curl --request GET \
--url https://api.open.cx/crawl/{id}{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"url": "<string>",
"display_name": "<string>",
"status": "<string>",
"page_limit": 123,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 123,
"last_crawl_started_at": "2023-11-07T05:31:56Z",
"last_crawl_completed_at": "2023-11-07T05:31:56Z",
"error_message": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"page_stats": {
"total": 123,
"synced": 123,
"pending": 123,
"error": 123,
"excluded": 123
},
"active_crawl_job": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "<string>",
"total_pages": 123,
"completed_pages": 123,
"new_pages": 123,
"updated_pages": 123,
"removed_pages": 123,
"unchanged_pages": 123,
"started_at": "2023-11-07T05:31:56Z"
}
}Retrieve a website datasource with page statistics and active crawl job information.
curl --request GET \
--url https://api.open.cx/crawl/{id}{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"url": "<string>",
"display_name": "<string>",
"status": "<string>",
"page_limit": 123,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 123,
"last_crawl_started_at": "2023-11-07T05:31:56Z",
"last_crawl_completed_at": "2023-11-07T05:31:56Z",
"error_message": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"page_stats": {
"total": 123,
"synced": 123,
"pending": 123,
"error": 123,
"excluded": 123
},
"active_crawl_job": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "<string>",
"total_pages": 123,
"completed_pages": 123,
"new_pages": 123,
"updated_pages": 123,
"removed_pages": 123,
"unchanged_pages": 123,
"started_at": "2023-11-07T05:31:56Z"
}
}The website datasource ID
Default Response
Show child attributes
Show child attributes
Was this page helpful?