changedOutput schema / (root)
Previous value: -nullNew value: +{
+ "properties": {
+ "actions": {
+ "description": "Outputs of the requested actions, keyed by action."
+ },
+ "data": {
+ "properties": {
+ "actions": {
+ "description": "Results of browser actions: screenshots, PDFs, scraped pages and JavaScript return values."
+ },
+ "attachments": {
+ "description": "Exported files when exportImages was requested.",
+ "items": {
+ "properties": {
+ "bytes": {
+ "description": "Size in bytes.",
+ "type": "integer"
+ },
+ "format": {
+ "description": "File format (extension).",
+ "type": "string"
+ },
+ "hash": {
+ "description": "SHA-256 of the content.",
+ "type": "string"
+ },
+ "id": {
+ "description": "Attachment id; read the file with resources/read.",
+ "type": "string"
+ },
+ "source": {
+ "description": "Original URL or document part, when known.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "format",
+ "bytes",
+ "hash"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "changeTracking": {
+ "properties": {
+ "changeStatus": {
+ "description": "How the page changed since the previous scrape.",
+ "enum": [
+ "new",
+ "same",
+ "changed",
+ "removed"
+ ],
+ "type": "string"
+ },
+ "diff": {
+ "description": "Structured diff when one was requested."
+ },
+ "previousScrapeAt": {
+ "description": "Time of the previous scrape of this URL.",
+ "type": "string"
+ },
+ "visibility": {
+ "description": "Whether the change is visible on the page.",
+ "enum": [
+ "visible",
+ "hidden"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "changeStatus",
+ "visibility"
+ ],
+ "type": "object"
+ },
+ "chunks": {
+ "description": "Markdown chunks when chunking was requested.",
+ "items": {
+ "properties": {
+ "end": {
+ "description": "End byte offset in the Markdown.",
+ "type": "integer"
+ },
+ "headingPath": {
+ "description": "Headings above the chunk.",
+ "items": {
+ "description": "Heading",
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "start": {
+ "description": "Start byte offset in the Markdown.",
+ "type": "integer"
+ },
+ "text": {
+ "description": "Chunk text.",
+ "type": "string"
+ },
+ "tokens": {
+ "description": "Estimated token count.",
+ "type": "integer"
+ }
+ },
+ "required": [
+ "text",
+ "headingPath",
+ "start",
+ "end",
+ "tokens"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "extract": {
+ "description": "Items extracted by an extract schema."
+ },
+ "html": {
+ "description": "Cleaned HTML when the html format was requested.",
+ "type": "string"
+ },
+ "images": {
+ "description": "Image URLs found on the page.",
+ "items": {
+ "description": "Absolute image URL.",
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "json": {
+ "description": "JSON extracted by the json format; its shape follows the requested schema."
+ },
+ "links": {
+ "description": "Links found on the page when the links format was requested.",
+ "items": {
+ "description": "Absolute URL.",
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "markdown": {
+ "description": "Page content as Markdown. Present when the markdown format was requested (the default).",
+ "type": "string"
+ },
+ "metadata": {
+ "properties": {
+ "author": {
+ "description": "Author declared by the page.",
+ "type": "string"
+ },
+ "cacheState": {
+ "description": "Whether the result came from the result cache.",
+ "enum": [
+ "hit",
+ "miss"
+ ],
+ "type": "string"
+ },
+ "cachedAt": {
+ "description": "Time the cached copy was stored.",
+ "type": "string"
+ },
+ "contentType": {
+ "description": "Response Content-Type.",
+ "type": "string"
+ },
+ "description": {
+ "description": "Meta description.",
+ "type": "string"
+ },
+ "error": {
+ "description": "Error note when the page was returned with an error status.",
+ "type": "string"
+ },
+ "favicon": {
+ "description": "Favicon URL.",
+ "type": "string"
+ },
+ "keywords": {
+ "description": "Meta keywords.",
+ "type": "string"
+ },
+ "language": {
+ "description": "Detected or declared language.",
+ "type": "string"
+ },
+ "modifiedTime": {
+ "description": "Modified time declared by the page.",
+ "type": "string"
+ },
+ "pagesift": {
+ "properties": {
+ "browserEngine": {
+ "description": "Browser kernel used for a rendered page.",
+ "type": "string"
+ },
+ "browserFingerprint": {
+ "description": "TLS fingerprint profile used for the request.",
+ "type": "string"
+ },
+ "contentHash": {
+ "description": "Hash of the cleaned content.",
+ "type": "string"
+ },
+ "crawl": {
+ "description": "How this page was discovered during a crawl."
