Fitanu (fitanu.com) scraper

Deprecated

Pricing

Pay per usage

See alternative Actors

Go to Apify Store

Fitanu (fitanu.com) scraper

Deprecated

See alternative Actors

Scrapes products titles, prices, images and availability. Does NOT scrape product details. Uses Crawlee (Apify v3).

Pricing

Pay per usage

Rating

0.0

(0)

Developer

Pavel Dolecek

Maintained by Community

Actor stats

Bookmarked

Total users

Monthly active users

3 years ago

Last modified

Dockerfile

FROM apify/actor-node:16

COPY package.json ./

RUN npm --quiet set progress=false \
  && npm install --only=prod --no-optional

COPY . ./

apify.json

{
  "name": "fitanu-fitanu-com-scraper",
  "version": "0.1",
  "buildTag": "latest",
  "env": null,
  "defaultRunOptions": {
    "build": "latest",
    "timeoutSecs": 3600,
    "memoryMbytes": 1024
  }
}

main.js

1import { Actor } from "apify3";
2import { CheerioCrawler, createCheerioRouter } from "crawlee";
3import { init, save, toNumberOrNull } from "./_utils/common.js";
4
5const LABELS = {
6  INDEX: `INDEX`,
7  PRODUCTS: `PRODUCTS`,
8};
9
10var MODE;
11
12(function (MODE) {
13  MODE["TEST"] = "TEST";
14  MODE["FULL"] = "FULL";
15})(MODE || (MODE = {}));
16
17const BASE_URL = `https://fitanu.com`;
18
19async function enqueueInitial(mode, crawler) {
20  if (mode === MODE.FULL) {
21    await crawler.addRequests([
22      {
23        userData: { label: LABELS.INDEX },
24        url: `https://fitanu.com/cz/nase-znacky`,
25      },
26    ]);
27  } else if (mode === MODE.TEST) {
28    await crawler.addRequests([
29      {
30        userData: { label: LABELS.PRODUCTS },
31        url: `https://fitanu.com/cz/produkty/zna%C4%8Dka/nike`,
32      },
33    ]);
34  }
35}
36
37const router = createCheerioRouter();
38
39router.addHandler(LABELS.INDEX, async ({ enqueueLinks }) => {
40  await enqueueLinks({
41    selector: `[href^="${BASE_URL}/cz/produkty/značka/"]`,
42    userData: { label: LABELS.PRODUCTS },
43  });
44});
45
46router.addHandler(LABELS.PRODUCTS, async ({ crawler, $, request, log }) => {
47  log.info(`[PRODUCTS] ${request.url}`);
48  if (!request.url.match(/\/page\/\d+$/)) {
49    // on first page, handle navigation
50    const totalPages = Number($(`.pages-items .page.last`).first().text()); // e.g. 6
51    for (let i = 2; i <= totalPages; i++) {
52      // skip first page, that is already handled
53      void crawler.addRequests([
54        {
55          userData: { label: LABELS.PRODUCTS },
56          url: `${request.url}/page/${i}`,
57        },
58      ]);
59    }
60  }
61
62  const products = [];
63  // Some .product-item are .category-description, not real products,
64  // that's why we need to filter just ones with data-product-sku
65  $(`.products-grid .product-item[data-product-sku]`).each((i, el) => {
66    const pid = $(el).attr(`data-product-sku`); // e.g. C92800472927
67    const url = $(el).find(`a.product-item-photo`).attr(`href`); // absolute url
68    const img = $(el).find(`img.product-image-photo`).attr(`src`); // absolute url
69    const name = $(el)
70      .find(`.product-item-name`)
71      .text()
72      .replace(/\n/g, ` `) // replace new lines with space
73      .replace(/\s+/g, ` `); // replace multiple spaces with single space
74    const price = $(el)
75      .find(`[data-price-type="finalPrice"]`)
76      .attr(`data-price-amount`); // e.g. 1099
77    const priceOrig = $(el)
78      .find(`[data-price-type="oldPrice"]`)
79      .attr(`data-price-amount`); // e.g. 1299
80    const inStock = undefined; // not available
81    const product = {
82      pid,
83      name,
84      url,
85      img,
86      inStock,
87      currentPrice: toNumberOrNull(price),
88      originalPrice: toNumberOrNull(priceOrig),
89      currency: `CZK`,
90    };
91    products.push(product);
92  });
93  await save(products);
94});
95
96void Actor.main(async () => {
97  const input = await Actor.getInput();
98  const { mode = MODE.FULL, ...rest } = input ?? {};
99  await init({ actorNameOverride: `fitanu` }, rest);
100  const crawler = new CheerioCrawler({ requestHandler: router });
101  await enqueueInitial(mode, crawler);
102  await crawler.run();
103});

