Profesia.sk Scraper

1import { ApifyClient } from 'apify-client';
2
3// Initialize the ApifyClient with your Apify API token
4// Replace the '<YOUR_API_TOKEN>' with your token
5const client = new ApifyClient({
6    token: '<YOUR_API_TOKEN>',
7});
8
9// Prepare Actor input
10const input = {
11    "datasetType": "jobOffers",
12    "jobOfferFilterMinSalaryPeriod": "month",
13    "inputExtendFromFunction": `/**
14         * Inputs:
15         *
16         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
17         * `ctx.input` - The input object that was passed to this Actor.
18         * `ctx.state` - An object you can use to persist state across all your custom functions.
19         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
20         *                       See https://crawlee.dev/docs/guides/got-scraping
21         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
22         *                        It takes the entry itself, and a list of properties to be used for hashing.
23         *                        By default, you should pass `input.cachePrimaryKeys` to it.
24         *
25         */
26        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
27        //   // Example: Load Actor config from GitHub URL (public)
28        //   const config = await sendRequest.get('https://raw.githubusercontent.com/username/project/main/config.json').json();
29        //   
30        //   // Increase concurrency during off-peak hours
31        //   // NOTE: Imagine we're targetting a small server, that can be slower during the day
32        //   const hours = new Date().getUTCHours();
33        //   const isOffPeak = hours < 6 || hours > 20;
34        //   config.maxConcurrency = isOffPeak ? 8 : 3;
35        //   
36        //   return config;
37        //
38        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
39        //
40        //   /**
41        //    * ======= ACCESSING DATASET ========
42        //    * To save/load/access entries in Dataset.
43        //    * Docs:
44        //    * - https://docs.apify.com/platform/storage/dataset
45        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
46        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
47        //    */
48        //   // const dataset = await io.openDataset('MyDatasetId');
49        //   // const info = await dataset.getInfo();
50        //   // console.log(info.itemCount);
51        //   // // => 0
52        //
53        //   /**
54        //    * ======= ACCESSING REMOTE DATA ========
55        //    * Use `sendRequest` to get data from the internet:
56        //    * Docs:
57        //    * - https://github.com/apify/got-scraping
58        //    */
59        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
60        //   // console.log(catFact.text);
61        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
62        //
63        //   /**
64        //    * ======= USING CACHE ========
65        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
66        //    * `itemCacheKey` to create the entry's ID for you:
67        //    */
68        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
69        //   // const cache = await io.openKeyValueStore('MyStoreId');
70        //   // cache.setValue(cacheId, entry);
71        // };`,
72    "startUrlsFromFunction": `/**
73         * Inputs:
74         *
75         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
76         * `ctx.input` - The input object that was passed to this Actor.
77         * `ctx.state` - An object you can use to persist state across all your custom functions.
78         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
79         *                       See https://crawlee.dev/docs/guides/got-scraping
80         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
81         *                        It takes the entry itself, and a list of properties to be used for hashing.
82         *                        By default, you should pass `input.cachePrimaryKeys` to it.
83         *
84         */
85        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
86        //   // Example: Create and load URLs from a Dataset by combining multiple fields
87        //   const dataset = await io.openDataset(datasetNameOrId);
88        //   const data = await dataset.getData();
89        //   const urls = data.items.map((item) => `https://example.com/u/${item.userId}/list/${item.listId}`);
90        //   return urls;
91        //
92        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
93        //
94        //   /**
95        //    * ======= ACCESSING DATASET ========
96        //    * To save/load/access entries in Dataset.
97        //    * Docs:
98        //    * - https://docs.apify.com/platform/storage/dataset
99        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
100        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
101        //    */
102        //   // const dataset = await io.openDataset('MyDatasetId');
103        //   // const info = await dataset.getInfo();
104        //   // console.log(info.itemCount);
105        //   // // => 0
106        //
107        //   /**
108        //    * ======= ACCESSING REMOTE DATA ========
109        //    * Use `sendRequest` to get data from the internet:
110        //    * Docs:
111        //    * - https://github.com/apify/got-scraping
112        //    */
113        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
114        //   // console.log(catFact.text);
115        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
116        //
117        //   /**
118        //    * ======= USING CACHE ========
119        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
120        //    * `itemCacheKey` to create the entry's ID for you:
121        //    */
122        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
123        //   // const cache = await io.openKeyValueStore('MyStoreId');
124        //   // cache.setValue(cacheId, entry);
125        // };`,
126    "requestMaxEntries": 50,
127    "requestTransform": `/**
128         * Inputs:
129         * `request` - Request holding URL to be scraped.
