Profesia.sk Scraper

1# Set API token
2API_TOKEN=<YOUR_API_TOKEN>
3
4# Prepare Actor input
5cat > input.json << 'EOF'
6{
7  "datasetType": "jobOffers",
8  "jobOfferFilterMinSalaryPeriod": "month",
9  "inputExtendFromFunction": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Load Actor config from GitHub URL (public)\n//   const config = await sendRequest.get('https://raw.githubusercontent.com/username/project/main/config.json').json();\n//   \n//   // Increase concurrency during off-peak hours\n//   // NOTE: Imagine we're targetting a small server, that can be slower during the day\n//   const hours = new Date().getUTCHours();\n//   const isOffPeak = hours < 6 || hours > 20;\n//   config.maxConcurrency = isOffPeak ? 8 : 3;\n//   \n//   return config;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
10  "startUrlsFromFunction": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Create and load URLs from a Dataset by combining multiple fields\n//   const dataset = await io.openDataset(datasetNameOrId);\n//   const data = await dataset.getData();\n//   const urls = data.items.map((item) => `https://example.com/u/${item.userId}/list/${item.listId}`);\n//   return urls;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
11  "requestMaxEntries": 50,
12  "requestTransform": "\n/**\n * Inputs:\n * `request` - Request holding URL to be scraped.\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async (request, { io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Tag requests\n//   // (maybe because we use RequestQueue that pools multiple scrapers)\n//   request.userData.tag = \"VARIANT_A\";\n//   return requestQueue;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
13  "requestTransformBefore": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code BEFORE requests are processed.\n//   state.categories = await sendRequest.get('https://example.com/my-categories').json();\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
14  "requestTransformAfter": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code AFTER requests are processed.\n//   delete state.categories;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
15  "requestFilter": "\n/**\n * Inputs:\n * `request` - Request holding URL to be scraped.\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async (request, { io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Filter requests based on their tag\n//   // (maybe because we use RequestQueue that pools multiple scrapers)\n//   return request.userData.tag === \"VARIANT_A\";\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
16  "requestFilterBefore": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code BEFORE requests are processed.\n//   state.categories = await sendRequest.get('https://example.com/my-categories').json();\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
17  "requestFilterAfter": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code AFTER requests are processed.\n//   delete state.categories;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
18  "outputMaxEntries": 50,
19  "outputTransform": "\n/**\n * Inputs:\n * `entry` - Scraped entry.\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async (entry, { io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Add extra custom fields like aggregates\n//   return {\n//     ...entry,\n//     imagesCount: entry.images.length,\n//   };\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
20  "outputTransformBefore": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code BEFORE entries are scraped.\n//   state.categories = await sendRequest.get('https://example.com/my-categories').json();\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
21  "outputTransformAfter": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code AFTER entries are scraped.\n//   delete state.categories;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
22  "outputFilter": "\n/**\n * Inputs:\n * `entry` - Scraped entry.\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async (entry, { io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Filter entries based on number of images they have (at least 5)\n//   return entry.images.length > 5;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
23  "outputFilterBefore": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code BEFORE entries are scraped.\n//   state.categories = await sendRequest.get('https://example.com/my-categories').json();\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
24  "outputFilterAfter": "\n/**\n * Inputs:\n *\n * `ctx.io` - Apify Actor class, see https://docs.apify.com/sdk/js/reference/class/Actor.\n * `ctx.input` - The input object that was passed to this Actor.\n * `ctx.state` - An object you can use to persist state across all your custom functions.\n * `ctx.sendRequest` - Fetch remote data. Uses 'got-scraping', same as Apify's `sendRequest`.\n *                       See https://crawlee.dev/docs/guides/got-scraping\n * `ctx.itemCacheKey` - A function you can use to get cacheID for current `entry`.\n *                        It takes the entry itself, and a list of properties to be used for hashing.\n *                        By default, you should pass `input.cachePrimaryKeys` to it.\n *\n */\n// async ({ io, input, state, sendRequest, itemCacheKey }) => {\n//   // Example: Fetch data or run code AFTER entries are scraped.\n//   delete state.categories;\n//\n//   /* ========== SEE BELOW FOR MORE EXAMPLES ========= */\n//\n//   /**\n//    * ======= ACCESSING DATASET ========\n//    * To save/load/access entries in Dataset.\n//    * Docs:\n//    * - https://docs.apify.com/platform/storage/dataset\n//    * - https://docs.apify.com/sdk/js/docs/guides/result-storage#dataset\n//    * - https://docs.apify.com/sdk/js/docs/examples/map-and-reduce\n//    */\n//   // const dataset = await io.openDataset('MyDatasetId');\n//   // const info = await dataset.getInfo();\n//   // console.log(info.itemCount);\n//   // // => 0\n//\n//   /**\n//    * ======= ACCESSING REMOTE DATA ========\n//    * Use `sendRequest` to get data from the internet:\n//    * Docs:\n//    * - https://github.com/apify/got-scraping\n//    */\n//   // const catFact = await sendRequest.get('https://cat-fact.herokuapp.com/facts/5887e1d85c873e0011036889').json();\n//   // console.log(catFact.text);\n//   // // => \"Cats make about 100 different sounds. Dogs make only about 10.\",\n//\n//   /**\n//    * ======= USING CACHE ========\n//    * To save the entry to the KeyValue cache (or retrieve it), you can use\n//    * `itemCacheKey` to create the entry's ID for you:\n//    */\n//   // const cacheId = itemCacheKey(item, input.cachePrimaryKeys);\n//   // const cache = await io.openKeyValueStore('MyStoreId');\n//   // cache.setValue(cacheId, entry);\n// };",
25  "maxRequestRetries": 3,
26  "maxRequestsPerMinute": 120,
27  "minConcurrency": 1,
28  "requestHandlerTimeoutSecs": 180,
29  "logLevel": "info",
30  "errorReportingDatasetId": "REPORTING"
31}
32EOF
33
34# Run the Actor using an HTTP API
35# See the full API reference at https://docs.apify.com/api/v2
36curl "https://api.apify.com/v2/acts/jurooravec~profesia-sk-scraper/runs?token=$API_TOKEN" \
37  -X POST \
38  -d @input.json \
39  -H 'Content-Type: application/json'