package.json

{
  "name": "fitanu-fitanu-com-scraper",
  "description": "Scrapes products titles, prices, images and availability. Does NOT scrape product details. Uses Crawlee (Apify v3).",
  "type": "module",
  "scripts": {
    "start": "node ./main.js",
    "push-to-apify-platform": "npx apify push"
  },
  "dependencies": {
    "apify3": "npm:apify@^3.0.2",
    "crawlee": "*",
    "pg": "*",
    "pg-connection-string": "*",
    "dotenv": "*",
    "find-config": "*",
    "@elastic/elasticsearch": "*",
    "filenamify": "*"
  },
  "apify": {
    "title": "Fitanu (fitanu.com) scraper",
    "description": "Scrapes products titles, prices, images and availability. Does NOT scrape product details. Uses Crawlee (Apify v3).",
    "isPublic": true,
    "isDeprecated": false,
    "isAnonymouslyRunnable": true,
    "notice": "",
    "pictureUrl": "",
    "seoTitle": "",
    "seoDescription": "",
    "categories": [
      "ECOMMERCE"
    ]
  }
}

.actor/actor.json

{
  "actorSpecification": 1,
  "name": "fitanu-fitanu-com-scraper",
  "title": "Fitanu (fitanu.com) scraper",
  "description": "Scrapes products titles, prices, images and availability. Does NOT scrape product details. Uses Crawlee (Apify v3).",
  "version": "0.1.0",
  "storages": {
    "dataset": {
      "actorSpecification": 1,
      "title": "Fitanu (fitanu.com) scraper",
      "description": "Scrapes products titles, prices, images and availability. Does NOT scrape product details. Uses Crawlee (Apify v3).",
      "views": {
        "overview": {
          "title": "Overview",
          "description": "Overview of the most important fields",
          "transformation": {
            "fields": [
              "pid",
              "name",
              "url",
              "img",
              "inStock",
              "currentPrice",
              "originalPrice",
              "currency"
            ]
          },
          "display": {
            "component": "table",
            "columns": [
              {
                "label": "Pid",
                "field": "pid",
                "format": "text"
              },
              {
                "label": "Name",
                "field": "name",
                "format": "text"
              },
              {
                "label": "Url",
                "field": "url",
                "format": "link"
              },
              {
                "label": "Img",
                "field": "img",
                "format": "image"
              },
              {
                "label": "In Stock",
                "field": "inStock",
                "format": "boolean"
              },
              {
                "label": "Current Price",
                "field": "currentPrice",
                "format": "number"
              },
              {
                "label": "Original Price",
                "field": "originalPrice",
                "format": "number"
              },
              {
                "label": "Currency",
                "field": "currency",
                "format": "text"
              }
            ]
          }
        }
      }
    }
  }
}

