Legacy Phantomjs Crawler

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4# Replace '<YOUR_API_TOKEN>' with your token.
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7# Prepare the Actor input
8run_input = {
9    "startUrls": [{
10            "key": "START",
11            "value": "https://www.example.com/",
12        }],
13    "crawlPurls": [{
14            "key": "MY_LABEL",
15            "value": "https://www.example.com/[.*]",
16        }],
17    "clickableElementsSelector": "a:not([rel=nofollow])",
18    "pageFunction": """function pageFunction(context) {
19    // called on every page the crawler visits, use it to extract data from it
20    var $ = context.jQuery;
21    var result = {
22        title: $('title').text(),
23        myValue: $('TODO').text()
24    };
25    return result;
26}
27""",
28    "interceptRequest": """function interceptRequest(context, newRequest) {
29    // called whenever the crawler finds a link to a new page,
30    // use it to override default behavior
31    return newRequest;
32}
33""",
34}
35
36# Run the Actor and wait for it to finish
37run = client.actor("apify/legacy-phantomjs-crawler").call(run_input=run_input)
38
39# Fetch and print Actor results from the run's dataset (if there are any)
40print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
41for item in client.dataset(run["defaultDatasetId"]).iterate_items():
42    print(item)
43
44# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start