{
  "openapi": "3.0.1",
  "info": {
    "title": "Web Page to Markdown for LLM & RAG – Chinese/Big5/GBK Ready",
    "description": "Convert web pages to clean Markdown for LLMs & RAG: main content only, absolute links, images without trackers, intact code blocks, Big5/GBK/GB2312 Chinese decoding, optional RAG chunks. HTTP first, browser only for JavaScript pages. Blocked, failed and garbled pages are free. No proxies.",
    "version": "0.2",
    "x-build-id": "6ammgFvzilvZnPvSL"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/raspberry_rondel~web-to-markdown-cjk/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-raspberry_rondel-web-to-markdown-cjk",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/raspberry_rondel~web-to-markdown-cjk/runs": {
      "post": {
        "operationId": "runs-sync-raspberry_rondel-web-to-markdown-cjk",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/raspberry_rondel~web-to-markdown-cjk/run-sync": {
      "post": {
        "operationId": "run-sync-raspberry_rondel-web-to-markdown-cjk",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": [
          "urls"
        ],
        "properties": {
          "urls": {
            "title": "Page URLs",
            "type": "array",
            "description": "Web pages to convert to Markdown, one URL per line. Each URL is fetched once; links are not followed.",
            "items": {
              "type": "string"
            }
          },
          "renderMode": {
            "title": "Rendering",
            "enum": [
              "auto",
              "http",
              "browser"
            ],
            "type": "string",
            "description": "Auto fetches the server HTML and only opens a headless browser when the page has little or no content without JavaScript. Browser-rendered pages are charged as the separate browser-page event.",
            "default": "auto"
          },
          "mainContentOnly": {
            "title": "Main content only",
            "type": "boolean",
            "description": "Remove navigation, headers, footers, cookie banners, sidebars and ads, and keep the article or document body. Turn off to convert the whole page.",
            "default": true
          },
          "includeLinks": {
            "title": "Keep links",
            "type": "boolean",
            "description": "Keep hyperlinks as Markdown links with absolute URLs. Turn off to get plain text with no URLs.",
            "default": true
          },
          "includeImages": {
            "title": "Keep images",
            "type": "boolean",
            "description": "Keep content images as Markdown image references (absolute URLs). Tracking pixels, spacers, icons and data: URIs are always removed.",
            "default": true
          },
          "maxMarkdownChars": {
            "title": "Max Markdown characters per page",
            "minimum": 0,
            "type": "integer",
            "description": "Cut each page's Markdown to this many characters (0 = no limit). Useful to cap LLM context size.",
            "default": 0
          },
          "chunkSize": {
            "title": "Chunk size for RAG (characters)",
            "minimum": 0,
            "maximum": 20000,
            "type": "integer",
            "description": "0 = off. When set (200-20000), each page also gets a \"chunks\" array: pieces of at most this many characters, split at headings, then paragraphs, then sentence ends (。！？ and . ! ?), keeping code blocks and tables whole when they fit. Each chunk carries its heading path. Chunking does not change the price: you pay per page, not per chunk.",
            "default": 0
          },
          "chunkOverlap": {
            "title": "Chunk overlap (characters)",
            "minimum": 0,
            "maximum": 10000,
            "type": "integer",
            "description": "Characters from the end of the previous chunk repeated at the start of the next one (capped at half the chunk size). 0 = no overlap.",
            "default": 0
          },
          "minContentChars": {
            "title": "Minimum content characters",
            "minimum": 0,
            "type": "integer",
            "description": "Pages with less text than this are reported as empty-content and not charged.",
            "default": 50
          },
          "browserWaitMs": {
            "title": "Extra wait after load (browser, ms)",
            "minimum": 0,
            "maximum": 5000,
            "type": "integer",
            "description": "When a page is rendered in a browser, wait this long after the load event for late content.",
            "default": 1000
          },
          "requestTimeoutSecs": {
            "title": "Page timeout (seconds)",
            "minimum": 10,
            "maximum": 40,
            "type": "integer",
            "description": "Maximum time to load one page (10-40 s). A page that times out is reported as failed and not charged.",
            "default": 30
          },
          "maxConcurrency": {
            "title": "Max parallel pages",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "How many pages are processed in parallel. Requests to the same website are always spaced at least 1 second apart (or the site's robots.txt Crawl-delay).",
            "default": 10
          },
          "respectRobotsTxt": {
            "title": "Respect robots.txt",
            "type": "boolean",
            "description": "Skip pages that the site's robots.txt disallows for our crawler (RondelBot). Skipped pages are not charged.",
            "default": true
          },
          "respectAiOptOut": {
            "title": "Respect robots.txt opt-outs for AI crawlers",
            "type": "boolean",
            "description": "Skip pages whose robots.txt has a rule for a known AI crawler (for example GPTBot, CCBot, Google-Extended, anthropic-ai, ClaudeBot, PerplexityBot) that disallows the page's path. Skipped pages get status \"skipped-ai-crawler-opt-out\" and are not charged. Turn off only if you have the right to use the content.",
            "default": true
          },
          "skipPaywalledContent": {
            "title": "Skip paywalled pages",
            "type": "boolean",
            "description": "Skip pages that declare paid content (schema.org isAccessibleForFree=false, article:content_tier=locked) or contain common paywall markers (elements with class/id such as \"paywall\" or \"regwall\"). Every row has paywallDetected. Skipped pages get status \"skipped-paywall\" and are not charged. Detection is heuristic. When off, detected pages are converted and charged normally and keep paywallDetected=true.",
            "default": true
          },
          "addSourceLine": {
            "title": "Add a source line",
            "type": "boolean",
            "description": "Start the Markdown of each converted page with one line naming the source: \"Source: <title> <url> (<site name>)\". Turn off to get the page content only. The line is added after maxMarkdownChars is applied.",
            "default": true
          },
          "maxUrlsPerDomain": {
            "title": "Max URLs per site",
            "minimum": 0,
            "type": "integer",
            "description": "Optional limit on how many URLs of the same site (host name, without www.) are processed in one run. URLs above the limit get status \"skipped-domain-limit\" and are not charged. 0 or empty = no limit."
          },
          "locale": {
            "title": "Browser locale",
            "type": "string",
            "description": "Language used by the browser for rendered pages, e.g. zh-TW, zh-CN or en-US.",
            "default": "en-US"
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}