OMR Review Scraper
No credit card required
No credit card required
Scrapes software reviews from OMR
Actor Metrics
4 monthly users
2 stars
>99% runs succeeded
Created in Dec 2024
Modified a month ago
ManM
1# Specify the base Docker image. You can read more about
2# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
3# You can also use any other image from Docker Hub.
4FROM apify/actor-node:20
5
6# Check preinstalled packages
7RUN npm ls crawlee apify puppeteer playwright
8
9# Copy just package.json and package-lock.json
10# to speed up the build using Docker layer cache.
11COPY package*.json ./
12
13# Install NPM packages, skip optional and development dependencies to
14# keep the image small. Avoid logging too much and print the dependency
15# tree for debugging
16RUN npm --quiet set progress=false \
17 && npm install --omit=dev --omit=optional \
18 && echo "Installed NPM packages:" \
19 && (npm list --omit=dev --all || true) \
20 && echo "Node.js version:" \
21 && node --version \
22 && echo "NPM version:" \
23 && npm --version \
24 && rm -r ~/.npm
25
26# Next, copy the remaining files and directories with the source code.
27# Since we do this after NPM install, quick build will be really fast
28# for most source file changes.
29COPY . ./
30
31
32# Run the image.
33CMD npm start --silent1{
2 "actorSpecification": 1,
3 "name": "my-actor",
4 "title": "Scrape single page in JavaScript",
5 "description": "Scrape data from single page with provided URL.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "js-start"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile"
12}1{
2 "$schema": "http://json-schema.org/draft-07/schema#",
3 "schemaVersion": 1,
4 "type": "object",
5 "title": "Input Schema for Review Scraper",
6 "description": "Schema for the input to the Actor that scrapes reviews.",
7 "properties": {
8 "url": {
9 "type": "string",
10 "title": "URL to scrape",
11 "description": "The URL of the webpage containing reviews to scrape.",
12 "editor": "textfield",
13 "default": "https://omr.com/en/reviews/product/microsoft-teams/all"
14 },
15 "maxReviews": {
16 "type": "integer",
17 "title": "Maximum Reviews",
18 "description": "The maximum number of reviews to scrape (e.g., 100).",
19 "editor": "number",
20 "default": 100
21 }
22 },
23 "required": ["url"],
24 "additionalProperties": false
25}1import { Actor } from 'apify';
2import axios from 'axios';
3import * as cheerio from 'cheerio';
4
5await Actor.init();
6
7const input = await Actor.getInput();
8const { url, maxReviews = 100 } = input;
9
10let currentPage = 1;
11const reviews = [];
12
13// Proxy rotation setup using actor-provided proxy URLs
14const proxyUrls = process.env.APIFY_PROXY_URLS?.split(',') || [];
15let proxyIndex = 0;
16
17while (reviews.length < maxReviews) {
18 const currentPageUrl = `${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();1# configurations
2.idea
3
4# crawlee and apify storage folders
5apify_storage
6crawlee_storage
7storage
8
9# installed files
10node_modules
11
12# git folder
13.git1# This file tells Git which files shouldn't be added to source control
2.DS_Store
3.idea
4dist
5node_modules
6apify_storage
7storage/*
8!storage/key_value_stores
9storage/key_value_stores/*
10!storage/key_value_stores/default
11storage/key_value_stores/default/*
12!storage/key_value_stores/default/INPUT.json1{
2 "name": "js-scrape-single-page",
3 "version": "0.0.1",
4 "type": "module",
5 "description": "This is an example of an Apify actor.",
6 "engines": {
7 "node": ">=18.0.0"
8 },
9 "dependencies": {
10 "apify": "^3.2.6",
11 "axios": "^1.5.0",
12 "cheerio": "^1.0.0-rc.12"
13 },
14 "scripts": {
15 "start": "node ./src/main.js",
16 "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
17 },
18 "author": "It's not you it's me",
19 "license": "ISC"
20}