130         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
131         * `ctx.input` - The input object that was passed to this Actor.
132         * `ctx.state` - An object you can use to persist state across all your custom functions.
133         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
134         *                       See https://crawlee.dev/docs/guides/got-scraping
135         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
136         *                        It takes the entry itself, and a list of properties to be used for hashing.
137         *                        By default, you should pass `input.cachePrimaryKeys` to it.
138         *
139         */
140        // async (request, { io, input, state, sendRequest, itemCacheKey }) => {
141        //   // Example: Tag requests
142        //   // (maybe because we use RequestQueue that pools multiple scrapers)
143        //   request.userData.tag = "VARIANT_A";
144        //   return requestQueue;
145        //
146        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
147        //
148        //   /**
149        //    * ======= ACCESSING DATASET ========
150        //    * To save/load/access entries in Dataset.
151        //    * Docs:
152        //    * - https://docs.apify.com/platform/storage/dataset
153        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
154        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
155        //    */
156        //   // const dataset = await io.openDataset('MyDatasetId');
157        //   // const info = await dataset.getInfo();
158        //   // console.log(info.itemCount);
159        //   // // => 0
160        //
161        //   /**
162        //    * ======= ACCESSING REMOTE DATA ========
163        //    * Use `sendRequest` to get data from the internet:
164        //    * Docs:
165        //    * - https://github.com/apify/got-scraping
166        //    */
167        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
168        //   // console.log(catFact.text);
169        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
170        //
171        //   /**
172        //    * ======= USING CACHE ========
173        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
174        //    * `itemCacheKey` to create the entry's ID for you:
175        //    */
176        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
177        //   // const cache = await io.openKeyValueStore('MyStoreId');
178        //   // cache.setValue(cacheId, entry);
179        // };`,
180    "requestTransformBefore": `/**
181         * Inputs:
182         *
183         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
184         * `ctx.input` - The input object that was passed to this Actor.
185         * `ctx.state` - An object you can use to persist state across all your custom functions.
186         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
187         *                       See https://crawlee.dev/docs/guides/got-scraping
188         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
189         *                        It takes the entry itself, and a list of properties to be used for hashing.
190         *                        By default, you should pass `input.cachePrimaryKeys` to it.
191         *
192         */
193        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
194        //   // Example: Fetch data or run code BEFORE requests are processed.
195        //   state.categories = await sendRequest.get('https://example.com/my-categories').json();
196        //
197        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
198        //
199        //   /**
200        //    * ======= ACCESSING DATASET ========
201        //    * To save/load/access entries in Dataset.
202        //    * Docs:
203        //    * - https://docs.apify.com/platform/storage/dataset
204        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
205        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
206        //    */
207        //   // const dataset = await io.openDataset('MyDatasetId');
208        //   // const info = await dataset.getInfo();
209        //   // console.log(info.itemCount);
210        //   // // => 0
211        //
212        //   /**
213        //    * ======= ACCESSING REMOTE DATA ========
214        //    * Use `sendRequest` to get data from the internet:
215        //    * Docs:
216        //    * - https://github.com/apify/got-scraping
217        //    */
218        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
219        //   // console.log(catFact.text);
220        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
221        //
222        //   /**
223        //    * ======= USING CACHE ========
224        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
225        //    * `itemCacheKey` to create the entry's ID for you:
226        //    */
227        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
228        //   // const cache = await io.openKeyValueStore('MyStoreId');
229        //   // cache.setValue(cacheId, entry);
230        // };`,
231    "requestTransformAfter": `/**
232         * Inputs:
233         *
234         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
235         * `ctx.input` - The input object that was passed to this Actor.
236         * `ctx.state` - An object you can use to persist state across all your custom functions.
237         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
238         *                       See https://crawlee.dev/docs/guides/got-scraping
239         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
240         *                        It takes the entry itself, and a list of properties to be used for hashing.
241         *                        By default, you should pass `input.cachePrimaryKeys` to it.
242         *
243         */
244        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
245        //   // Example: Fetch data or run code AFTER requests are processed.
246        //   delete state.categories;
247        //
248        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
249        //
250        //   /**
251        //    * ======= ACCESSING DATASET ========
252        //    * To save/load/access entries in Dataset.
