Profesia.sk Scraper

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4client = ApifyClient("<YOUR_API_TOKEN>")
5
6# Prepare the Actor input
7run_input = {
8    "datasetType": "jobOffers",
9    "jobOfferFilterMinSalaryPeriod": "month",
10    "inputExtendFromFunction": """
11/**
12 * Inputs:
13 *
14 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
15 * `ctx.input` - The input object that was passed to this Actor.
16 * `ctx.state` - An object you can use to persist state across all your custom functions.
17 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
18 *                       See https://crawlee.dev/docs/guides/got-scraping
19 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
20 *                        It takes the entry itself, and a list of properties to be used for hashing.
21 *                        By default, you should pass `input.cachePrimaryKeys` to it.
22 *
23 */
24// async ({ io, input, state, sendRequest, itemCacheKey }) => {
25//   // Example: Load Actor config from GitHub URL (public)
26//   const config = await sendRequest.get('https://raw.githubusercontent.com/username/project/main/config.json').json();
27//   
28//   // Increase concurrency during off-peak hours
29//   // NOTE: Imagine we're targetting a small server, that can be slower during the day
30//   const hours = new Date().getUTCHours();
31//   const isOffPeak = hours < 6 || hours > 20;
32//   config.maxConcurrency = isOffPeak ? 8 : 3;
33//   
34//   return config;
35//
36//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
37//
38//   /**
39//    * ======= ACCESSING DATASET ========
40//    * To save/load/access entries in Dataset.
41//    * Docs:
42//    * - https://docs.apify.com/platform/storage/dataset
43//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
44//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
45//    */
46//   // const dataset = await io.openDataset('MyDatasetId');
47//   // const info = await dataset.getInfo();
48//   // console.log(info.itemCount);
49//   // // => 0
50//
51//   /**
52//    * ======= ACCESSING REMOTE DATA ========
53//    * Use `sendRequest` to get data from the internet:
54//    * Docs:
55//    * - https://github.com/apify/got-scraping
56//    */
57//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
58//   // console.log(catFact.text);
59//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
60//
61//   /**
62//    * ======= USING CACHE ========
63//    * To save the entry to the KeyValue cache (or retrieve it), you can use
64//    * `itemCacheKey` to create the entry's ID for you:
65//    */
66//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
67//   // const cache = await io.openKeyValueStore('MyStoreId');
68//   // cache.setValue(cacheId, entry);
69// };""",
70    "startUrlsFromFunction": """
71/**
72 * Inputs:
73 *
74 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
75 * `ctx.input` - The input object that was passed to this Actor.
76 * `ctx.state` - An object you can use to persist state across all your custom functions.
77 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
78 *                       See https://crawlee.dev/docs/guides/got-scraping
79 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
80 *                        It takes the entry itself, and a list of properties to be used for hashing.
81 *                        By default, you should pass `input.cachePrimaryKeys` to it.
82 *
83 */
84// async ({ io, input, state, sendRequest, itemCacheKey }) => {
85//   // Example: Create and load URLs from a Dataset by combining multiple fields
86//   const dataset = await io.openDataset(datasetNameOrId);
87//   const data = await dataset.getData();
88//   const urls = data.items.map((item) => `https://example.com/u/${item.userId}/list/${item.listId}`);
89//   return urls;
90//
91//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
92//
93//   /**
94//    * ======= ACCESSING DATASET ========
95//    * To save/load/access entries in Dataset.
96//    * Docs:
97//    * - https://docs.apify.com/platform/storage/dataset
98//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
99//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
100//    */
101//   // const dataset = await io.openDataset('MyDatasetId');
102//   // const info = await dataset.getInfo();
103//   // console.log(info.itemCount);
104//   // // => 0
105//
106//   /**
107//    * ======= ACCESSING REMOTE DATA ========
108//    * Use `sendRequest` to get data from the internet:
109//    * Docs:
110//    * - https://github.com/apify/got-scraping
111//    */
112//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
113//   // console.log(catFact.text);
114//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
115//
116//   /**
117//    * ======= USING CACHE ========
118//    * To save the entry to the KeyValue cache (or retrieve it), you can use
119//    * `itemCacheKey` to create the entry's ID for you:
120//    */
121//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
122//   // const cache = await io.openKeyValueStore('MyStoreId');
123//   // cache.setValue(cacheId, entry);
124// };""",
125    "requestMaxEntries": 50,
126    "requestTransform": """
127/**
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/**
182 * Inputs:
183 *
184 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
185 * `ctx.input` - The input object that was passed to this Actor.
186 * `ctx.state` - An object you can use to persist state across all your custom functions.
187 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
188 *                       See https://crawlee.dev/docs/guides/got-scraping
189 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
190 *                        It takes the entry itself, and a list of properties to be used for hashing.
191 *                        By default, you should pass `input.cachePrimaryKeys` to it.
192 *
193 */
194// async ({ io, input, state, sendRequest, itemCacheKey }) => {
195//   // Example: Fetch data or run code BEFORE requests are processed.
196//   state.categories = await sendRequest.get('https://example.com/my-categories').json();
197//
198//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
199//
200//   /**
201//    * ======= ACCESSING DATASET ========
202//    * To save/load/access entries in Dataset.
203//    * Docs:
204//    * - https://docs.apify.com/platform/storage/dataset
205//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
206//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
207//    */
208//   // const dataset = await io.openDataset('MyDatasetId');
209//   // const info = await dataset.getInfo();
210//   // console.log(info.itemCount);
211//   // // => 0
212//
213//   /**
214//    * ======= ACCESSING REMOTE DATA ========
215//    * Use `sendRequest` to get data from the internet:
216//    * Docs:
217//    * - https://github.com/apify/got-scraping
218//    */
219//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
220//   // console.log(catFact.text);
221//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
222//
223//   /**
224//    * ======= USING CACHE ========
225//    * To save the entry to the KeyValue cache (or retrieve it), you can use
226//    * `itemCacheKey` to create the entry's ID for you:
227//    */
228//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
229//   // const cache = await io.openKeyValueStore('MyStoreId');
230//   // cache.setValue(cacheId, entry);
231// };""",
232    "requestTransformAfter": """
233/**
234 * Inputs:
235 *
236 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
237 * `ctx.input` - The input object that was passed to this Actor.
238 * `ctx.state` - An object you can use to persist state across all your custom functions.
239 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
240 *                       See https://crawlee.dev/docs/guides/got-scraping
241 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
242 *                        It takes the entry itself, and a list of properties to be used for hashing.
243 *                        By default, you should pass `input.cachePrimaryKeys` to it.
244 *
245 */
246// async ({ io, input, state, sendRequest, itemCacheKey }) => {
247//   // Example: Fetch data or run code AFTER requests are processed.
248//   delete state.categories;
249//
250//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
251//
252//   /**
253//    * ======= ACCESSING DATASET ========
254//    * To save/load/access entries in Dataset.
255//    * Docs:
256//    * - https://docs.apify.com/platform/storage/dataset
257//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
258//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
259//    */
260//   // const dataset = await io.openDataset('MyDatasetId');
261//   // const info = await dataset.getInfo();
262//   // console.log(info.itemCount);
263//   // // => 0
264//
265//   /**
266//    * ======= ACCESSING REMOTE DATA ========
267//    * Use `sendRequest` to get data from the internet:
268//    * Docs:
269//    * - https://github.com/apify/got-scraping
270//    */
271//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
272//   // console.log(catFact.text);
273//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
274//
275//   /**
276//    * ======= USING CACHE ========
277//    * To save the entry to the KeyValue cache (or retrieve it), you can use
278//    * `itemCacheKey` to create the entry's ID for you:
279//    */
280//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
281//   // const cache = await io.openKeyValueStore('MyStoreId');
282//   // cache.setValue(cacheId, entry);
283// };""",
284    "requestFilter": """
285/**
286 * Inputs:
287 * `request` - Request holding URL to be scraped.
288 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
289 * `ctx.input` - The input object that was passed to this Actor.
290 * `ctx.state` - An object you can use to persist state across all your custom functions.