+ },
+ "duplicateOf": {
+ "description": "Canonical URL when this page duplicates another.",
+ "type": "string"
+ },
+ "engine": {
+ "description": "Engine that produced the result.",
+ "enum": [
+ "http",
+ "browser",
+ "upload"
+ ],
+ "type": "string"
+ },
+ "etag": {
+ "description": "ETag from the response.",
+ "type": "string"
+ },
+ "itna": {
+ "description": "Access-barrier recovery attempts and their outcomes, when itna is enabled."
+ },
+ "jsonLd": {
+ "description": "JSON-LD blocks found on the page.",
+ "items": {
+ "description": "Parsed JSON-LD object."
+ },
+ "type": "array"
+ },
+ "lastModified": {
+ "description": "Last-Modified from the response.",
+ "type": "string"
+ },
+ "notModified": {
+ "description": "The origin answered 304 to a conditional request.",
+ "type": "boolean"
+ },
+ "ocr": {
+ "description": "OCR engine, device and page counts for scanned PDFs."
+ },
+ "plan": {
+ "description": "Render and merge decisions recorded by explain."
+ },
+ "queryFilter": {
+ "description": "How many blocks the query filter kept and token counts."
+ },
+ "rawHash": {
+ "description": "Hash of the raw response.",
+ "type": "string"
+ },
+ "redirectChain": {
+ "description": "URLs visited before the final page.",
+ "items": {
+ "description": "URL",
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "relevance": {
+ "description": "Query relevance score from 0 to 1.",
+ "type": "number"
+ },
+ "textHash": {
+ "description": "Hash of the normalized text used for change tracking.",
+ "type": "string"
+ },
+ "timings": {
+ "description": "Time per phase in milliseconds.",
+ "type": "object"
+ },
+ "warnings": {
+ "description": "Warnings that may mean the content is incomplete.",
+ "items": {
+ "description": "Warning",
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "proxyUsed": {
+ "description": "Egress or proxy used for the request.",
+ "type": "string"
+ },
+ "publishedTime": {
+ "description": "Published time declared by the page.",
+ "type": "string"
+ },
+ "robots": {
+ "description": "robots meta directive.",
+ "type": "string"
+ },
+ "scrapeId": {
+ "description": "Id of the kept browser page when keepSession was used; pass it to pagesift_interact.",
+ "type": "string"
+ },
+ "sourceURL": {
+ "description": "URL that was requested.",
+ "type": "string"
+ },
+ "statusCode": {
+ "description": "HTTP status code of the response.",
+ "type": "integer"
+ },
+ "title": {
+ "description": "Page title.",
+ "type": "string"
+ },
+ "url": {
+ "description": "Final URL after redirects.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "statusCode",
+ "proxyUsed"
+ ],
+ "type": "object"
+ },
+ "pages": {
+ "description": "Per-page Markdown, only for PDF page mode.",
+ "items": {
+ "properties": {
+ "markdown": {
+ "description": "Markdown for this page.",
+ "type": "string"
+ },
+ "pageNumber": {
+ "description": "1-based PDF page number.",
+ "type": "integer"
+ }
+ },
+ "required": [
+ "pageNumber",
+ "markdown"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "rawHtml": {
+ "description": "Unmodified response body when the rawHtml format was requested.",
+ "type": "string"
+ },
+ "screenshot": {
+ "description": "Screenshot URL or data URL when the screenshot format was requested.",
+ "type": "string"
+ },
+ "summary": {
+ "description": "Summary produced when the summary format was requested.",
+ "type": "string"
+ },
+ "warning": {
+ "description": "Compatibility or deprecation warning from the scrape.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "metadata"
+ ],
+ "type": "object"
+ },
+ "error": {
+ "description": "Failure reason when the action did not complete.",
+ "type": "string"
+ },
+ "exitCode": {
+ "description": "Exit code of the action run.",
+ "type": "integer"
+ },
+ "killed": {
+ "description": "The run was stopped at the time limit.",
+ "type": "boolean"
+ },
+ "output": {
+ "description": "Answer to a prompt (only with prompt).",
+ "type": "string"
+ },
+ "result": {
+ "description": "Last browser action result, such as a JavaScript return value.",
+ "type": "string"
+ },
+ "stderr": {
+ "description": "Always empty; pagesift does not execute shell commands.",
+ "type": "string"
+ },
+ "stdout": {
+ "description": "Always empty; pagesift does not execute shell commands.",
+ "type": "string"
+ },
+ "steps": {
+ "description": "Steps executed for a prompt.",
+ "items": {
+ "description": "One step the prompt executed.",
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "success": {
+ "description": "The action or prompt completed.",
+ "type": "boolean"
+ },
+ "warnings": {
+ "description": "Warnings from the interaction.",
+ "items": {
+ "description": "Warning",
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "success"
+ ],
+ "type": "object"
+}
