1from apify_client import ApifyClient
2
3
4
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7
8run_input = {
9 "startUrls": [
10 { "url": "http://github.com" },
11 { "url": "https://example.com" },
12 { "url": "https://example.com/this-page-does-not-exist" },
13 { "url": "https://www.iana.org/" },
14 { "url": "https://www.wikipedia.org/" },
15 ],
16 "sourceMode": "urls",
17 "redirectExpectations": [],
18 "crawlDepth": 1,
19 "maxPagesToCrawl": 10,
20 "linkScope": "all",
21 "includeAssets": False,
22 "includeUrlPatterns": [],
23 "excludeUrlPatterns": [],
24 "respectRobotsTxt": True,
25 "expectedStatus": [],
26 "mustContainText": [],
27 "mustNotContainText": [],
28 "requiredHeaders": [],
29 "warnAboveRedirects": 2,
30 "slowThresholdMs": 3000,
31 "maxResponseTimeMs": 0,
32 "sslWarnDays": 30,
33 "detectSoft404": False,
34 "extractPageBasics": False,
35 "includeSecurityHeaders": False,
36 "includeResponseHeaders": False,
37 "probeHttp2": False,
38 "maxItems": 10,
39 "outputFilter": "all",
40 "trackHistory": True,
41 "monitorScope": "default",
42 "responseRegressionPercent": 100,
43 "confirmChanges": True,
44 "requestMethod": "HEAD_FALLBACK",
45 "followRedirects": True,
46 "maxRedirects": 10,
47 "timeoutSecs": 20,
48 "retries": 1,
49 "userAgentType": "monitor",
50 "userAgent": "",
51 "customHeaders": [],
52 "maxConcurrency": 10,
53 "maxConcurrencyPerHost": 2,
54 "delayPerHostMs": 250,
55 "proxyConfiguration": { "useApifyProxy": False },
56}
57
58
59run = client.actor("getascraper/http-status-intelligence-monitor").call(run_input=run_input)
60
61
62print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
63for item in client.dataset(run.default_dataset_id).iterate_items():
64 print(item)
65
66
