RealityMix.cz Scraper

Deprecated

Pricing

Pay per usage

See alternative Actors

Go to Apify Store

RealityMix.cz Scraper

Deprecated

See alternative Actors

Developed by

Denis Leskovar

Maintained by Community

A web scraper for the realitymix.cz real estate portal. The scaper looks through listings with an applied filter. The filter is specified in the actor's input. The output is all available listings with the filter applied.

0.0 (0)

Pricing

Pay per usage

Last modified

4 years ago

Real estate

Open source

src/consts.js

1module.exports = {
2    STATES: {
3        "Praha" : 19,
4        "Jihočeský kraj" : 27,
5        "Jihomoravský kraj" : 60,
6        "Karlovarský kraj" : 51, 
7        "Královéhradecký kraj" : 78, 
8        "Liberecký kraj": 86, 
9        "Moravskoslezský kraj" : 94, 
10        "Olomoucký kraj" : 124, 
11        "Pardubický kraj" : 132, 
12        "Plzeňský kraj" : 141, 
13        "Středočeský kraj" : 116, 
14        "Ústecký kraj" : 108, 
15        "Vysočina" : 35, 
16        "Zlínský kraj" : 43
17    },
18    LAYOUTS: {
19        "Garsoniéra" : 1, 
20        "1+kk" : 2, 
21        "1+1" : 9, 
22        "2+kk" : 10, 
23        "2+1" : 3, 
24        "3+kk" : 4, 
25        "3+1" : 11, 
26        "4+kk" : 5, 
27        "4+1" : 12, 
28        "5+kk" : 6, 
29        "5+1" : 14, 
30        "6+kk" : 16,
31        "6+1" : 13, 
32        "7+kk" : 8, 
33        "7+1" : 17, 
34        "Atypický" : 7,
35        "Jiný" : 15
36    },
37    ADVERTTYPES : {
38        "Prodej" : 1,
39        "Pronájem" : 2,
40        "Vše" : 0
41    },
42    BUILDINGTYPES : {
43        "Byty" : 4,
44        "Domy" : 6,
45        "Chaty" : 10,
46        "Pozemky" : 3,
47    },
48    OWNERSHIPTYPES : {
49        "osobní vlastnictví" : 1, 
50        "družstevní vlastnictví" : 2, 
51        "jiné vlastnictví" : 3
52    }
53};

src/routes.js

1const Apify = require("apify");
2
3const {
4    utils: { log },
5} = Apify;
6
7exports.handleStart = async ({ request, page, crawler }) => {
8    log.info("[START]: Start.");
9
10    const lastPageNumber = await page.$$eval("li.paginator__list-item", $list => {
11        const classContainer = Array.from($list)
12        const item = classContainer[classContainer.length - 2];
13
14        return parseInt(item.querySelector('a').textContent);
15    });
16
17    const pageUrl = page.url();
18
19    for (let index = 1; index < lastPageNumber; index++) {
20        const link = pageUrl.concat(`&stranka=${index}`);
21        const request = {
22            userData: {
23                label: "LIST",
24            },
25            url: link,
26        };
27        log.info(`Adding listing page url: ${request.url}`);
28        await crawler.requestQueue.addRequest(request);
29    }
30
31    log.info("[START]: Listing pages pushed.");
32};
33
34exports.handleList = async ({ request, page, crawler }) => {
35    log.info("[LIST]: Start.");
36   
37    const listings = await page.$$eval(".advert-list-items__content", ($listing) => {
38            const items = [];
39            $listing.forEach(($item) => {
40                const link = $item.querySelector("h2 > a").getAttribute("href");
41                items.push({
42                    userData: {
43                        label: "DETAIL",
44                    },
45                    url: link,
46                });
47            });
48            return items;
49        });
50
51    log.info("[LIST]: Scraped.");
52
53    for (let index = 0; index < listings.length; index++) {
54        const request = listings[index];
55        await crawler.requestQueue.addRequest(request);
56    }
57
58    log.info("[LIST]: Listings pushed.");
59};
60
61exports.handleDetail = async ({ request, page }) => {
62    log.info("[DETAIL]: Getting detail info.");
63
64    let {
65        buildingType,
66        location,
67        price 
68    } = await page.$$eval(".advert-detail-fixed-top__content-info", $list => {
69        const item = Array.from($list)[0];
70        
71        const headerText = item.querySelector("h4").textContent.trim();
72        const buildingType = headerText.split(",")[0].trim();
73        const location = item.querySelector("p").textContent.trim();
74        
75        const highlight = item.querySelector("strong");
76        const price = highlight.querySelector("span").textContent.trim();
77
78        flag = true;
79
80        return {
81            "buildingType" : buildingType,
82            "location" : location,
83            "price" : price
84        }
85    });
86
87    let mainImage = await page.$$eval(".gallery__main-img-inner", $list => {
88        const item = Array.from($list)[0];
89
90        const imageUrl = item.querySelector("img").src;
91
92        return { "imageUrl" : imageUrl }
93    });
94
95    let smallImages = await page.$$eval(".gallery__item--image", $list => {
96        const items = [];
97
98        $list.forEach($item => {
99            const imageContainer = $item.querySelector("a");
100            const imageUrl = imageContainer.querySelector("img").src;
101
102            items.push({ "imageUrl" : imageUrl });
103        });
104        
105        return items;
106    });
107
108    let images = [ mainImage ].concat(smallImages);
109
110    let propertyElList = await page.$$eval(".detail-information__data-item", $list => {
111        const items = [];
112
113        $list.forEach($item => {
114            const key = $item.querySelector("span:nth-child(1)").textContent.trim();
115            const value = $item.querySelector("span:nth-child(2)").textContent.trim();
116
117            items.push({ "key": key, "value" : value });
118        });
119        
120        return items;
121    });
122
123    let {
124        description 
125    } = await page.$$eval(".advert-description__text-inner-inner", $list => {
126        const item = Array.from($list)[0];
127
128        return { "description" : item.textContent.trim() };
129    });
130
131    await Apify.pushData({buildingType, location, price, "images" : images, "properties" : propertyElList, description });
132
133    log.info("[DETAIL]: Detail info done.");
134};

src/tools.js

1const Apify = require('apify');
2const { STATES, LAYOUTS, ADVERTTYPES, BUILDINGTYPES, OWNERSHIPTYPES } = require('./consts');
3
4const { utils: { log } } = Apify;
5
6const getAndValidateInput = async () => {
7    const input = await Apify.getInput();
8
9    const stateToInt = (x) => {
10        if (x in STATES)
11            return STATES[x];
12        throw new Error("Invalid state.");
13    }
14
15    const layoutToInt = (x) => {
16        if (x in LAYOUTS)
17            return LAYOUTS[x];
18        throw new Error("Invalid layout.");
19    }
20
21    const advertTypeToInt = (x) => {
22        if (x in ADVERTTYPES)
23            return ADVERTTYPES[x];
24        throw new Error("Invalid advert type.");
25    }
26
27    const buildingTypeToInt = (x) => {
28        if (x in BUILDINGTYPES)
29            return BUILDINGTYPES[x];
30        throw new Error("Invalid building type.");
31    }
32
33    const ownershipTypeToInt = (x) => {
34        if (x in OWNERSHIPTYPES)
35            return OWNERSHIPTYPES[x];
36        throw new Error("Invalid ownership type.");
37    }
38
39    const maybeThis = (x) => { 
40        return (x === undefined) ? "" : x;
41    }
42
43    let {
44        state,
45        priceStart,
46        priceEnd,
47        layout,
48        advertType,
49        buildingType,
50        areaFrom,
51        areaTo,
52        levelFrom,
53        levelTo,
54        ownershipType,
55    } = input;
56
57    state = stateToInt(state);
58    layout = layoutToInt(layout);
59    advertType = advertTypeToInt(advertType);
60    buildingType = buildingTypeToInt(buildingType);
61    ownershipType = ownershipTypeToInt(ownershipType);
62
63    priceStart = maybeThis(priceStart);
64    priceEnd = maybeThis(priceEnd);
65    areaFrom = maybeThis(areaFrom);
66    areaTo = maybeThis(areaTo);
67    levelFrom = maybeThis(levelFrom);
68    levelTo = maybeThis(levelTo);
69
70    log.info("----- Input overview -----");
71    log.info(`Search state: ${state}`);
72    log.info(`Search priceStart: ${priceStart}`);
73    log.info(`Search priceEnd: ${priceEnd}`);
74    log.info(`Search layout: ${layout}`);
75    log.info(`Search advertType: ${advertType}`);
76    log.info(`Search buildingType: ${buildingType}`);
77    log.info(`Search areaFrom: ${areaFrom}`);
78    log.info(`Search areaTo: ${areaTo}`);
79    log.info(`Search levelFrom: ${levelFrom}`);
80    log.info(`Search levelTo: ${levelTo}`);
81    log.info(`Search ownershipType: ${ownershipType}`);
82    log.info("----- End of input overview -----");
83
84    return {
85        state,
86        priceStart,
87        priceEnd,
88        layout,
89        advertType,
90        buildingType,
91        areaFrom,
92        areaTo,
93        levelFrom,
94        levelTo,
95        ownershipType,
96    };
97}
98
99module.exports = {
100    getAndValidateInput
101};

.editorconfig

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

.eslintrc

{
    "extends": "@apify"
}

.gitignore

# This file tells Git which files shouldn't be added to source control

.idea
node_modules

apify_storage

Dockerfile

# First, specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-puppeteer-chrome:16

# Second, copy just package.json and package-lock.json since it should be
# the only file that affects "npm install" in the next step, to speed up the build
COPY package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
 && npm install --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && (npm list --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./

# Optionally, specify how to launch the source code of your actor.
# By default, Apify's base Docker images define the CMD instruction
# that runs the Node.js source code using the command specified
# in the "scripts.start" section of the package.json file.
# In short, the instruction looks something like this:
#
# CMD npm start

apify.json

{
	"name": "realitymix-scraper",
	"version": "0.0",
	"buildTag": "latest",
	"env": null,
	"template": "project_puppeteer_crawler"
}

main.js

1const Apify = require('apify');
2const { getAndValidateInput } = require('./src/tools');
3const { handleStart, handleList, handleDetail } = require('./src/routes');
4
5const { utils: { log } } = Apify;
6
7Apify.main(async () => {
8    const {
9        state,
10        priceStart,
11        priceEnd,
12        layout,
13        advertType,
14        buildingType,
15        areaFrom,
16        areaTo,
17        levelFrom,
18        levelTo,
19        ownershipType,
20    } = await getAndValidateInput();
21
22    let startUrl = `https://realitymix.cz/vypis-nabidek/?form%5Badresa_kraj_id%5D[]=${state}&form%5Badresa_obec_id%5D=&form%5Bcena_mena%5D=&form%5Bcena_normalizovana__from%5D=${priceStart}&form%5Bcena_normalizovana__to%5D=${priceEnd}&form%5Bdispozice%5D[]=${layout}&form%5Bexclusive%5D=&form%5Bfk_rk%5D=&form%5Binzerat_typ%5D=${advertType}&form%5Bnemovitost_typ%5D[]=${buildingType}&form%5Bplocha__from%5D=${areaFrom}&form%5Bplocha__to%5D=${areaTo}&form%5Bpodlazi_cislo__from%5D=${levelFrom}&form%5Bpodlazi_cislo__to%5D=${levelTo}&form%5Bprojekt_id%5D=&form%5Bsearch_in_city%5D=&form%5Bsearch_in_text%5D=&form%5Bstari_inzeratu%5D=&form%5Bstav_objektu%5D=&form%5Btop_nabidky%5D=&form%5Bvlastnictvi%5D[]=${ownershipType}`
23
24    log.info(`Starting at url: ${startUrl}`);
25
26    const requestList = await Apify.openRequestList('start-urls', [ startUrl ]);
27    const requestQueue = await Apify.openRequestQueue();
28    const proxyConfiguration = await Apify.createProxyConfiguration();
29
30    const crawler = new Apify.PuppeteerCrawler({
31        requestList,
32        requestQueue,
33        proxyConfiguration,
34        launchContext: {
35            useChrome: false,
36            stealth: true,
37        },
38        handlePageFunction: async (context) => {
39            const { url, userData: { label } } = context.request;
40            log.info('Page opened.', { label, url });
41            switch (label) {
42                case 'LIST':
43                    return handleList(context);
44                case 'DETAIL':
45                    return handleDetail(context);
46                default:
47                    return handleStart(context);
48            }
49        },
50    });
51
52    log.info('Starting the crawl.');
53    await crawler.run();
54    log.info('Crawl finished.');
55});

package.json

{
	"name": "realitymix-scraper",
	"version": "0.0.1",
	"description": "This is a boilerplate of an Apify actor.",
	"dependencies": {
		"apify": "^2.0.7",
		"puppeteer": "*"
	},
	"devDependencies": {
		"@apify/eslint-config": "^0.1.3",
		"eslint": "^7.0.0"
	},
	"scripts": {
		"start": "node main.js",
		"lint": "./node_modules/.bin/eslint ./src --ext .js,.jsx",
		"lint:fix": "./node_modules/.bin/eslint ./src --ext .js,.jsx --fix",
		"test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
	},
	"author": "It's not you it's me",
	"license": "ISC"
}

Google Maps Scraper

compass/crawler-google-places

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

Compass

187K

4.7

(322)

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

82K

4.7

(93)

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

83K

4.4

(71)

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

142K

4.5

(147)

🏯 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

24K

3.6

(98)

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

33K

4.4

(53)

Instagram Post Scraper

apify/instagram-post-scraper

Scrape Instagram posts. Just add one or more Instagram usernames and get your data in seconds including caption, metrics, images, mentions, coauthors, recent comments, sponsored status, video duration, views. Export scraped data, schedule scraper via API, integrate with other tools or AI workflows.

Apify

54K

4.8

(51)

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

11K

4.7

(31)

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

ScrapTik

847

4.7

(6)

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

61K

4.6

(101)

📩📍 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.

Lukáš Křivka

45K

4.4

(89)

RealityMix.cz Scraper

RealityMix.cz Scraper

src/consts.js

src/routes.js

src/tools.js

.editorconfig

.eslintrc

.gitignore

Dockerfile

apify.json

main.js

package.json

You might also like

Google Maps Scraper

Website Content Crawler

TikTok Scraper

Instagram Scraper

🏯 Tweet Scraper V2 - X / Twitter Scraper

Facebook Posts Scraper

Instagram Post Scraper

Facebook Ad Library Scraper

Full TikTok API Scraper

Google Maps Extractor

📩📍 Google Maps Email Extractor

src/consts.js

src/routes.js

src/tools.js

.editorconfig

.eslintrc

.gitignore

Dockerfile

apify.json

main.js

package.json