Web Scraper

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    "runMode": "DEVELOPMENT",
10    "startUrls": [{ "url": "https://crawlee.dev/js" }],
11    "respectRobotsTxtFile": True,
12    "linkSelector": "a[href]",
13    "globs": [{ "glob": "https://crawlee.dev/js/*/*" }],
14    "pseudoUrls": [],
15    "excludes": [{ "glob": "/**/*.{png,jpg,jpeg,pdf}" }],
16    "pageFunction": """// The function accepts a single argument: the \"context\" object.
17// For a complete list of its properties and functions,
18// see https://apify.com/apify/web-scraper#page-function 
19async function pageFunction(context) {
20    // This statement works as a breakpoint when you're trying to debug your code. Works only with Run mode: DEVELOPMENT!
21    // debugger; 
22
23    // jQuery is handy for finding DOM elements and extracting data from them.
24    // To use it, make sure to enable the \"Inject jQuery\" option.
25    const $ = context.jQuery;
26    const pageTitle = $('title').first().text();
27    const h1 = $('h1').first().text();
28    const first_h2 = $('h2').first().text();
29    const random_text_from_the_page = $('p').first().text();
30
31
32    // Print some information to Actor log
33    context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
34
35    // Manually add a new page to the queue for scraping.
36   await context.enqueueRequest({ url: 'http://www.example.com' });
37
38    // Return an object with the data extracted from the page.
39    // It will be stored to the resulting dataset.
40    return {
41        url: context.request.url,
42        pageTitle,
43        h1,
44        first_h2,
45        random_text_from_the_page
46    };
47}""",
48    "proxyConfiguration": { "useApifyProxy": True },
49    "initialCookies": [],
50    "waitUntil": ["networkidle2"],
51    "preNavigationHooks": """// We need to return array of (possibly async) functions here.
52// The functions accept two arguments: the \"crawlingContext\" object
53// and \"gotoOptions\".
54[
55    async (crawlingContext, gotoOptions) => {
56        // ...
57    },
58]
59""",
60    "postNavigationHooks": """// We need to return array of (possibly async) functions here.
61// The functions accept a single argument: the \"crawlingContext\" object.
62[
63    async (crawlingContext) => {
64        // ...
65    },
66]""",
67    "breakpointLocation": "NONE",
68    "customData": {},
69}
70
71# Run the Actor and wait for it to finish
72run = client.actor("apify/web-scraper").call(run_input=run_input)
73
74# Fetch and print Actor results from the run's dataset (if there are any)
75print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
76for item in client.dataset(run["defaultDatasetId"]).iterate_items():
77    print(item)
78
79# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start