fetch-ecommerce-image

# 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

# 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": "fetch-amazon-image",
    "title": "Project Cheerio Crawler Javascript",
    "description": "Crawlee and Cheerio project in javascript.",
    "version": "0.0",
    "meta": {
        "templateId": "js-crawlee-cheerio"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
    "title": "CheerioCrawler Template",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "pageurl": {
            "title": "URL",
            "type": "string",
            "editor": "textfield",
            "description": "Product URL",
            "default": "https://crawlee.dev"
        },
        "asincode": {
            "title": "asincode",
            "type": "string",
            "editor": "textfield",
            "description": "Asin code for the product",
            "default": "B0B4N77Y34"
        },
        "type": {
            "title": "Type: asin or search",
            "type": "string",
            "editor": "textfield",
            "description": "Must be one from asin or search",
            "default": "asin"
        },
        "service": {
            "title": "Type: amazon or flipkart",
            "type": "string",
            "editor": "textfield",
            "description": "Must be one amazon or flipkart",
            "default": "amazon"
        },
        "maxRequestsPerCrawl": {
            "title": "Max Requests per Crawl",
            "type": "integer",
            "description": "Maximum number of requests that can be made by this crawler.",
            "default": 100
        }
    }
}

1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
2import { Actor } from 'apify';
3// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
4import { CheerioCrawler, Dataset } from 'crawlee';
5import { PlaywrightCrawler } from 'crawlee';
6import { ProxyConfiguration } from 'apify';
7// this is ESM project, and as such, it requires you to specify extensions in your relative imports
8// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
9// import { router } from './routes.js';
10
11// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
12await Actor.init();
13
14// Structure of input is defined in input_schema.json
15const {
16    pageurl = 'https://www.amazon.in/gp/aod/ajax?asin=B0D945V84N&ref=auto_load_aod&pc=dp',
17    asincode = 'B0B4N77Y34',
18    type = 'asin',
19    service = 'amazon',
20    maxRequestsPerCrawl = 2,
21} = await Actor.getInput() ?? {};
22 
23//const proxyConfiguration = await Actor.createProxyConfiguration();
24const proxyConfiguration = new ProxyConfiguration({
25    groups: ['RESIDENTIAL'],
26    countryCode: 'US', // Optionally, you can specify the proxy country code.
27    // This is useful for sites like Amazon, which display different content based on the user's location.
28});
29
30if(type === 'search' && service === 'amazon'){
31    const crawler = new CheerioCrawler({
32        maxRequestRetries: 5,
33        proxyConfiguration,
34        maxRequestsPerCrawl,
35        async requestHandler({ request, $, log }) {
36            log.info('enqueueing new URLs');
37
38            const image = $('#landingImage').attr('src');
39            log.info('Log', { url: request.loadedUrl, image });
40
41            await Dataset.pushData({ image })
42        },
43    });
44
45    await crawler.run([pageurl]);
46}
47
48if(type === 'asin' && service === 'amazon'){
49    const crawler = new CheerioCrawler({
50        maxRequestRetries: 5,
51        proxyConfiguration,
52        maxRequestsPerCrawl,
53        handlePageFunction: ({ proxyInfo }) => {
54     const usedProxyUrl = proxyInfo.url; // Getting the proxy URL
55     log.info(usedProxyUrl)
56  },
57        async requestHandler({ request, $, log }) {
58            log.info('enqueueing new URLs');
59
60            const image = $('#aod-asin-image-id').attr('src');
61            log.info('Log', { url: request.loadedUrl, image });
62
63            await Dataset.pushData({ image })
64        },
65    });
66
67    await crawler.run([`https://www.amazon.in/gp/aod/ajax?asin=${asincode}&ref=auto_load_aod&pc=dp`]);
68}
69
70if(type === 'asin' && service === 'amazon_v2'){
71    const crawler = new PlaywrightCrawler({
72        maxRequestRetries: 5,
73        proxyConfiguration,
74        maxRequestsPerCrawl,
75        async requestHandler({ request, $, log }) {
76            log.info('enqueueing new URLs');
77
78            const image = $('#aod-asin-image-id').attr('src');
79            log.info('Log', { url: request.loadedUrl, image });
80
81            await Dataset.pushData({ image })
82        },
83    });
84
85    await crawler.run([`https://www.amazon.in/gp/aod/ajax?asin=${asincode}&ref=auto_load_aod&pc=dp`]);
86}
87
88if(type === 'search' && service === 'flipkart'){
89    const crawler = new CheerioCrawler({
90        maxRequestRetries: 5,
91        proxyConfiguration,
92        maxRequestsPerCrawl,
93        async requestHandler({ request, $, log }) {
94            log.info('enqueueing new URLs');
95            
96            const ogImage = $('meta[property="og:image"]').attr('content');
97            const addToCartButton = $('button:contains("Add to cart")');
98            const buyNowButton = $('button:contains("Buy Now")');
99    
100            if (ogImage) {
101                log.info('Log', { url: request.loadedUrl });
102
103                await Dataset.pushData({ image: ogImage });
104            } else if(addToCartButton.length == 0 && buyNowButton.length == 0) {
105                // get the first image from the search result
106
107                const images = $('div._1YokD2._2GoDe3 > div:nth-child(2) > div:nth-child(2) > div > div:nth-child(1) > div > a._2rpwqI > div:nth-child(1) > div > div > img');
108                const image = images[0];
109
110                const category = $("#container > div > div._36fx1h._6t1WkM._3HqJxg > div._1YokD2._2GoDe3 > div:nth-child(2) > div:nth-child(2) > div > div:nth-child(1) > div > a > div:nth-child(1) > div > div > div > img")
111                const categoryImage = category[0];
112
113                if(image){
114                    log.info('Log', { url: request.loadedUrl });
115
116                    await Dataset.pushData({ image: image.attribs.src });
117                }else if(categoryImage){
118                    log.info('Log', { url: request.loadedUrl });
119
120                    await Dataset.pushData({ image: categoryImage.attribs.src });
121                }
122            } else if(addToCartButton.length > 0 && buyNowButton.length > 0){
123                // get the landing page image
124
125                const image = $('img[loading="eager"]')[0];
126                if(image){
127                    log.info('Log', { url: request.loadedUrl });
128
129                    await Dataset.pushData({ image: image.attribs.src });
130                }
131            } else {
132                // If no Open Graph image is found, use a fallback (e.g., favicon)
133
134                const favicon = $('link[rel="icon"]').attr('href');
135                if (favicon) {
136                    log.info('Log', { url: request.loadedUrl });
137
138                    await Dataset.pushData({ image: favicon });
139                }
140            }
141        },
142    });
143
144    await crawler.run([pageurl]);
145}
146
147// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
148await Actor.exit();

