OMR Review Scraper

# 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:20

# Check preinstalled packages
RUN npm ls crawlee apify puppeteer playwright

# 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

{
    "actorSpecification": 1,
    "name": "my-actor",
    "title": "Scrape single page in JavaScript",
    "description": "Scrape data from single page with provided URL.",
    "version": "0.0",
    "meta": {
        "templateId": "js-start"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "schemaVersion": 1,
  "type": "object",
  "title": "Input Schema for Review Scraper",
  "description": "Schema for the input to the Actor that scrapes reviews.",
  "properties": {
    "url": {
      "type": "string",
      "title": "URL to scrape",
      "description": "The URL of the webpage containing reviews to scrape.",
      "editor": "textfield",
      "default": "https://omr.com/en/reviews/product/microsoft-teams/all"
    },
    "maxReviews": {
      "type": "integer",
      "title": "Maximum Reviews",
      "description": "The maximum number of reviews to scrape (e.g., 100).",
      "editor": "number",
      "default": 100
    }
  },
  "required": ["url"],
  "additionalProperties": false
}

1import { Actor } from 'apify';
2import axios from 'axios';
3import * as cheerio from 'cheerio';
4
5await Actor.init();
6
7const input = await Actor.getInput();
8const { url, maxReviews = 100 } = input;
9
10let currentPage = 1;
11const reviews = [];
12
13// Proxy rotation setup using actor-provided proxy URLs
14const proxyUrls = process.env.APIFY_PROXY_URLS?.split(',') || [];
15let proxyIndex = 0;
16
17while (reviews.length < maxReviews) {
18    const currentPageUrl = `${url}/${currentPage}`;
19    console.log(`Scraping page: ${currentPageUrl}`);
20
21    try {
22        // Use proxy URLs if available
23        const proxyUrl = proxyUrls.length > 0 ? proxyUrls[proxyIndex % proxyUrls.length] : null;
24        proxyIndex++;
25
26        const axiosConfig = proxyUrl
27            ? {
28                  proxy: false,
29                  httpsAgent: new (require('https-proxy-agent'))(proxyUrl),
30              }
31            : {};
32
33        // Fetch the HTML content of the current page
34        const response = await axios.get(currentPageUrl, axiosConfig);
35        const $ = cheerio.load(response.data);
36
37        // Extract reviews from the current page
38        const pageReviews = [];
39        $('[data-testid="text-review-quotes"]').each((i, element) => {
40            if (reviews.length + pageReviews.length >= maxReviews) return false;
41
42            const positive = $(element).find('[data-testid="text-review-quotes-positive"] [data-testid="review-quote-answer"]').text().trim() || '';
43            const negative = $(element).find('[data-testid="text-review-negative"] [data-testid="review-quote-answer"]').text().trim() || '';
44            const problems = $(element).find('[data-testid="text-review-problems"] [data-testid="review-quote-answer"]').text().trim() || '';
45            const dateText = $(element).closest('[data-testid="review-card"]').find('[data-testid="review-author-date"]').text().trim() || '';
46
47            // Parse the date text into a JavaScript Date object
48            const parsedDate = dateText ? new Date(Date.parse(dateText.replace('Older than', '').trim())) : null;
49
50            pageReviews.push({
51                Positive: positive,
52                Negative: negative,
53                Problems: problems,
54                Date: parsedDate,
55                OriginalDate: dateText
56            });
57        });
58
59        reviews.push(...pageReviews);
60
61        if (reviews.length >= maxReviews) break;
62
63        if (pageReviews.length === 0) {
64            console.log('No more reviews found on this page. Ending pagination.');
65            break;
66        }
67
68        currentPage++;
69    } catch (error) {
70        console.error(`Failed to fetch page: ${currentPageUrl}`, error);
71        break;
72    }
73}
74
75// Sort reviews by date in descending order
76reviews.sort((a, b) => (b.Date || 0) - (a.Date || 0));
77
78// Save the extracted reviews to the default dataset
79await Actor.pushData(reviews);
80
81console.log(`${reviews.length} reviews extracted.`);
82
83await Actor.exit();

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

# This file tells Git which files shouldn't be added to source control
.DS_Store
.idea
dist
node_modules
apify_storage
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

{
    "name": "js-scrape-single-page",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.2.6",
        "axios": "^1.5.0",
        "cheerio": "^1.0.0-rc.12"
    },
    "scripts": {
        "start": "node ./src/main.js",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}