Requirements Scrape Graph AI requires an active account and an API access token from your account settings to connect. Both are set up on its own site.[3] https://scrapegraphai.com
Get your Scrape Graph AI credentials Connect Scrape Graph AI in WEXTL Log in to your WEXTL account, add the Scrape Graph AI node module to your workflow, and click Create new credential . Optional: In the Credential name field, enter a name for the credential. Enter the authentication credentials you copied from your Scrape Graph AI account, or follow the on-screen instructions to create the credential. If prompted, authenticate your account and confirm access. If you want to make changes to your credential in the future, follow the steps in Manage credentials → Notes Credentials are org-scoped. Share them with teammates from the Credentials picker on any of its nodes. For detailed information on connecting an application, see Connect an application →
Scrape Graph AI triggers and actions on WEXTL The list below is a reference of every Scrape Graph AI node module the integration supports. You will be able to pick any of them on the workflow canvas while building automations.
Browse every Scrape Graph AI node module below. Each one opens to show its input parameters, outputs, and connection requirements.
Get a Crawl Status Search Progress of one crawl job. Input fields[3] Field Type Crawl IDRequired
text
Output fields[3] Field Type ID text Status text Total number Finished number Pages array Page object
Get a History Entry Search One past request with its result. Input fields[3] Field Type Request IDRequired
text
Output fields[3] Field Type ID text User ID text Session ID text Service text Status text Params text Result text Error text Elapsed Ms number Request Parent ID text Created At date
Get a Monitor Search Settings and state of one monitor. Input fields[3] Field Type MonitorRequired
choice
Output fields[3] Field Type Cron ID text Schedule ID text Interval text Status text Config text Created At date Updated At date
Get Credits Search Credits left on your account. Output fields[3] Field Type Remaining number Used number Plan text Jobs object Crawl object Monitor object
List Crawl Pages Search Pages visited by a crawl job. Input fields[3] Field Type Crawl IDRequired
text LimitRequired
number
Output fields[3] Field Type URL text Depth number Title text Status text Parent URL text Content Type text Links array Scrape Ref ID text Scrape text
List History Search Earlier requests on your account. Input fields[3] Field Type LimitRequired
number Service choice Session ID text
Output fields[3] Field Type ID text User ID text Session ID text Service text Status text Params text Result text Error text Elapsed Ms number Request Parent ID text Created At date
List Monitor Activity Search Run log of a single monitor. Input fields[3] Field Type MonitorRequired
choice Cursor text
Output fields[3] Field Type ID text Status text Created At date Elapsed Ms number Changed boolean Diffs text Next Cursor text
List Monitors Search All monitors set up on the account. Output fields[3] Field Type Cron ID text Schedule ID text Interval text Status text Config text Created At date Updated At date
Search the Web Search Web search with optional extraction. Input fields[3] Field Type QueryRequired
text Number of Results number Prompt text Schema text Result Format choice Time Range choice Location text Allowed Types array MIME Type text PDF Pages number Fetch Mode choice Stealth boolean Request Headers array Header object Request Cookies array Cookie object Scrolls number Wait (ms) number Fetch Timeout (ms) number Country text Session ID text
Output fields[3] Field Type ID text Results array Result object JSON text Raw text Usage object Prompt Tokens number Completion Tokens number Metadata text
Create a Monitor Action Recurring page check on a cron interval. Input fields[3] Field Type URLRequired
text NameRequired
text IntervalRequired
text Formats choice Markdown Mode choice HTML Mode choice JSON Prompt text JSON Schema text Screenshot Full Page boolean Screenshot Width number Screenshot Height number Screenshot Quality number Webhook URL text Fetch Mode choice Stealth boolean Request Headers array Header object Request Cookies array Cookie object Scrolls number Wait (ms) number Fetch Timeout (ms) number
1 other input field