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

root = true

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

{
    "extends": "@apify",
    "root": true
}

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

.DS_Store
.idea
dist
node_modules
apify_storage
storage

1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
2import { Actor } from 'apify';
3// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
4import { CheerioCrawler, Dataset } from 'crawlee';
5// this is ESM project, and as such, it requires you to specify extensions in your relative imports
6// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
7// import { router } from './routes.js';
8
9// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
10await Actor.init();
11
12// Structure of input is defined in input_schema.json
13const {
14    scrapurl = 'https://crawlee.dev',
15    type = 'asin',
16    maxRequestsPerCrawl = 100,
17} = await Actor.getInput() ?? {};
18
19const proxyConfiguration = await Actor.createProxyConfiguration();
20
21if(type === 'asin'){
22    const crawler = new CheerioCrawler({
23        maxRequestRetries: 5,
24        proxyConfiguration,
25        maxRequestsPerCrawl,
26        async requestHandler({ request, $, log }) {
27            log.info('enqueueing new URLs');
28
29            // Extract title from the page.
30            //const title = $('title').text();
31
32            const image = $('#landingImage').attr('src');
33            log.info('Log', { url: request.loadedUrl, image: image });
34
35            if(!image) return request.pushErrorMessage("Failed to fetch image");
36
37            // Save url and title to Dataset - a table-like storage.
38            await Dataset.pushData({ image })
39        },
40    });
41
42    await crawler.run([scrapurl]);
43}
44
45// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
46await Actor.exit();

{
    "name": "crawlee-cheerio-javascript",
    "version": "0.0.1",
    "type": "module",
    "description": "This is a boilerplate of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.1.10",
        "crawlee": "^3.5.4"
    },
    "devDependencies": {
        "@apify/eslint-config": "^0.4.0",
        "eslint": "^8.50.0"
    },
    "scripts": {
        "start": "node src/main.js",
        "lint": "eslint ./src --ext .js,.jsx",
        "lint:fix": "eslint ./src --ext .js,.jsx --fix",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}