1from apify_client import ApifyClient
2
3
4
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7
8run_input = {
9 "reportName": "Sample dataset quality report",
10 "maxItems": 1000,
11 "validateAllItems": False,
12 "itemOffset": 0,
13 "itemOrder": "first",
14 "failRunOnError": False,
15 "items": [
16 {
17 "id": "item-1",
18 "url": "https://example.com/a",
19 "email": "owner@example.com",
20 },
21 {
22 "id": "item-2",
23 "url": "https://example.com/b",
24 "email": "second@example.com",
25 },
26 ],
27 "requiredFields": [
28 "id",
29 "url",
30 ],
31 "expectedSchema": {
32 "id": "string",
33 "url": "string",
34 "email": "string",
35 },
36 "uniqueFields": ["id"],
37 "formatRules": {
38 "url": "url",
39 "email": "email",
40 },
41}
42
43
44run = client.actor("jy-labs/dataset-quality-gate").call(run_input=run_input)
45
46
47print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
48for item in client.dataset(run["defaultDatasetId"]).iterate_items():
49 print(item)
50
51