We've launched
Crawlee,our open-source scraping library!
Crawlee,our open-source scraping library!
Simple scraper for https://prazdnedomy.cz which gather old, valuable but not inhabited houses.
- Modified
- Users10
- Runs325
Dockerfile
# Dockerfile contains instructions how to build a Docker image that
# will contain all the code and configuration needed to run your actor.
# For a full Dockerfile reference,
# see https://docs.docker.com/engine/reference/builder/
# First, specify the base Docker image. Apify provides the following
# base images for your convenience:
# apify/actor-node-basic (Node.js 10 on Alpine Linux, small and fast)
# apify/actor-node-chrome (Node.js 10 + Chrome on Debian)
# apify/actor-node-chrome-xvfb (Node.js 10 + Chrome + Xvfb on Debian)
# For more information, see https://apify.com/docs/actor#base-images
# Note that you can use any other image from Docker Hub.
FROM apify/actor-node-basic
# Copy all files and directories with the source code
COPY . ./
# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging to 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 \
&& echo "Node.js version:" \
&& node --version \
&& echo "NPM version:" \
&& npm --version
# Specify how to run the source code
CMD npm start
README.md
# My beautiful actor
Contains a documentation what your actor does and how to use it,
which is then displayed in the app or library. It's always a good
idea to write a good README.md, in a few months not even you
will remember all the details about the actor.
You can use [Markdown](https://www.markdownguide.org/cheat-sheet)
language for rich formatting.
package.json
{
"name": "my-actor",
"version": "0.0.1",
"dependencies": {
"apify": "^0.13.7"
},
"scripts": {
"start": "node main.js"
},
"author": "Me!"
}INPUT_SCHEMA.json
{
"title": "My input schema",
"type": "object",
"schemaVersion": 1,
"properties": {
"myField": {
"title": "My input field",
"type": "string",
"nullable": false,
"description": "This is a customizable description providing help to the users of your actor.",
"editor": "textarea"
}
}
}main.js
// This is the main Node.js source code file of your actor.
// It is referenced from the "scripts" section of the package.json file.
const Apify = require('apify');
Apify.main(async () => {
// Get input of the actor. Input fields can be modified in INPUT_SCHEMA.json file.
// For more information, see https://apify.com/docs/actor/input-schema
const input = await Apify.getInput();
console.log('Input:');
console.dir(input);
// Here you can prepare your input for actor apify/cheerio-scraper this input is based on a actor
// task you used as the starting point.
const metamorphInput = {
"startUrls": [
{
"url": "https://prazdnedomy.cz/domy/objekty/?paginator-page=1",
"method": "GET"
}
],
"useRequestQueue": true,
"pseudoUrls": [
{
"purl": "https://prazdnedomy.cz/domy/objekty/?paginator-page=[\\d+]",
"method": "GET"
}
],
"linkSelector": "a",
"pageFunction": "async function pageFunction(context) {\n const { request, $ } = context;\n let result = [];\n $('.estates-list .estate').each(function(i) {\n let typ = null;\n let stav = null;\n let gps = null;\n let adresa = null;\n\n $(this).find('.icons .icon').each(function() {\n const maybeHtml = $(this).attr('title')\n if (!maybeHtml) return\n const maybeTyp = maybeHtml.match(/<td>Typ: <\\/td><td>(.+?)<\\/td>/)\n if (maybeTyp) {\n typ = maybeTyp[1]\n }\n const maybeStav = maybeHtml.match(/<td>Stav: <\\/td><td>(.+)<\\/td>/)\n if (maybeStav) {\n stav = maybeStav[1]\n return\n }\n \n const maybeGps = maybeHtml.match(/\\d+°.+''/)\n if (maybeGps) {\n gps = maybeGps[0]\n adresa = maybeHtml.replace(gps, '')\n }\n \n })\n\n result.push({\n title: $(this).find('.content .title').text().trim(),\n url: 'https://prazdnedomy.cz' + $(this).find('a').attr('href'),\n typ,\n stav,\n gps,\n adresa,\n })\n })\n return result;\n}",
"proxyConfiguration": {
"useApifyProxy": false
},
"debugLog": false,
"ignoreSslErrors": false,
"useCookieJar": false
};
// Now let's metamorph into actor apify/cheerio-scraper using the created input.
await Apify.metamorph('apify/cheerio-scraper', metamorphInput);
});