253        //    * Docs:
254        //    * - https://docs.apify.com/platform/storage/dataset
255        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
256        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
257        //    */
258        //   // const dataset = await io.openDataset('MyDatasetId');
259        //   // const info = await dataset.getInfo();
260        //   // console.log(info.itemCount);
261        //   // // => 0
262        //
263        //   /**
264        //    * ======= ACCESSING REMOTE DATA ========
265        //    * Use `sendRequest` to get data from the internet:
266        //    * Docs:
267        //    * - https://github.com/apify/got-scraping
268        //    */
269        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
270        //   // console.log(catFact.text);
271        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
272        //
273        //   /**
274        //    * ======= USING CACHE ========
275        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
276        //    * `itemCacheKey` to create the entry's ID for you:
277        //    */
278        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
279        //   // const cache = await io.openKeyValueStore('MyStoreId');
280        //   // cache.setValue(cacheId, entry);
281        // };`,
282    "requestFilter": `/**
283         * Inputs:
284         * `request` - Request holding URL to be scraped.
285         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
286         * `ctx.input` - The input object that was passed to this Actor.
287         * `ctx.state` - An object you can use to persist state across all your custom functions.
288         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
289         *                       See https://crawlee.dev/docs/guides/got-scraping
290         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
291         *                        It takes the entry itself, and a list of properties to be used for hashing.
292         *                        By default, you should pass `input.cachePrimaryKeys` to it.
293         *
294         */
295        // async (request, { io, input, state, sendRequest, itemCacheKey }) => {
296        //   // Example: Filter requests based on their tag
297        //   // (maybe because we use RequestQueue that pools multiple scrapers)
298        //   return request.userData.tag === "VARIANT_A";
299        //
300        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
301        //
302        //   /**
303        //    * ======= ACCESSING DATASET ========
304        //    * To save/load/access entries in Dataset.
305        //    * Docs:
306        //    * - https://docs.apify.com/platform/storage/dataset
307        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
308        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
309        //    */
310        //   // const dataset = await io.openDataset('MyDatasetId');
311        //   // const info = await dataset.getInfo();
312        //   // console.log(info.itemCount);
313        //   // // => 0
314        //
315        //   /**
316        //    * ======= ACCESSING REMOTE DATA ========
317        //    * Use `sendRequest` to get data from the internet:
318        //    * Docs:
319        //    * - https://github.com/apify/got-scraping
320        //    */
321        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
322        //   // console.log(catFact.text);
323        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
324        //
325        //   /**
326        //    * ======= USING CACHE ========
327        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
328        //    * `itemCacheKey` to create the entry's ID for you:
329        //    */
330        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
331        //   // const cache = await io.openKeyValueStore('MyStoreId');
332        //   // cache.setValue(cacheId, entry);
333        // };`,
334    "requestFilterBefore": `/**
335         * Inputs:
336         *
337         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
338         * `ctx.input` - The input object that was passed to this Actor.
339         * `ctx.state` - An object you can use to persist state across all your custom functions.
340         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
341         *                       See https://crawlee.dev/docs/guides/got-scraping
342         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
343         *                        It takes the entry itself, and a list of properties to be used for hashing.
344         *                        By default, you should pass `input.cachePrimaryKeys` to it.
345         *
346         */
347        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
348        //   // Example: Fetch data or run code BEFORE requests are processed.
349        //   state.categories = await sendRequest.get('https://example.com/my-categories').json();
350        //
351        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
352        //
353        //   /**
354        //    * ======= ACCESSING DATASET ========
355        //    * To save/load/access entries in Dataset.
356        //    * Docs:
357        //    * - https://docs.apify.com/platform/storage/dataset
358        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
359        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
360        //    */
361        //   // const dataset = await io.openDataset('MyDatasetId');
362        //   // const info = await dataset.getInfo();
363        //   // console.log(info.itemCount);
364        //   // // => 0
365        //
366        //   /**
367        //    * ======= ACCESSING REMOTE DATA ========
368        //    * Use `sendRequest` to get data from the internet:
369        //    * Docs:
370        //    * - https://github.com/apify/got-scraping
371        //    */
372        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
373        //   // console.log(catFact.text);
374        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
375        //
376        //   /**
377        //    * ======= USING CACHE ========
378        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
379        //    * `itemCacheKey` to create the entry's ID for you:
380        //    */
381        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
382        //   // const cache = await io.openKeyValueStore('MyStoreId');
383        //   // cache.setValue(cacheId, entry);
384        // };`,
385    "requestFilterAfter": `/**
386         * Inputs:
387         *
388         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
389         * `ctx.input` - The input object that was passed to this Actor.