_utils/common.js

1import { createHash } from 'crypto'
2import os from "os"
3import path from "path"
4// eslint-disable-next-line @apify/apify-actor/no-forbidden-node-internals
5import fs from "fs"
6import pg from "pg"
7import pgConnectionString from 'pg-connection-string'
8import { config } from 'dotenv'
9import findConfig from "find-config"
10import { Client as ElasticClient } from "@elastic/elasticsearch"
11import filenamify from 'filenamify'
12import { Dataset } from 'crawlee'
13
14config({ path: findConfig(`.env`) })
15
16const elasticIndexName = `actors-monorepo-shops`
17
18const globalLogsProps = {
19  __NODE_STARTED: new Date().toISOString(),
20}
21
22let actorName
23let pgClient
24let pgClientNormalized
25let elasticClient
26export async function init ({ actorNameOverride }, restInput) {
27  parseEnvFromInput(restInput)
28
29  if (os.platform() === `darwin`) {
30    const filePath = process.argv[1] // ~/Projects/apify-actors-monorepo/actors/foo.ts
31    const basename = path.basename(filePath) // foo.ts
32    actorName = actorNameOverride ?? basename.split(`.`)[0] // foo
33    const gitBranch = fs.readFileSync(path.join(process.cwd(), `..`, `.git/HEAD`), `utf8`)
34      .split(` `)[1]
35      .trim()
36      .replace(`refs/heads/`, ``)
37    const gitCommit = fs.readFileSync(path.join(process.cwd(), `..`, `.git/refs/heads/${gitBranch}`), `utf8`)
38    const gitCommitShort = gitCommit.substring(0, 7)
39    globalLogsProps.__GIT_COMMIT = gitCommitShort
40  }
41
42  if (process.env.APIFY_IS_AT_HOME) {
43    actorName = actorNameOverride ?? process.env.APIFY_ACTOR_ID // Name would be better, but it's not in ENV
44  }
45
46  /* ELASTIC */
47  /* ======= */
48  if (process.env.ELASTIC_CLOUD_ID) {
49    elasticClient = new ElasticClient({
50      cloud: { id: process.env.ELASTIC_CLOUD_ID },
51      auth: { apiKey: process.env.ELASTIC_CLOUD_API_KEY },
52    })
53
54    // const mapping = await elasticClient.indices.getMapping({ index: actorName })
55
56    // eslint-disable-next-line no-inner-declarations
57    async function enforceIndexMapping () {
58      const doesIndexExist = await elasticClient.indices.exists({ index: elasticIndexName })
59      if (!doesIndexExist) await elasticClient.indices.create({ index: elasticIndexName })
60      await elasticClient.indices.putMapping({
61        index: elasticIndexName,
62        body: {
63          properties: {
64            _discount: { type: `float` },
65            originalPrice: { type: `float` },
66            currentPrice: { type: `float` },
67          },
68        },
69      })
70    }
71
72    try {
73      await enforceIndexMapping()
74    } catch (err) {
75      if (err.message.includes(`cannot be changed from type`)) {
76        console.log(`Elastic index ${elasticIndexName} already exists with incorrect mappings. As existing mapping cannot be changed, index will be deleted and recreated.`)
77        await elasticClient.indices.delete({ index: elasticIndexName })
78        await enforceIndexMapping()
79      }
80    }
81  }
82
83  /* POSTGRESQL */
84  /* ========== */
85  if (process.env.PG_CONNECTION_STRING) {
86    const pgConfig = pgConnectionString(process.env.PG_CONNECTION_STRING)
87    // const pgPool = new pg.Pool(pgConfig)
88
89    pgClient = new pg.Client(pgConfig)
90    await pgClient.connect()
91
92    // Check if table exists and have proper columns
93    const { rows: tables } = await pgClient.query(`
94    SELECT table_name
95    FROM information_schema.tables
96    WHERE table_schema = 'public'
97  `)
98
99    // eslint-disable-next-line camelcase
100    const tableExists = tables.some(({ table_name }) => table_name === process.env.PG_DATA_TABLE)
101    if (!tableExists) {
102      throw new Error(`Table ${process.env.PG_DATA_TABLE} does not exist in database ${pgConfig.database}`)
103    }
104
105  // TODO: Handle pgClient closing
106  }
107
108  if (process.env.PG_CONNECTION_STRING_NORMALIZED) {
109    const pgConfig = pgConnectionString(process.env.PG_CONNECTION_STRING_NORMALIZED)
110
111    pgClientNormalized = new pg.Client(pgConfig)
112    await pgClientNormalized.connect()
113
114    // Check if table exists and have proper columns
115    const { rows: tables } = await pgClientNormalized.query(`
116    SELECT table_name
117    FROM information_schema.tables
118    WHERE table_schema = 'public'
119  `)
120
121    // eslint-disable-next-line camelcase
122    const tableMainExists = tables.some(({ table_name }) => table_name === process.env.PG_DATA_TABLE)
123    // eslint-disable-next-line camelcase
124    const tablePricesExists = tables.some(({ table_name }) => table_name === process.env.PG_DATA_PRICE_TABLE)
125    if (!tableMainExists) throw new Error(`Table ${process.env.PG_DATA_TABLE} does not exist in database ${pgConfig.database}`)
126    if (!tablePricesExists) throw new Error(`Table ${process.env.PG_DATA_PRICE_TABLE} does not exist in database ${pgConfig.database}`)
127
128  // TODO: Handle pgClient closing
129  }
130}
131
132// inspired by @drobnikj
133// TODO: Similar, but less obfuscated for easier debugging
134export const createUniqueKeyFromUrl = (url) => {
135  const hash = createHash(`sha256`)
136  const cleanUrl = url.split(`://`)[1] // Remove protocol
137  hash.update(cleanUrl)
138  return hash.digest(`hex`)
139}
140
141/**
142 *
143 * @param {Date} datetime
144 * @return {Promise<void>}
145 */
146export const sleepUntil = async (datetime) => {
147  const now = new Date()
148  const difference = datetime - now
149  if (difference > 0) {
150    return new Promise((resolve) => {
151      setTimeout(resolve, difference)
152    })
153  }
154  return Promise.resolve()
155}
156
157export function parsePrice (string) {
158  let amount, currency
159  const noText = string.replace(/[^\d,.]/g, ``)
160  const decimals = noText.match(/([,.])(\d{2})$/)
161  if (decimals) {
162    const decimalSeparator = decimals[1]
163    // eslint-disable-next-line @typescript-eslint/no-unused-vars, no-unused-vars
164    const decimalAmount = decimals[2]
165    amount = parseInt(noText.split(decimalSeparator)[0])
166  } {
167    const justNumbers = noText.replace(/[,.]/g, ``)
168    amount = parseInt(justNumbers)
169  }
170  return { amount, currency }
171}
172
173export function toNumberOrNull (str) {
174  // TODO: Handle better, but only after adding test
175  if (str === undefined) return null
176  if (str === null) return null
177  if (str === ``) return null
178  const num = Number(str)
179  if (Number.isNaN(num)) return null
180  return num
181}
182
183export async function save (objs) {
184  if (!Array.isArray(objs)) objs = [objs]
185  if (objs.length === 0) return
186
187  const objsExtended = objs.map((obj) => {
188    const objExtended = {
189      ...obj,
190      actorName,
191      ...globalLogsProps,
192      // __NODE_VERSION: global.process.versions.node,
193      // __NODE_UPTIME: global.process.uptime().toFixed(2), // seconds, 2 decimals
194    }
195    // if run on Apify
196    if (process.env.APIFY_IS_AT_HOME) {
197      objExtended.__APIFY_ACTOR_ID = process.env.APIFY_ACTOR_ID
198      objExtended.__APIFY_ACTOR_RUN_ID = process.env.APIFY_ACTOR_RUN_ID
199      objExtended.__APIFY_ACTOR_BUILD_ID = process.env.APIFY_ACTOR_BUILD_ID
200      objExtended.__APIFY_ACTOR_BUILD_NUMBER = process.env.APIFY_ACTOR_BUILD_NUMBER
201      objExtended.__APIFY_ACTOR_TASK_ID = process.env.APIFY_ACTOR_TASK_ID
202      if (!process.env.APIFY_DONT_STORE_IN_DATASET) void Dataset.pushData(obj)
203    }
204    return objExtended
205  })
206  // if runs on local machine (MacOS)
207  if (os.platform() === `darwin`) {
208    const cwd = process.cwd() // ~/Projects/apify-actors-monorepo/actors
209    const storageDir = path.join(cwd, `${actorName}.storage`) // ~/Projects/apify-actors-monorepo/actors/foo.storage
210    if (!fs.existsSync(storageDir)) fs.mkdirSync(storageDir)
211    const dataDir = path.join(storageDir, `data`) // ~/Projects/apify-actors-monorepo/actors/foo.storage/data
212    if (!fs.existsSync(dataDir)) fs.mkdirSync(dataDir)
213    for (const objExtended of objsExtended) {
214      const id = objExtended.id ?? objExtended.pid // ?? uuidv4()
215      const fileName = `${filenamify(id)}.json`
216      const dataFilePath = path.join(dataDir, fileName) // ~/Projects/apify-actors-monorepo/actors/foo.storage/data/foo.json
217      fs.writeFileSync(dataFilePath, JSON.stringify(objExtended, null, 2))
218    }
219  }
220
221  if (pgClient) {
222    const objsPg = objs.map((obj) => ({
223      ...obj,
224      // TODO: This is becoming not nice, and not clear
225      shop: actorName,
226      scrapedAt: new Date().toISOString().split(`T`)[0],
227    }))
228
229    const columns = getColumns(objsPg)
230    const values = getValues(objsPg)
231    const queryString = `
232        INSERT INTO public."${process.env.PG_DATA_TABLE}" (${columns})
233        VALUES (${values})
234    `
235    try {
236      const { rowCount } = await pgClient.query(queryString)
237      console.log(`[save] saved to database: ${JSON.stringify(rowCount)}`)
238    } catch (err) {
239      if (err.message.includes(`violates unique constraint`)) console.warn(`PostgresSQL: violates unique constraint`)
240      else throw err
241    }
242  }
243
244  // Only make sense for HlidacShopu
245  if (pgClientNormalized) {
246    const objsPgData = objs.map((obj) => ({
247      shop: actorName,
248      pid: obj.pid,
249      name: obj.name,
250      url: obj.url,
251      img: obj.img,
252    }))
253
254    const objsPgDataPrice = objs.map((obj) => ({
255      shop: actorName,
256      pid: obj.pid,
257      scrapedAt: new Date().toISOString().split(`T`)[0],
258      currentPrice: obj.currentPrice,
259      originalPrice: obj.originalPrice,
260      inStock: obj.inStock,
261    }))
262
263    const queryString = `
264        INSERT INTO public."${process.env.PG_DATA_TABLE}" (${getColumns(objsPgData)})
265        VALUES (${getValues(objsPgData)})
266        ON CONFLICT DO NOTHING
267    `
268    try {
269      const { rowCount } = await pgClientNormalized.query(queryString)
270      console.log(`[save] saved to database (data): ${JSON.stringify(rowCount)}`)
271    } catch (err) {
272      if (err.message.includes(`violates unique constraint`)) console.warn(`PostgresSQL: violates unique constraint`)
273      else throw err
274    }
275
276    const queryStringPrice = `
277        INSERT INTO public."${process.env.PG_DATA_PRICE_TABLE}" (${getColumns(objsPgDataPrice)})
278        VALUES (${getValues(objsPgDataPrice)})
279        ON CONFLICT DO NOTHING
280    `
281    try {
282      const { rowCount } = await pgClientNormalized.query(queryStringPrice)
283      console.log(`[save] saved to database (price): ${JSON.stringify(rowCount)}`)
284    } catch (err) {
285      if (err.message.includes(`violates unique constraint`)) console.warn(`PostgresSQL: violates unique constraint`)
286      else throw err
287    }
288  }
289
290  if (elasticClient) {
291    // .index creates or updates the document
292    // .create creates a new document if it doesn't exist, 409 if it does
293    // try {
294    //   const res = await elasticClient.index({
295    //     index: `actors-monorepo-shops`, // TODO: Consider using actorName
296    //     id, // foo-bar
297    //     document: objExtended, // {...}
298    //   })
299    // } catch (err) {
300    //   // https://discuss.elastic.co/t/elasticsearch-503-ok-false-message-the-requested-deployment-is-currently-unavailable/200583
301    //   if (err.message.includes(`requested resource is currently unavailable`)) console.log(`Elasticsearch is unavailable, skipping, but not aborting`)
302    //   else throw err
303    // }
304  }
305}
306
307function getColumns (objs) {
308  return Object.keys(objs[0]).map((key) => `"${key}"`).join(`, `)
309}
310
311function getValues (objs) {
312  return objs.map(objPg => Object.values(objPg).map((value) => {
313    // escape strings to prevent SQL injection
314    if (typeof value === `string`) return `'${value.replace(/'/g, `''`)}'`
315    // convert to DB specific null
316    if (typeof value === `undefined` || value === null) return `NULL`
317    return value
318  }).join(`, `)).join(`), (`)
319}
320
321export function parseEnvFromInput (input) {
322  const env = {}
323  for (const key in input) {
324    if (key === key.toUpperCase()) env[key] = input[key]
325  }
326  console.log(`[parseEnvFromInput] ${JSON.stringify(env)}`)
327  Object.assign(process.env, env)
328}

