review pages up to `maxPages`.",
            "default": false
          },
          "maxPages": {
            "title": "Max Pages to Paginate per Start URL (`maxPages`)",
            "minimum": 1,
            "maximum": 50,
            "type": "integer",
            "description": "Maximum number of pagination pages to follow per listing URL when `autoPaginate` is enabled (1 to 50).",
            "default": 1
          },
          "followDetailLinks": {
            "title": "🔗 Two-Hop Listing -> Detail Crawling (`followDetailLinks`)",
            "type": "boolean",
            "description": "When scraping a listing/category page, automatically follow the discovered item links and extract full detail schemas (`product`, `jobPosting`, `realEstate`, `article`, `contactInfo`) from each detail page.",
            "default": false
          },
          "outputMode": {
            "title": "Dataset Output Mode (`outputMode`)",
            "enum": [
              "page",
              "items"
            ],
            "type": "string",
            "description": "Choose `page` (default: 1 dataset row per URL containing all requested schemas) or `items` (flatten `productList`, `jobPostingList`, `realEstateList`, `reviewList`, or `detailPages` so each extracted listing card is emitted as its own dataset row).",
            "default": "page"
          },
          "includeTechStack": {
            "title": "🔬 Detect Website Tech Stack — 7,291 Technologies (+Add-On Event)",
            "type": "boolean",
            "description": "Identify CMS, e-commerce platforms, JavaScript frameworks, analytics pixels, CDNs, and WAFs on the page. Triggers the `tech-stack-scan` add-on event only when technologies are detected.",
            "default": false
          },
          "extractFrom": {
            "title": "Execution Mode (`extractFrom`)",
            "enum": [
              "auto",
              "httpResponseBody",
              "browserHtml"
            ],
            "type": "string",
            "description": "Leave on `auto` (recommended) so the engine starts with fast Coherent TLS HTTP and automatically escalates to a Stealth Browser with fresh residential proxy sessions only when a WAF challenge or unhydrated SPA shell is detected.",
            "default": "auto"
          },
          "country": {
            "title": "Geo-Targeting Country (`country`)",
            "type": "string",
            "description": "2-letter ISO country code for proxy geo-targeting (e.g. `us`, `gb`, `de`, `fr`, `ca`, `au`, `jp`), or `auto` to infer from the target URL domain.",
            "default": "auto"
          },
          "device": {
            "title": "Device Profile (`device`)",
            "enum": [
              "desktop",
              "mobile"
            ],
            "type": "string",
            "description": "Emulate a Desktop (`desktop`) or Mobile (`mobile`) browser/TLS profile.",
            "default": "desktop"
          },
          "waitSelector": {
            "title": "Wait for CSS Selector (`waitSelector`)",
            "type": "string",
            "description": "Optional CSS selector to wait for when rendering dynamic Single-Page Applications (e.g. `#productTitle`, `[data-testid='listing-card']`)."
          },
          "clickSelector": {
            "title": "Click Element Before Extraction (`clickSelector`)",
            "type": "string",
            "description": "Optional CSS selector to click after page load (e.g. cookie consent button, 'Show More', or 'Reviews' tab)."
          },
          "scrollCount": {
            "title": "Infinite Scroll Viewports (`scrollCount`)",
            "minimum": 0,
            "maximum": 15,
            "type": "integer",
            "description": "Number of viewports (0 to 15) to scroll down before extracting to trigger lazy-loaded listing grids or infinite scroll.",
            "default": 0
          },
          "waitMs": {
            "title": "Additional Post-Load Wait (`waitMs`)",
            "minimum": 0,
            "maximum": 10000,
            "type": "integer",
            "description": "Optional extra wait time in milliseconds (0 to 10000) after page hydration / interaction before extracting.",
            "default": 0
          },
          "sessionId": {
            "title": "Sticky Proxy Session ID (`sessionId`)",
            "type": "string",
            "description": "Optional session identifier to reuse the same residential/ISP proxy IP across multiple requests."
          },
          "customHeaders": {
            "title": "Custom HTTP Headers (`customHeaders`)",
            "type": "object",
            "description": "Optional JSON object of custom HTTP request headers to send with the request."
          },
          "cookies": {
            "title": "Custom Request Cookies (`cookies`)",
            "type": "object",
            "description": "Optional JSON object of custom cookies (`{\"name\": \"value\"}`) to attach to the request."
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}