1from apify_client import ApifyClient
2
3
4
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7
8run_input = {
9 "documents": [
10 {
11 "label": "Project Gutenberg",
12 "url": "https://www.gutenberg.org/policy/robot_access.html",
13 },
14 {
15 "label": "Project Gutenberg terms of use",
16 "url": "https://www.gutenberg.org/policy/terms_of_use.html",
17 },
18 ],
19 "clauseTerms": [
20 "automated means",
21 "automated",
22 "scrape",
23 "scraping",
24 "crawler",
25 "crawl",
26 "spider",
27 "bot",
28 "robot",
29 "robots.txt",
30 "data mining",
31 "text and data mining",
32 "harvest",
33 "AI agent",
34 "artificial intelligence",
35 "machine learning",
36 "LLM",
37 "large language model",
38 "rate limit",
39 "API key",
40 "resale",
41 "resell",
42 ],
43 "contextChars": 600,
44 "reportUnchanged": False,
45 "stateStoreName": "tos-clause-baselines",
46 "timeoutSeconds": 20,
47 "maxResponseBytes": 1000000,
48 "maxRedirects": 3,
49 "concurrency": 4,
50 "userAgent": "TosClauseWatcher/0.1 (+https://apify.com)",
51}
52
53
54run = client.actor("kingii98/target-site-terms-automation-clause-change-watcher").call(run_input=run_input)
55
56
57print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
58for item in client.dataset(run.default_dataset_id).iterate_items():
59 print(item)
60
61