Google Maps Scraper

compass/crawler-google-places

Extract data from thousands of Google Maps locations and businesses, including reviews, reviewer details, images, contact info, including full name, email, and job title, opening hours, prices & more. Export data, run via API, schedule and monitor runs, or integrate with other tools.

Compass

203K

4.8

(488)

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

86K

4.6

(116)

TikTok Scraper

clockworks/tiktok-scraper

Extract data from TikTok videos, hashtags, and users. Use URLs or search queries to scrape TikTok profiles, hashtags, posts, URLs, shares, followers, hearts, names, video, and music-related data. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Clockworks

92K

4.7

(109)

Instagram Scraper

apify/instagram-scraper

Scrape and download Instagram posts, profiles, places, hashtags, photos, and comments. Get data from Instagram using one or more Instagram URLs or search queries. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

147K

4.6

(203)

🏯 Tweet Scraper V2 - X / Twitter Scraper

apidojo/tweet-scraper

⚡️ Lightning-fast search, URL, list, and profile scraping, with customizable filters. At $0.40 per 1000 tweets, and 30-80 tweets per second, it is ideal for researchers, entrepreneurs, and businesses! Get comprehensive insights from Twitter (X) now!

API Dojo

27K

4.2

(110)

Facebook Posts Scraper

apify/facebook-posts-scraper

Extract data from hundreds of Facebook posts from one or multiple Facebook pages and profiles. Get post URL, post text, page or profile URL, timestamp, number of likes, shares, comments, and more. Download the data in JSON, CSV, and Excel and use it in apps, spreadsheets, and reports.

Apify

36K

4.6

(71)

Facebook Pages Scraper

apify/facebook-pages-scraper

Extract basic data from multiple Facebook Pages or Profiles. Extract Facebook page details, website, email, address, messenger, likes, followers, rating, ad running status, and other public data. Export scraped data, schedule scraper via API, integrate with other tools or AI workflows.

Apify

30K

4.6

(24)

Facebook Ad Library Scraper

curious_coder/facebook-ads-library-scraper

Scrape facebook ads search and ads run by facebook pages - Fast and lightweight. $0.75 per 1000 results

Curious Coder

13K

3.6

(41)

Full TikTok API Scraper

scraptik/tiktok-api

Apify’s LOWEST-COST TikTok Scraper. Access the TikTok mobile API for user, posts, sounds, search, comments, followers, and more. Unlock TikTok data at scale. Have custom needs? Visit scraptik.com to get in touch.

ScrapTik

1.5K

4.5

(10)

Google Maps Extractor

compass/google-maps-extractor

Extract data from hundreds of places fast. Scrape Google Maps by keyword, category, location, URLs & other filters. Get addresses, contact info, opening hours, popular times, prices, menus & more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.

Compass

63K

4.6

(119)

📩📍 Google Maps Email Extractor

lukaskrivka/google-maps-with-contact-details

Extract Google Maps contact details. Scrape websites of Google Maps places for contact details and get email addresses, website, location, address, zipcode, phone number, social media links. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.