390         * `ctx.state` - An object you can use to persist state across all your custom functions.
391         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
392         *                       See https://crawlee.dev/docs/guides/got-scraping
393         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
394         *                        It takes the entry itself, and a list of properties to be used for hashing.
395         *                        By default, you should pass `input.cachePrimaryKeys` to it.
396         *
397         */
398        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
399        //   // Example: Fetch data or run code AFTER requests are processed.
400        //   delete state.categories;
401        //
402        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
403        //
404        //   /**
405        //    * ======= ACCESSING DATASET ========
406        //    * To save/load/access entries in Dataset.
407        //    * Docs:
408        //    * - https://docs.apify.com/platform/storage/dataset
409        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
410        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
411        //    */
412        //   // const dataset = await io.openDataset('MyDatasetId');
413        //   // const info = await dataset.getInfo();
414        //   // console.log(info.itemCount);
415        //   // // => 0
416        //
417        //   /**
418        //    * ======= ACCESSING REMOTE DATA ========
419        //    * Use `sendRequest` to get data from the internet:
420        //    * Docs:
421        //    * - https://github.com/apify/got-scraping
422        //    */
423        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
424        //   // console.log(catFact.text);
425        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
426        //
427        //   /**
428        //    * ======= USING CACHE ========
429        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
430        //    * `itemCacheKey` to create the entry's ID for you:
431        //    */
432        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
433        //   // const cache = await io.openKeyValueStore('MyStoreId');
434        //   // cache.setValue(cacheId, entry);
435        // };`,
436    "outputMaxEntries": 50,
437    "outputTransform": `/**
438         * Inputs:
439         * `entry` - Scraped entry.
440         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
441         * `ctx.input` - The input object that was passed to this Actor.
442         * `ctx.state` - An object you can use to persist state across all your custom functions.
443         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
444         *                       See https://crawlee.dev/docs/guides/got-scraping
445         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
446         *                        It takes the entry itself, and a list of properties to be used for hashing.
447         *                        By default, you should pass `input.cachePrimaryKeys` to it.
448         *
449         */
450        // async (entry, { io, input, state, sendRequest, itemCacheKey }) => {
451        //   // Example: Add extra custom fields like aggregates
452        //   return {
453        //     ...entry,
454        //     imagesCount: entry.images.length,
455        //   };
456        //
457        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
458        //
459        //   /**
460        //    * ======= ACCESSING DATASET ========
461        //    * To save/load/access entries in Dataset.
462        //    * Docs:
463        //    * - https://docs.apify.com/platform/storage/dataset
464        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
465        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
466        //    */
467        //   // const dataset = await io.openDataset('MyDatasetId');
468        //   // const info = await dataset.getInfo();
469        //   // console.log(info.itemCount);
470        //   // // => 0
471        //
472        //   /**
473        //    * ======= ACCESSING REMOTE DATA ========
474        //    * Use `sendRequest` to get data from the internet:
475        //    * Docs:
476        //    * - https://github.com/apify/got-scraping
477        //    */
478        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
479        //   // console.log(catFact.text);
480        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
481        //
482        //   /**
483        //    * ======= USING CACHE ========
484        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
485        //    * `itemCacheKey` to create the entry's ID for you:
486        //    */
487        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
488        //   // const cache = await io.openKeyValueStore('MyStoreId');
489        //   // cache.setValue(cacheId, entry);
490        // };`,
491    "outputTransformBefore": `/**
492         * Inputs:
493         *
494         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
495         * `ctx.input` - The input object that was passed to this Actor.
496         * `ctx.state` - An object you can use to persist state across all your custom functions.
497         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
498         *                       See https://crawlee.dev/docs/guides/got-scraping
499         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
500         *                        It takes the entry itself, and a list of properties to be used for hashing.
501         *                        By default, you should pass `input.cachePrimaryKeys` to it.
502         *
503         */
504        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
505        //   // Example: Fetch data or run code BEFORE entries are scraped.
506        //   state.categories = await sendRequest.get('https://example.com/my-categories').json();
507        //
508        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
509        //
510        //   /**
511        //    * ======= ACCESSING DATASET ========
512        //    * To save/load/access entries in Dataset.
