# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git


.dockerignore

root = true

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


.editorconfig

.eslintrc

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

.idea
dist
node_modules
apify_storage
storage

apify_storage

.gitignore

kaktus-dobijecka

apify.json

# 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:16

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
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 --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# 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 . ./


# Run the image.
CMD npm start --silent


Dockerfile

Set to, cc and bcc. You can set more objects with addresses, in this case more e-mails will be sent.

E-mail data

CheerioCrawler Template

INPUT_SCHEMA.json

package.json

import { Actor } from 'apify';
import { CheerioCrawler } from 'crawlee';
import { router } from './routes.js';

await Actor.init();

const startUrls = ['https://www.mujkaktus.cz/chces-pridat'];

const crawler = new CheerioCrawler({
    requestHandler: router,
});

await crawler.run(startUrls);

await Actor.exit();


src/main.js

import { Actor } from 'apify';
import { createCheerioRouter } from 'crawlee';
import { Utils } from './utils.js';

export const router = createCheerioRouter();

router.addDefaultHandler(async ({ $ }) => {
  for (const h3 of $('h3')) {

    const text = $(h3).text();

    const validity = Utils.parseDate(text);

    if (validity) {
      await Actor.pushData(Utils.getResult(validity, text));

      if (Utils.isSameDay(validity.date, new Date())) {

        const { email: emailsData } = await Actor.getInput();

        if (emailsData) {
          for (const emailData of emailsData) {
            await Utils.sendEmail(emailData, validity, text);
          }
        }

      }

    }
  }
});

src/routes.js

import { Actor } from 'apify';

export class Utils {

  static parseDate(input) {
    const dateRegexp = /(\d{1,2}\. ?\d{1,2}\. ?\d{4})[^\d]*(\d{1,2}:\d{1,2})[^\d]*(\d{1,2}:\d{1,2})/;

    const match = input.match(dateRegexp);

    if (match?.length === 4) {
      const date = match[1].split('.');

      const year = parseInt(date[2]);
      const month = parseInt(date[1]);
      const day = parseInt(date[0]);

      const parsedDate = new Date(year, month - 1, day);

      const from = match[2];
      const to = match[3];

      return new Validity(parsedDate, from, to);

    }

    return null;
  }

  static isSameDay(a, b) {
    return a.getDate() === b.getDate() && a.getMonth() === b.getMonth() && a.getFullYear() === b.getFullYear();
  }

  static getResult(validity, text) {
    const { date } = validity;

    return {
      Date: `${date.getFullYear()}-${(date.getMonth() + 1).toString().padStart(2, '0')}-${date.getDate().toString().padStart(2, '0')}`,
      From: validity.from,
      To: validity.to,
      Text: text,
    };
  }

  static async sendEmail(emailData, validity, text) {

    await Actor.call('apify/send-mail', {
      to: emailData.to,
      cc: emailData.cc,
      bcc: emailData.bcc,
      subject: `Kaktus dobíječka dnes od ${validity.from} do ${validity.to}`,
      text: text,
    });

  }

}

export class Validity {
  constructor(date, from, to) {
    this.date = date;
    this.from = from;
    this.to = to;
  }

}


src/utils.js

import { assert } from 'chai';

import { Utils, Validity } from '../src/utils.js';

describe('isSameDay', () => {

  it('should should return true for same days', () => {
    assert.isTrue(Utils.isSameDay(new Date(), new Date()));
    assert.isTrue(Utils.isSameDay(new Date(2022, 9, 23), new Date(2022, 9, 23, 15, 10, 0)));
  });

  it('should should return false for different days', () => {
    assert.isFalse(Utils.isSameDay(new Date(2022, 10, 23), new Date(2022, 9, 23)));
  });

});

describe('parseDate', () => {

  it('should parse date from string', () => {
    assert.deepEqual(Utils.parseDate('Pokud si dneska 12. 10. 2022 od 17:00 do 20:00 hodin dobiješ alespoň 200 Kč, dáme ti dvojnásob'), new Validity(new Date(2022, 9, 12), '17:00', '20:00'));
  });

  it('should not parse date from string', () => {
    assert.notDeepEqual(Utils.parseDate('Pokud si dneska 13. 10. 2022 od 17:00 do 20:00 hodin dobiješ alespoň 200 Kč, dáme ti dvojnásob'), new Validity(new Date(2022, 9, 12), '17:00', '20:00'));
    assert.isNull(Utils.parseDate('test'));
  });
});

test/test.js

Actor which checks date of top up double action for Czech phone operator Kaktus. It returns date and from-to when this action was available for last time. It's possible to set e-mail for sending notification if the day is today.

Kaktus dobíječka

Kaktus dobíječka · Apify

Input · Kaktus dobíječka · Apify

API · Kaktus dobíječka · Apify

Source code · Kaktus dobíječka · Apify

Related Actors · Kaktus dobíječka · Apify

Actor which checks date of top up double action for Czech phone operator Kaktus. It returns date and from-to when this action was available for last time. It's possible to set e-mail for sending no...

Where next?