291 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
292 *                       See https://crawlee.dev/docs/guides/got-scraping
293 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
294 *                        It takes the entry itself, and a list of properties to be used for hashing.
295 *                        By default, you should pass `input.cachePrimaryKeys` to it.
296 *
297 */
298// async (request, { io, input, state, sendRequest, itemCacheKey }) => {
299//   // Example: Filter requests based on their tag
300//   // (maybe because we use RequestQueue that pools multiple scrapers)
301//   return request.userData.tag === \"VARIANT_A\";
302//
303//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
304//
305//   /**
306//    * ======= ACCESSING DATASET ========
307//    * To save/load/access entries in Dataset.
308//    * Docs:
309//    * - https://docs.apify.com/platform/storage/dataset
310//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
311//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
312//    */
313//   // const dataset = await io.openDataset('MyDatasetId');
314//   // const info = await dataset.getInfo();
315//   // console.log(info.itemCount);
316//   // // => 0
317//
318//   /**
319//    * ======= ACCESSING REMOTE DATA ========
320//    * Use `sendRequest` to get data from the internet:
321//    * Docs:
322//    * - https://github.com/apify/got-scraping
323//    */
324//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
325//   // console.log(catFact.text);
326//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
327//
328//   /**
329//    * ======= USING CACHE ========
330//    * To save the entry to the KeyValue cache (or retrieve it), you can use
331//    * `itemCacheKey` to create the entry's ID for you:
332//    */
333//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
334//   // const cache = await io.openKeyValueStore('MyStoreId');
335//   // cache.setValue(cacheId, entry);
336// };""",
337    "requestFilterBefore": """
338/**
339 * Inputs:
340 *
341 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
342 * `ctx.input` - The input object that was passed to this Actor.
343 * `ctx.state` - An object you can use to persist state across all your custom functions.
344 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
345 *                       See https://crawlee.dev/docs/guides/got-scraping
346 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
347 *                        It takes the entry itself, and a list of properties to be used for hashing.
348 *                        By default, you should pass `input.cachePrimaryKeys` to it.
349 *
350 */
351// async ({ io, input, state, sendRequest, itemCacheKey }) => {
352//   // Example: Fetch data or run code BEFORE requests are processed.
353//   state.categories = await sendRequest.get('https://example.com/my-categories').json();
354//
355//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
356//
357//   /**
358//    * ======= ACCESSING DATASET ========
359//    * To save/load/access entries in Dataset.
360//    * Docs:
361//    * - https://docs.apify.com/platform/storage/dataset
362//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
363//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
364//    */
365//   // const dataset = await io.openDataset('MyDatasetId');
366//   // const info = await dataset.getInfo();
367//   // console.log(info.itemCount);
368//   // // => 0
369//
370//   /**
371//    * ======= ACCESSING REMOTE DATA ========
372//    * Use `sendRequest` to get data from the internet:
373//    * Docs:
374//    * - https://github.com/apify/got-scraping
375//    */
376//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
377//   // console.log(catFact.text);
378//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
379//
380//   /**
381//    * ======= USING CACHE ========
382//    * To save the entry to the KeyValue cache (or retrieve it), you can use
383//    * `itemCacheKey` to create the entry's ID for you:
384//    */
385//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
386//   // const cache = await io.openKeyValueStore('MyStoreId');
387//   // cache.setValue(cacheId, entry);
388// };""",
389    "requestFilterAfter": """
390/**
391 * Inputs:
392 *
393 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
394 * `ctx.input` - The input object that was passed to this Actor.
395 * `ctx.state` - An object you can use to persist state across all your custom functions.
396 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
397 *                       See https://crawlee.dev/docs/guides/got-scraping
398 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
399 *                        It takes the entry itself, and a list of properties to be used for hashing.
400 *                        By default, you should pass `input.cachePrimaryKeys` to it.
401 *
402 */
403// async ({ io, input, state, sendRequest, itemCacheKey }) => {
404//   // Example: Fetch data or run code AFTER requests are processed.
405//   delete state.categories;
406//
407//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
408//
409//   /**
410//    * ======= ACCESSING DATASET ========
411//    * To save/load/access entries in Dataset.