513        //    * Docs:
514        //    * - https://docs.apify.com/platform/storage/dataset
515        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
516        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
517        //    */
518        //   // const dataset = await io.openDataset('MyDatasetId');
519        //   // const info = await dataset.getInfo();
520        //   // console.log(info.itemCount);
521        //   // // => 0
522        //
523        //   /**
524        //    * ======= ACCESSING REMOTE DATA ========
525        //    * Use `sendRequest` to get data from the internet:
526        //    * Docs:
527        //    * - https://github.com/apify/got-scraping
528        //    */
529        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
530        //   // console.log(catFact.text);
531        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
532        //
533        //   /**
534        //    * ======= USING CACHE ========
535        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
536        //    * `itemCacheKey` to create the entry's ID for you:
537        //    */
538        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
539        //   // const cache = await io.openKeyValueStore('MyStoreId');
540        //   // cache.setValue(cacheId, entry);
541        // };`,
542    "outputTransformAfter": `/**
543         * Inputs:
544         *
545         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
546         * `ctx.input` - The input object that was passed to this Actor.
547         * `ctx.state` - An object you can use to persist state across all your custom functions.
548         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
549         *                       See https://crawlee.dev/docs/guides/got-scraping
550         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
551         *                        It takes the entry itself, and a list of properties to be used for hashing.
552         *                        By default, you should pass `input.cachePrimaryKeys` to it.
553         *
554         */
555        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
556        //   // Example: Fetch data or run code AFTER entries are scraped.
557        //   delete state.categories;
558        //
559        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
560        //
561        //   /**
562        //    * ======= ACCESSING DATASET ========
563        //    * To save/load/access entries in Dataset.
564        //    * Docs:
565        //    * - https://docs.apify.com/platform/storage/dataset
566        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
567        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
568        //    */
569        //   // const dataset = await io.openDataset('MyDatasetId');
570        //   // const info = await dataset.getInfo();
571        //   // console.log(info.itemCount);
572        //   // // => 0
573        //
574        //   /**
575        //    * ======= ACCESSING REMOTE DATA ========
576        //    * Use `sendRequest` to get data from the internet:
577        //    * Docs:
578        //    * - https://github.com/apify/got-scraping
579        //    */
580        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
581        //   // console.log(catFact.text);
582        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
583        //
584        //   /**
585        //    * ======= USING CACHE ========
586        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
587        //    * `itemCacheKey` to create the entry's ID for you:
588        //    */
589        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
590        //   // const cache = await io.openKeyValueStore('MyStoreId');
591        //   // cache.setValue(cacheId, entry);
592        // };`,
593    "outputFilter": `/**
594         * Inputs:
595         * `entry` - Scraped entry.
596         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
597         * `ctx.input` - The input object that was passed to this Actor.
598         * `ctx.state` - An object you can use to persist state across all your custom functions.
599         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
600         *                       See https://crawlee.dev/docs/guides/got-scraping
601         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
602         *                        It takes the entry itself, and a list of properties to be used for hashing.
603         *                        By default, you should pass `input.cachePrimaryKeys` to it.
604         *
605         */
606        // async (entry, { io, input, state, sendRequest, itemCacheKey }) => {
607        //   // Example: Filter entries based on number of images they have (at least 5)
608        //   return entry.images.length > 5;
609        //
610        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
611        //
612        //   /**
613        //    * ======= ACCESSING DATASET ========
614        //    * To save/load/access entries in Dataset.
615        //    * Docs:
616        //    * - https://docs.apify.com/platform/storage/dataset
617        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
618        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
619        //    */
620        //   // const dataset = await io.openDataset('MyDatasetId');
621        //   // const info = await dataset.getInfo();
622        //   // console.log(info.itemCount);
623        //   // // => 0
624        //
625        //   /**
626        //    * ======= ACCESSING REMOTE DATA ========
627        //    * Use `sendRequest` to get data from the internet:
628        //    * Docs:
629        //    * - https://github.com/apify/got-scraping
630        //    */
631        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
632        //   // console.log(catFact.text);
633        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
634        //
635        //   /**
636        //    * ======= USING CACHE ========
637        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
638        //    * `itemCacheKey` to create the entry's ID for you:
639        //    */
640        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
641        //   // const cache = await io.openKeyValueStore('MyStoreId');
642        //   // cache.setValue(cacheId, entry);
643        // };`,
644    "outputFilterBefore": `/**
645         * Inputs:
646         *
647         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
648         * `ctx.input` - The input object that was passed to this Actor.
