1from apify_client import ApifyClient
2
3
4
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7
8run_input = {
9 "startUrls": [{ "url": "https://docs.apify.com" }],
10 "maxCrawlDepth": 1,
11 "maxCrawlPages": 3,
12 "useSitemaps": False,
13 "useLlmsTxt": False,
14 "respectRobotsTxtFile": True,
15 "crawlOnlyPagesChangedSince": "",
16 "includeUrlGlobs": [],
17 "excludeUrlGlobs": [],
18 "includeUrlRegexps": [],
19 "excludeUrlRegexps": [],
20 "keepUrlFragments": False,
21 "ignoreCanonicalUrl": False,
22 "outputFormat": "markdown",
23 "htmlTransformer": "auto",
24 "includeImages": False,
25 "chunkMarkdown": False,
26 "chunkMaxChars": 2000,
27 "chunkOverlapChars": 200,
28 "keepElementsCssSelector": "",
29 "removeElementsCssSelector": "",
30 "parsePdfText": True,
31 "clickElementsCssSelector": "",
32 "takeScreenshots": False,
33 "customHttpHeaders": [],
34 "storeSkippedUrls": False,
35}
36
37
38run = client.actor("vexaloom-labs/domain-scoped-site-crawler-for-markdown-datasets").call(run_input=run_input)
39
40
41print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
42for item in client.dataset(run.default_dataset_id).iterate_items():
43 print(item)
44
45