412//    * Docs:
413//    * - https://docs.apify.com/platform/storage/dataset
414//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
415//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
416//    */
417//   // const dataset = await io.openDataset('MyDatasetId');
418//   // const info = await dataset.getInfo();
419//   // console.log(info.itemCount);
420//   // // => 0
421//
422//   /**
423//    * ======= ACCESSING REMOTE DATA ========
424//    * Use `sendRequest` to get data from the internet:
425//    * Docs:
426//    * - https://github.com/apify/got-scraping
427//    */
428//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
429//   // console.log(catFact.text);
430//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
431//
432//   /**
433//    * ======= USING CACHE ========
434//    * To save the entry to the KeyValue cache (or retrieve it), you can use
435//    * `itemCacheKey` to create the entry's ID for you:
436//    */
437//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
438//   // const cache = await io.openKeyValueStore('MyStoreId');
439//   // cache.setValue(cacheId, entry);
440// };""",
441    "outputMaxEntries": 50,
442    "outputTransform": """
443/**
444 * Inputs:
445 * `entry` - Scraped entry.
446 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
447 * `ctx.input` - The input object that was passed to this Actor.
448 * `ctx.state` - An object you can use to persist state across all your custom functions.
449 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
450 *                       See https://crawlee.dev/docs/guides/got-scraping
451 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
452 *                        It takes the entry itself, and a list of properties to be used for hashing.
453 *                        By default, you should pass `input.cachePrimaryKeys` to it.
454 *
455 */
456// async (entry, { io, input, state, sendRequest, itemCacheKey }) => {
457//   // Example: Add extra custom fields like aggregates
458//   return {
459//     ...entry,
460//     imagesCount: entry.images.length,
461//   };
462//
463//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
464//
465//   /**
466//    * ======= ACCESSING DATASET ========
467//    * To save/load/access entries in Dataset.
468//    * Docs:
469//    * - https://docs.apify.com/platform/storage/dataset
470//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
471//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
472//    */
473//   // const dataset = await io.openDataset('MyDatasetId');
474//   // const info = await dataset.getInfo();
475//   // console.log(info.itemCount);
476//   // // => 0
477//
478//   /**
479//    * ======= ACCESSING REMOTE DATA ========
480//    * Use `sendRequest` to get data from the internet:
481//    * Docs:
482//    * - https://github.com/apify/got-scraping
483//    */
484//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
485//   // console.log(catFact.text);
486//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
487//
488//   /**
489//    * ======= USING CACHE ========
490//    * To save the entry to the KeyValue cache (or retrieve it), you can use
491//    * `itemCacheKey` to create the entry's ID for you:
492//    */
493//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
494//   // const cache = await io.openKeyValueStore('MyStoreId');
495//   // cache.setValue(cacheId, entry);
496// };""",
497    "outputTransformBefore": """
498/**
499 * Inputs:
500 *
501 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
502 * `ctx.input` - The input object that was passed to this Actor.
503 * `ctx.state` - An object you can use to persist state across all your custom functions.
504 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
505 *                       See https://crawlee.dev/docs/guides/got-scraping
506 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
507 *                        It takes the entry itself, and a list of properties to be used for hashing.
508 *                        By default, you should pass `input.cachePrimaryKeys` to it.
509 *
510 */
511// async ({ io, input, state, sendRequest, itemCacheKey }) => {
512//   // Example: Fetch data or run code BEFORE entries are scraped.
513//   state.categories = await sendRequest.get('https://example.com/my-categories').json();
514//
515//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
516//
517//   /**
518//    * ======= ACCESSING DATASET ========
519//    * To save/load/access entries in Dataset.