649         * `ctx.state` - An object you can use to persist state across all your custom functions.
650         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
651         *                       See https://crawlee.dev/docs/guides/got-scraping
652         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
653         *                        It takes the entry itself, and a list of properties to be used for hashing.
654         *                        By default, you should pass `input.cachePrimaryKeys` to it.
655         *
656         */
657        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
658        //   // Example: Fetch data or run code BEFORE entries are scraped.
659        //   state.categories = await sendRequest.get('https://example.com/my-categories').json();
660        //
661        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
662        //
663        //   /**
664        //    * ======= ACCESSING DATASET ========
665        //    * To save/load/access entries in Dataset.
666        //    * Docs:
667        //    * - https://docs.apify.com/platform/storage/dataset
668        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
669        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
670        //    */
671        //   // const dataset = await io.openDataset('MyDatasetId');
672        //   // const info = await dataset.getInfo();
673        //   // console.log(info.itemCount);
674        //   // // => 0
675        //
676        //   /**
677        //    * ======= ACCESSING REMOTE DATA ========
678        //    * Use `sendRequest` to get data from the internet:
679        //    * Docs:
680        //    * - https://github.com/apify/got-scraping
681        //    */
682        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
683        //   // console.log(catFact.text);
684        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
685        //
686        //   /**
687        //    * ======= USING CACHE ========
688        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
689        //    * `itemCacheKey` to create the entry's ID for you:
690        //    */
691        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
692        //   // const cache = await io.openKeyValueStore('MyStoreId');
693        //   // cache.setValue(cacheId, entry);
694        // };`,
695    "outputFilterAfter": `/**
696         * Inputs:
697         *
698         * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
699         * `ctx.input` - The input object that was passed to this Actor.
700         * `ctx.state` - An object you can use to persist state across all your custom functions.
701         * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
702         *                       See https://crawlee.dev/docs/guides/got-scraping
703         * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
704         *                        It takes the entry itself, and a list of properties to be used for hashing.
705         *                        By default, you should pass `input.cachePrimaryKeys` to it.
706         *
707         */
708        // async ({ io, input, state, sendRequest, itemCacheKey }) => {
709        //   // Example: Fetch data or run code AFTER entries are scraped.
710        //   delete state.categories;
711        //
712        //   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
713        //
714        //   /**
715        //    * ======= ACCESSING DATASET ========
716        //    * To save/load/access entries in Dataset.
717        //    * Docs:
718        //    * - https://docs.apify.com/platform/storage/dataset
719        //    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
720        //    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
721        //    */
722        //   // const dataset = await io.openDataset('MyDatasetId');
723        //   // const info = await dataset.getInfo();
724        //   // console.log(info.itemCount);
725        //   // // => 0
726        //
727        //   /**
728        //    * ======= ACCESSING REMOTE DATA ========
729        //    * Use `sendRequest` to get data from the internet:
730        //    * Docs:
731        //    * - https://github.com/apify/got-scraping
732        //    */
733        //   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
734        //   // console.log(catFact.text);
735        //   // // => "Cats make about 100 different sounds. Dogs make only about 10.",
736        //
737        //   /**
738        //    * ======= USING CACHE ========
739        //    * To save the entry to the KeyValue cache (or retrieve it), you can use
740        //    * `itemCacheKey` to create the entry's ID for you:
741        //    */
742        //   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
743        //   // const cache = await io.openKeyValueStore('MyStoreId');
744        //   // cache.setValue(cacheId, entry);
745        // };`,
746    "maxRequestRetries": 3,
747    "maxRequestsPerMinute": 120,
748    "minConcurrency": 1,
749    "requestHandlerTimeoutSecs": 180,
750    "logLevel": "info",
751    "errorReportingDatasetId": "REPORTING"
752};
753
754// Run the Actor and wait for it to finish
755const run = await client.actor("jurooravec/profesia-sk-scraper").call(input);
756
757// Fetch and print Actor results from the run's dataset (if any)
758console.log('Results from dataset');
759console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
760const { items } = await client.dataset(run.defaultDatasetId).listItems();
761items.forEach((item) => {
762    console.dir(item);
763});
764
765// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs