# Specify the base Docker image. You can read more about
# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:18 AS builder

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./


# Install all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY . ./

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build

# Create final image
FROM apify/actor-node:18

# 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

# Copy built JS files from builder image
COPY --from=builder /usr/src/app/dist ./dist

# 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 run start:prod --silent


.actor/Dockerfile

google-jobs-scraper

Google jobs scraper

.actor/actor.json

Overview

.actor/dataset_schema.json

📅 Date posted

🌍 Domain

⌛ Employment type

🌐 Job language

📍 Location (country, city, region ...)

🔢 Max rows

🔎 Query

📍 Radius

Get data directly google jobs

.actor/input_schema.json

export enum DomainEnum {
  com = 'com',
  fr = 'fr',
  de = 'de',
  es = 'es',
  it = 'it',
  nl = 'nl',
  pl = 'pl',
  ru = 'ru',
  uk = 'uk',
  br = 'br',
  ca = 'ca',
  cn = 'cn',
  hk = 'hk',
  in = 'in',
  jp = 'jp',
  mx = 'mx',
  tw = 'tw',
  vn = 'vn',
  ar = 'ar',
  au = 'au',
  at = 'at',
  be = 'be',
  bg = 'bg',
  cl = 'cl',
  co = 'co',
  cr = 'cr',
  hr = 'hr',
  cz = 'cz',
  dk = 'dk',
  ec = 'ec',
  eg = 'eg',
  ee = 'ee',
  fi = 'fi',
  gr = 'gr',
  hu = 'hu',
  id = 'id',
  ie = 'ie',
  il = 'il',
  lv = 'lv',
  lt = 'lt',
}

export type Domain = keyof typeof DomainEnum;

export enum LanguageEnum {
  en = 'en',
  fr = 'fr',
  de = 'de',
  es = 'es',
  it = 'it',
  nl = 'nl',
  pl = 'pl',
  ru = 'ru',
  uk = 'uk',
  br = 'br',
  ca = 'ca',
  cn = 'cn',
  hk = 'hk',
  in = 'in',
  jp = 'jp',
  mx = 'mx',
  tw = 'tw',
  vn = 'vn',
  ar = 'ar',
  au = 'au',
  at = 'at',
  be = 'be',
  bg = 'bg',
  cl = 'cl',
  co = 'co',
  cr = 'cr',
  hr = 'hr',
  cz = 'cz',
  dk = 'dk',
  ec = 'ec',
  eg = 'eg',
  ee = 'ee',
  fi = 'fi',
  gr = 'gr',
  hu = 'hu',
  id = 'id',
  ie = 'ie',
  il = 'il',
  lv = 'lv',
  lt = 'lt',
}

export type Language = keyof typeof LanguageEnum;

export enum EmploymentTypeEnum {
  FULLTIME = 'FULLTIME',
  CONTRACTOR = 'CONTRACTOR',
  INTERN = 'INTERN',
  PARTTIME = 'PARTTIME',
}

export type EmploymentType = keyof typeof EmploymentTypeEnum;

export enum DatePostedEnum {
  today = 'today',
  '3days' = '3days',
  week = 'week',
  month = 'month',
}

export type DatePosted = keyof typeof DatePostedEnum;

export const RadiusEnum = {
  '2': '2',
  '10': '10',
  '25': '25',
  '50': '50',
  '100': '100',
  '300': '300',
  '1000': '1000',
} as const;

export type Radius = keyof typeof RadiusEnum;


src/dtos/global.dto.ts

// languages?: string[];
//     radius?: 2 | 10 | 25 | 50 | 100 | 300 | 1000;
//     employmentTypes?: ('FULLTIME' | 'CONTRACTOR' | 'INTERN' | 'PARTTIME')[];
//     datePosted?: 'today' | '3days' | 'week' | 'month';
//     location?: string;

import {
  DatePosted,
  Domain,
  EmploymentType,
  Language,
  Radius,
} from './global.dto.js';


export class ProxyInputDto {
  server: string;

  username?: string;

  password?: string;
}

export class GetJobInputDto {
  proxy: ProxyInputDto;

  query: string;

  session: string;

  domain: Domain;

  maxRows?: number;

  location?: string;

  languages?: Language[];

  radius?: Radius;

  employmentTypes?: EmploymentType[];

  datePosted?: DatePosted;
}


export class Input {
  query: string;

  domain: Domain;

  location?: string;

  language?: Language;

  radius?: Radius;

  employmentType?: EmploymentType;

  datePosted?: DatePosted;

  maxRows: number;

  constructor(input: any) {
    this.query = input.query;
    this.domain = input.domain;
    this.location = input.location;
    this.language = input.language;
    this.radius = input.radius;
    this.employmentType = input.employmentType;
    this.datePosted = input.datePosted;
    this.maxRows = input.maxRows;
  }

  toApiInput(proxy: ProxyInputDto, session: string): GetJobInputDto {
    return {
      query: this.query,
      domain: this.domain,
      location: this.location,
      languages: this.language ? [this.language] : undefined,
      radius: this.radius,
      employmentTypes: this.employmentType ? [this.employmentType] : undefined,
      datePosted: this.datePosted,
      proxy,
      session,
      maxRows: this.maxRows,
    };
  }
}


src/dtos/input.dto.ts

exports.__esModule;
import { Actor } from "apify";
import { io } from "socket.io-client";
// import { Logger } from "tslog";
import { Input } from "./dtos/input.dto.js";
import winston from "winston";
// import http from "http";
// import https from "https";
// import express from 'express';
// import httpProxy from 'http-proxy';

const logger = winston.createLogger({
  // level: 'info',
  format: winston.format.cli(),
  // defaultMeta: { service: 'user-service' },
  transports: [
    //
    // - Write all logs with importance level of `error` or less to `error.log`
    // - Write all logs with importance level of `info` or less to `combined.log`
    //
    // new winston.transports.File({ filename: 'error.log', level: 'error' }),
    // new winston.transports.File({ filename: 'combined.log' }),
    new winston.transports.Console(),
  ],
});
(async () => {
  try {
    await Actor.init();

    // const input = await Actor.getInput() as Input;

    const input = new Input(await Actor.getInput());

    // const proxyConfig = await (await Actor.createProxyConfiguration({
    //   groups: ["RESIDENTIAL"],
    // }))?.newProxyInfo();

    // const input = await Actor.getInput();
    const session = Actor.getEnv().actorRunId;

    // with params toto=R
    const socket = io(`https://api.google-jobs.cariz.fr?session=${session}`, {
      extraHeaders: {
        "x-api-key": "FGSD.UGORufgexsugfsefug57rt2+7hytj!sg/sdfuhqzg",
      },
      // autoConnect: false,
    });

    socket.on("ok", () => {
      logger.info("Send request to scraper");
      socket.emit("get-jobs", {
        // // query: input.query,
        // // domain: "com",
        // ...input,
        // session: session,
        // proxy: {
        //   server: "http://proxy.apify.com:8000/",
        //   username: "groups-BUYPROXIES94952",
        //   password: "apify_proxy_FZtOxOUocS7BgxegnTdaSTIMVu0Az746wgjV",
        // },
        ...input.toApiInput(
          {
            server: "http://proxy.apify.com:8000/",
            username: "groups-BUYPROXIES94952",
            password: "apify_proxy_FZtOxOUocS7BgxegnTdaSTIMVu0Az746wgjV",
          },
          session
        ),
      });
    });

    socket.on("connect", () => {
      logger.info("Socket connected");
    });

    socket.on("connect_error", async (err) => {
      logger.error("connect_error", err.message);
      await Actor.exit("Scraper connection error", { exitCode: 84 });
    });

    socket.on("connect_timeout", async (err) => {
      logger.error("connect_timeout", err.message);
      await Actor.exit("Scraper connection timeout", { exitCode: 84 });
    });

    socket.on("error", async (err) => {
      logger.error("error", err);
      await Actor.exit("Scraper error", { exitCode: 84 });
    });

    socket.on("disconnect", (reason) => {
      logger.warn("disconnect", reason);
    });

    socket.on("reconnect", (attemptNumber) => {
      logger.warn("reconnect", attemptNumber);
    });

    socket.on("reconnect_attempt", (attemptNumber) => {
      logger.warn("reconnect_attempt", attemptNumber);
    });

    socket.on("scraping.error", async (err) => {
      logger.error("job-scraping.error", err);
      await Actor.exit("Scraper error", { exitCode: 84 });
    });

    socket.on("scraping.end", async (payload) => {
      logger.info(
        `Scraping finished with ${payload.data.jobs.length} jobs scraped`
      );
      socket.disconnect();
    });

    socket.on("scraping.event", async (payload) => {
      const dataStr = payload.data ? JSON.stringify(payload.data) : undefined;
      (payload.event.includes('ko') ? logger.error : logger.info)(
        `EVENT: ${payload.event} => ${payload.message} ${dataStr ? dataStr.substring(0, dataStr.length > 100 ? 100 : dataStr.length) : ''}`
      );
      if (payload.event === "browser.job.ok") {
        await Actor.pushData(payload.data.job);
      }
    });


    // socket.connect();

    const socketClosedPromise = new Promise<void>((resolve) => {
      socket.on("disconnect", () => {
        console.log("Socket disconnected");
        resolve();
      });
    });

    await socketClosedPromise;

    console.log("end");
    await Actor.exit();
  } catch (error) {
    console.log(error);
    await Actor.exit();
  }
})();


src/main.ts

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

# dist folder
dist


.dockerignore

.gitignore

storage
apify_storage
crawlee_storage
node_modules
dist
tsconfig.tsbuildinfo
storage/*
!storage/key_value_stores
storage/key_value_stores/*
!storage/key_value_stores/default
storage/key_value_stores/default/*
!storage/key_value_stores/default/INPUT.json


.gitingore

Action

Contract type

Employee number range

Job language

Select search profession

Work type (remote or not)

Company sectors

Get data directly and fastly from Vinted

input_schema.json

package.json

pnpm-lock.yaml

tsconfig.json

tsconfig.tsbuildinfo

ℹ️ Discover the power of automation with Bebity's Google Jobs Scraper, an innovative Apify actor that retrieves job listings from Google Jobs in seconds. Tailored to your needs, it filters jobs by title, employment type, location, language, and domain, giving you access to global job opportunities.

🔥 Google Jobs Scraper (with highlights)

🔥 Google Jobs Scraper (with highlights) · Apify

Input · 🔥 Google Jobs Scraper (with highlights) · Apify

API · 🔥 Google Jobs Scraper (with highlights) · Apify

Related Actors · 🔥 Google Jobs Scraper (with highlights) · Apify

ℹ️ Discover the power of automation with Bebity's Google Jobs Scraper, an innovative Apify actor that retrieves job listings from Google Jobs in seconds. Tailored to your needs, it filters jobs by ...

Where next?