520//    * Docs:
521//    * - https://docs.apify.com/platform/storage/dataset
522//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
523//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
524//    */
525//   // const dataset = await io.openDataset('MyDatasetId');
526//   // const info = await dataset.getInfo();
527//   // console.log(info.itemCount);
528//   // // => 0
529//
530//   /**
531//    * ======= ACCESSING REMOTE DATA ========
532//    * Use `sendRequest` to get data from the internet:
533//    * Docs:
534//    * - https://github.com/apify/got-scraping
535//    */
536//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
537//   // console.log(catFact.text);
538//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
539//
540//   /**
541//    * ======= USING CACHE ========
542//    * To save the entry to the KeyValue cache (or retrieve it), you can use
543//    * `itemCacheKey` to create the entry's ID for you:
544//    */
545//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
546//   // const cache = await io.openKeyValueStore('MyStoreId');
547//   // cache.setValue(cacheId, entry);
548// };""",
549    "outputTransformAfter": """
550/**
551 * Inputs:
552 *
553 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
554 * `ctx.input` - The input object that was passed to this Actor.
555 * `ctx.state` - An object you can use to persist state across all your custom functions.
556 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
557 *                       See https://crawlee.dev/docs/guides/got-scraping
558 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
559 *                        It takes the entry itself, and a list of properties to be used for hashing.
560 *                        By default, you should pass `input.cachePrimaryKeys` to it.
561 *
562 */
563// async ({ io, input, state, sendRequest, itemCacheKey }) => {
564//   // Example: Fetch data or run code AFTER entries are scraped.
565//   delete state.categories;
566//
567//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
568//
569//   /**
570//    * ======= ACCESSING DATASET ========
571//    * To save/load/access entries in Dataset.
572//    * Docs:
573//    * - https://docs.apify.com/platform/storage/dataset
574//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
575//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
576//    */
577//   // const dataset = await io.openDataset('MyDatasetId');
578//   // const info = await dataset.getInfo();
579//   // console.log(info.itemCount);
580//   // // => 0
581//
582//   /**
583//    * ======= ACCESSING REMOTE DATA ========
584//    * Use `sendRequest` to get data from the internet:
585//    * Docs:
586//    * - https://github.com/apify/got-scraping
587//    */
588//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
589//   // console.log(catFact.text);
590//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
591//
592//   /**
593//    * ======= USING CACHE ========
594//    * To save the entry to the KeyValue cache (or retrieve it), you can use
595//    * `itemCacheKey` to create the entry's ID for you:
596//    */
597//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
598//   // const cache = await io.openKeyValueStore('MyStoreId');
599//   // cache.setValue(cacheId, entry);
600// };""",
601    "outputFilter": """
602/**
603 * Inputs:
604 * `entry` - Scraped entry.
605 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
606 * `ctx.input` - The input object that was passed to this Actor.
607 * `ctx.state` - An object you can use to persist state across all your custom functions.
608 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
609 *                       See https://crawlee.dev/docs/guides/got-scraping
610 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
611 *                        It takes the entry itself, and a list of properties to be used for hashing.
612 *                        By default, you should pass `input.cachePrimaryKeys` to it.
613 *
614 */
615// async (entry, { io, input, state, sendRequest, itemCacheKey }) => {
616//   // Example: Filter entries based on number of images they have (at least 5)
617//   return entry.images.length > 5;
618//
619//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
620//
621//   /**
622//    * ======= ACCESSING DATASET ========
623//    * To save/load/access entries in Dataset.
624//    * Docs:
625//    * - https://docs.apify.com/platform/storage/dataset
626//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
627//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
628//    */
629//   // const dataset = await io.openDataset('MyDatasetId');
630//   // const info = await dataset.getInfo();
631//   // console.log(info.itemCount);
632//   // // => 0
633//
634//   /**
635//    * ======= ACCESSING REMOTE DATA ========
636//    * Use `sendRequest` to get data from the internet:
637//    * Docs:
638//    * - https://github.com/apify/got-scraping
639//    */
640//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
641//   // console.log(catFact.text);
642//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
643//
644//   /**
645//    * ======= USING CACHE ========
646//    * To save the entry to the KeyValue cache (or retrieve it), you can use
647//    * `itemCacheKey` to create the entry's ID for you:
648//    */
649//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
650//   // const cache = await io.openKeyValueStore('MyStoreId');
651//   // cache.setValue(cacheId, entry);
652// };""",
653    "outputFilterBefore": """
654/**
655 * Inputs:
656 *
657 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
658 * `ctx.input` - The input object that was passed to this Actor.
