{"id":"html_structured_data","name":"HTML Structured Data","alias":"HTMLStructuredData","aliases":[],"description_short":"Extract structured data (JSON-LD) from HTML pages.","description_long":"\n    Extract structured data from HTML pages in JSON-LD format.\n    ","description_tool_prompt":"\n    Extract structured data from HTML pages in JSON-LD format.\n    ","source":"Browser Fetching or SiteCrawler","conversation_examples":["Extract the structured data from https://www.example.org/p/5866-toothbrush","Extract the structured data from https://www.example.org/p/1234-phone for the types 'Product'"],"tags":["url data"],"available_in_chat":true,"available_in_deepthink":true,"available_in_mcp":true,"mcp_audience":"all","config":{"type":"object","properties":{"country_code":{"default":"us","description":"The country code to use for the real-time fetch. 2 letters lowercase","title":"Country Code","type":"string"},"types":{"description":"The types of structured data to extract. Will extract all if not provided.","items":{"type":"string"},"title":"Types","type":"array"},"fallback_real_time_fetch":{"default":false,"description":"Fallback to real_time_fetch_url if the URL is not found in SiteCrawler","title":"Fallback To Real Time Fetch","type":"boolean"}},"required":[]},"item":{"type":"object","properties":{"url":{"description":"The URL of the page to extract structured data from","title":"Url","type":"string"}},"required":["url"]},"response":{"$defs":{"HTMLStructuredData":{"description":"Represents a structured data object found in a page.","properties":{"type":{"anyOf":[{"type":"string"},{"items":{"type":"string"},"type":"array"}],"description":"JSON-LD @type: a single type name or a list of types (e.g. Book and Product).","title":"Type"},"data":{"additionalProperties":true,"description":"The structured data in JSON-LD format","title":"Data","type":"object"}},"required":["type","data"],"title":"HTMLStructuredData","type":"object"},"HTMLStructuredDataParsingError":{"description":"Represents an error that occurred while parsing structured data.","properties":{"error":{"description":"The error message","title":"Error","type":"string"},"raw_json":{"description":"The raw JSON that caused the error","title":"Raw Json","type":"string"}},"required":["error","raw_json"],"title":"HTMLStructuredDataParsingError","type":"object"},"OriginEnum":{"enum":["site_crawler","real_time_fetch_url","rendering_farm","temporary_upload"],"title":"OriginEnum","type":"string"}},"properties":{"origin":{"anyOf":[{"$ref":"#/$defs/OriginEnum"},{"type":"null"}],"default":null,"description":"The origin of the HTML (site_crawler, real_time_fetch_url, or rendering_farm)"},"status_code":{"anyOf":[{"type":"integer"},{"type":"null"}],"default":null,"description":"HTTP status code of the fetched page","title":"Status Code"},"url_found":{"default":true,"description":"Whether the URL was found in the crawl","title":"Url Found","type":"boolean"},"objects":{"description":"List of extracted structured data objects","items":{"$ref":"#/$defs/HTMLStructuredData"},"title":"Objects","type":"array"},"has_objects":{"description":"Whether any structured data objects were found","title":"Has Objects","type":"boolean"},"has_errors":{"description":"Whether any errors were reported in `errors` (currently JSON-LD extraction/parsing; may include other kinds later)","title":"Has Errors","type":"boolean"},"errors":{"description":"List of errors encountered during extraction","items":{"$ref":"#/$defs/HTMLStructuredDataParsingError"},"title":"Errors","type":"array"},"title":{"description":"Title indicating the source URL","title":"Title","type":"string"}},"required":["objects","has_objects","has_errors","errors","title"],"title":"HTMLStructuredDataProcessedItem","type":"object"},"has_canvas":true,"open_canvas_automatically":false}