Get Web Crawler Job

GET

Gets a web crawler job.

Query parameters

idstringRequiredformat: "id"

The ID of the job.

Response

The response to get a web crawler job.

web_crawler_jobobject

GET

1 curl -G https://api.devrev.ai/web-crawler-jobs.get \
2      -H "Authorization: Bearer <token>" \
3      -d id=id

200Retrieved

1 {
2   "web_crawler_job": {
3     "id": "id",
4     "accept_regexs": [
5       "accept_regexs",
6       "accept_regexs"
7     ],
8     "created_by": {
9       "type": "dev_user",
10       "id": "id",
11       "display_id": "display_id",
12       "display_name": "display_name",
13       "display_picture": {
14         "id": "id",
15         "display_id": "display_id",
16         "file": {}
17       },
18       "email": "email",
19       "full_name": "full_name",
20       "state": "active"
21     },
22     "created_date": "created_date",
23     "description": "description",
24     "display_id": "display_id",
25     "domain_names": [
26       "domain_names",
27       "domain_names"
28     ],
29     "frequency": 1,
30     "max_depth": 1,
31     "modified_by": {
32       "type": "dev_user",
33       "id": "id",
34       "display_id": "display_id",
35       "display_name": "display_name",
36       "display_picture": {
37         "id": "id",
38         "display_id": "display_id",
39         "file": {}
40       },
41       "email": "email",
42       "full_name": "full_name",
43       "state": "active"
44     },
45     "modified_date": "modified_date",
46     "no_parent": true,
47     "notify_on_complete": true,
48     "num_bytes": 1,
49     "num_timeout_urls": 1,
50     "num_urls_scraped": 1,
51     "reject_regexs": [
52       "reject_regexs",
53       "reject_regexs"
54     ],
55     "sitemap_index_urls": [
56       "sitemap_index_urls",
57       "sitemap_index_urls"
58     ],
59     "sitemap_urls": [
60       "sitemap_urls",
61       "sitemap_urls"
62     ],
63     "state": "aborted",
64     "urls": [
65       "urls",
66       "urls"
67     ]
68   }
69 }

Get Web Crawler Job (POST)

Up Next

Built with

1	curl -G https://api.devrev.ai/web-crawler-jobs.get \
2	-H "Authorization: Bearer <token>" \
3	-d id=id

1	{
2	"web_crawler_job": {
3	"id": "id",
4	"accept_regexs": [
5	"accept_regexs",
6	"accept_regexs"
7	],
8	"created_by": {
9	"type": "dev_user",
10	"id": "id",
11	"display_id": "display_id",
12	"display_name": "display_name",
13	"display_picture": {
14	"id": "id",
15	"display_id": "display_id",
16	"file": {}
17	},
18	"email": "email",
19	"full_name": "full_name",
20	"state": "active"
21	},
22	"created_date": "created_date",
23	"description": "description",
24	"display_id": "display_id",
25	"domain_names": [
26	"domain_names",
27	"domain_names"
28	],
29	"frequency": 1,
30	"max_depth": 1,
31	"modified_by": {
32	"type": "dev_user",
33	"id": "id",
34	"display_id": "display_id",
35	"display_name": "display_name",
36	"display_picture": {
37	"id": "id",
38	"display_id": "display_id",
39	"file": {}
40	},
41	"email": "email",
42	"full_name": "full_name",
43	"state": "active"
44	},
45	"modified_date": "modified_date",
46	"no_parent": true,
47	"notify_on_complete": true,
48	"num_bytes": 1,
49	"num_timeout_urls": 1,
50	"num_urls_scraped": 1,
51	"reject_regexs": [
52	"reject_regexs",
53	"reject_regexs"
54	],
55	"sitemap_index_urls": [
56	"sitemap_index_urls",
57	"sitemap_index_urls"
58	],
59	"sitemap_urls": [
60	"sitemap_urls",
61	"sitemap_urls"
62	],
63	"state": "aborted",
64	"urls": [
65	"urls",
66	"urls"
67	]
68	}
69	}