659 * `ctx.state` - An object you can use to persist state across all your custom functions.
660 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
661 *                       See https://crawlee.dev/docs/guides/got-scraping
662 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
663 *                        It takes the entry itself, and a list of properties to be used for hashing.
664 *                        By default, you should pass `input.cachePrimaryKeys` to it.
665 *
666 */
667// async ({ io, input, state, sendRequest, itemCacheKey }) => {
668//   // Example: Fetch data or run code BEFORE entries are scraped.
669//   state.categories = await sendRequest.get('https://example.com/my-categories').json();
670//
671//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
672//
673//   /**
674//    * ======= ACCESSING DATASET ========
675//    * To save/load/access entries in Dataset.
676//    * Docs:
677//    * - https://docs.apify.com/platform/storage/dataset
678//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
679//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
680//    */
681//   // const dataset = await io.openDataset('MyDatasetId');
682//   // const info = await dataset.getInfo();
683//   // console.log(info.itemCount);
684//   // // => 0
685//
686//   /**
687//    * ======= ACCESSING REMOTE DATA ========
688//    * Use `sendRequest` to get data from the internet:
689//    * Docs:
690//    * - https://github.com/apify/got-scraping
691//    */
692//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
693//   // console.log(catFact.text);
694//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
695//
696//   /**
697//    * ======= USING CACHE ========
698//    * To save the entry to the KeyValue cache (or retrieve it), you can use
699//    * `itemCacheKey` to create the entry's ID for you:
700//    */
701//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
702//   // const cache = await io.openKeyValueStore('MyStoreId');
703//   // cache.setValue(cacheId, entry);
704// };""",
705    "outputFilterAfter": """
706/**
707 * Inputs:
708 *
709 * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.
710 * `ctx.input` - The input object that was passed to this Actor.
711 * `ctx.state` - An object you can use to persist state across all your custom functions.
712 * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.
713 *                       See https://crawlee.dev/docs/guides/got-scraping
714 * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.
715 *                        It takes the entry itself, and a list of properties to be used for hashing.
716 *                        By default, you should pass `input.cachePrimaryKeys` to it.
717 *
718 */
719// async ({ io, input, state, sendRequest, itemCacheKey }) => {
720//   // Example: Fetch data or run code AFTER entries are scraped.
721//   delete state.categories;
722//
723//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */
724//
725//   /**
726//    * ======= ACCESSING DATASET ========
727//    * To save/load/access entries in Dataset.
728//    * Docs:
729//    * - https://docs.apify.com/platform/storage/dataset
730//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset
731//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce
732//    */
733//   // const dataset = await io.openDataset('MyDatasetId');
734//   // const info = await dataset.getInfo();
735//   // console.log(info.itemCount);
736//   // // => 0
737//
738//   /**
739//    * ======= ACCESSING REMOTE DATA ========
740//    * Use `sendRequest` to get data from the internet:
741//    * Docs:
742//    * - https://github.com/apify/got-scraping
743//    */
744//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();
745//   // console.log(catFact.text);
746//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",
747//
748//   /**
749//    * ======= USING CACHE ========
750//    * To save the entry to the KeyValue cache (or retrieve it), you can use
751//    * `itemCacheKey` to create the entry's ID for you:
752//    */
753//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);
754//   // const cache = await io.openKeyValueStore('MyStoreId');
755//   // cache.setValue(cacheId, entry);
756// };""",
757    "maxRequestRetries": 3,
758    "maxRequestsPerMinute": 120,
759    "minConcurrency": 1,
760    "requestHandlerTimeoutSecs": 180,
761    "logLevel": "info",
762    "errorReportingDatasetId": "REPORTING",
763}
764
765# Run the Actor and wait for it to finish
766run = client.actor("jurooravec/profesia-sk-scraper").call(run_input=run_input)
767
768# Fetch and print Actor results from the run's dataset (if there are any)
769print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
770for item in client.dataset(run["defaultDatasetId"]).iterate_items():
771    print(item)
772
773# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start