Output fields[3] Field Type Cron ID text Schedule ID text Interval text Status text Config text Created At date Updated At date
Delete a Crawl Action Removes one crawl job and its pages. Input fields[3] Field Type Crawl IDRequired
text
Output fields[3] Field Type ID text OK boolean
Delete a Monitor Action Removes one monitor and its history. Input fields[3] Field Type MonitorRequired
choice
Output fields[3] Field Type ID text OK boolean
Extract Data Action Prompt-driven structured extraction. Input fields[3] Field Type PromptRequired
text URL text HTML text Markdown text Schema text HTML Mode choice Allowed Types array MIME Type text PDF Pages number Fetch Mode choice Stealth boolean Request Headers array Header object Request Cookies array Cookie object Scrolls number Wait (ms) number Fetch Timeout (ms) number Country text Session ID text
Output fields[3] Field Type ID text Raw text JSON text Usage object Prompt Tokens number Completion Tokens number Metadata text
Generate a Schema Action Builds a JSON schema from a description. Input fields[3] Field Type PromptRequired
text Existing Schema text Model text
Output fields[3] Field Type Refined Prompt text Schema text Usage object Prompt Tokens number Completion Tokens number
Make an API Call universal Free-form Scrape Graph AI REST API request. Input fields[3] Field Type URLRequired
text MethodRequired
choice Headers array Header object Query string array Parameter object Body text
Output fields[3] Field Type Body text Headers object Key text Value text Status code number
Pause a Monitor Action Suspends scheduled runs of one monitor. Input fields[3] Field Type MonitorRequired
choice
Output fields[3] Field Type Cron ID text Schedule ID text Interval text Status text Config text Created At date Updated At date
Resume a Crawl Action Continues a stopped crawl. Input fields[3] Field Type Crawl IDRequired
text
Output fields[3] Field Type ID text OK boolean
Resume a Monitor Action Re-enables a paused monitor. Input fields[3] Field Type MonitorRequired
choice
Output fields[3] Field Type Cron ID text Schedule ID text Interval text Status text Config text Created At date Updated At date
Scrape a Page Action Fetches one page as Markdown, HTML or JSON. Input fields[3] Field Type URLRequired
text FormatsRequired
choice Markdown Mode choice HTML Mode choice JSON Prompt text JSON Schema text Screenshot Full Page boolean Screenshot Width number Screenshot Height number Screenshot Quality number Content Type text Allowed Types array MIME Type text PDF Pages number Fetch Mode choice Stealth boolean Request Headers array Header object Request Cookies array Cookie object Scrolls number Wait (ms) number Fetch Timeout (ms) number
2 other input fields
Output fields[3] Field Type ID text Results text Metadata object Content Type text
Start a Crawl Action Starts a multi-page crawl job. Input fields[3] Field Type URLRequired
text Formats choice Markdown Mode choice HTML Mode choice JSON Prompt text JSON Schema text Screenshot Full Page boolean Screenshot Width number Screenshot Height number Screenshot Quality number Max Pages number Max Depth number Max Links per Page number Include Patterns array Pattern text Exclude Patterns array Pattern text Allow External Links boolean Allowed Types array MIME Type text PDF Pages number Fetch Mode choice Stealth boolean
7 other input fields
Output fields[3] Field Type ID text Status text Total number Finished number Pages array
Stop a Crawl Action Ends a crawl job that is still running. Input fields[3] Field Type Crawl IDRequired
text
Output fields[3] Field Type ID text OK boolean
Update a Monitor Action Changes the schedule or settings of a monitor. Input fields[3] Field Type MonitorRequired
choice Interval text Formats choice Markdown Mode choice HTML Mode choice JSON Prompt text JSON Schema text Screenshot Full Page choice Screenshot Width number Screenshot Height number Screenshot Quality number Webhook URL text Fetch Mode choice Stealth choice Request Headers array Header object Request Cookies array Cookie object Scrolls number Wait (ms) number Fetch Timeout (ms) number Country text
Output fields[3] Field Type Cron ID text Schedule ID text Interval text Status text Config text Created At date Updated At date
Templates Look for Scrape Graph AI templates in the WEXTL template library.
Browse templates → Other AI integrations on WEXTL