fetch-ecommerce-image avatar
fetch-ecommerce-image
Try for free

No credit card required

View all Actors
fetch-ecommerce-image

fetch-ecommerce-image

red_vault/fetch-ecommerce-image
Try for free

No credit card required

Get amazon and flipkart product image

.actor/Dockerfile

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:18
5
6# Copy just package.json and package-lock.json
7# to speed up the build using Docker layer cache.
8COPY package*.json ./
9
10# Install NPM packages, skip optional and development dependencies to
11# keep the image small. Avoid logging too much and print the dependency
12# tree for debugging
13RUN npm --quiet set progress=false \
14    && npm install --omit=dev --omit=optional \
15    && echo "Installed NPM packages:" \
16    && (npm list --omit=dev --all || true) \
17    && echo "Node.js version:" \
18    && node --version \
19    && echo "NPM version:" \
20    && npm --version \
21    && rm -r ~/.npm
22
23# Next, copy the remaining files and directories with the source code.
24# Since we do this after NPM install, quick build will be really fast
25# for most source file changes.
26COPY . ./
27
28
29# Run the image.
30CMD npm start --silent

.actor/actor.json

1{
2    "actorSpecification": 1,
3    "name": "fetch-amazon-image",
4    "title": "Project Cheerio Crawler Javascript",
5    "description": "Crawlee and Cheerio project in javascript.",
6    "version": "0.0",
7    "meta": {
8        "templateId": "js-crawlee-cheerio"
9    },
10    "input": "./input_schema.json",
11    "dockerfile": "./Dockerfile"
12}

.actor/input_schema.json

1{
2    "title": "CheerioCrawler Template",
3    "type": "object",
4    "schemaVersion": 1,
5    "properties": {
6        "pageurl": {
7            "title": "URL",
8            "type": "string",
9            "editor": "textfield",
10            "description": "Product URL",
11            "default": "https://crawlee.dev"
12        },
13        "asincode": {
14            "title": "asincode",
15            "type": "string",
16            "editor": "textfield",
17            "description": "Asin code for the product",
18            "default": "B0B4N77Y34"
19        },
20        "type": {
21            "title": "Type: asin or search",
22            "type": "string",
23            "editor": "textfield",
24            "description": "Must be one from asin or search",
25            "default": "asin"
26        },
27        "service": {
28            "title": "Type: amazon or flipkart",
29            "type": "string",
30            "editor": "textfield",
31            "description": "Must be one amazon or flipkart",
32            "default": "amazon"
33        },
34        "maxRequestsPerCrawl": {
35            "title": "Max Requests per Crawl",
36            "type": "integer",
37            "description": "Maximum number of requests that can be made by this crawler.",
38            "default": 100
39        }
40    }
41}

src/main.js

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    pageurl = 'https://crawlee.dev',
15    asincode = 'B0B4N77Y34',
16    type = 'asin',
17    service = 'amazon',
18    maxRequestsPerCrawl = 100,
19} = await Actor.getInput() ?? {};
20 
21const proxyConfiguration = await Actor.createProxyConfiguration();
22
23if(type === 'search' && service === 'amazon'){
24    const crawler = new CheerioCrawler({
25        maxRequestRetries: 5,
26        proxyConfiguration,
27        maxRequestsPerCrawl,
28        async requestHandler({ request, $, log }) {
29            log.info('enqueueing new URLs');
30
31            const image = $('#landingImage').attr('src');
32            log.info('Log', { url: request.loadedUrl, image });
33
34            await Dataset.pushData({ image })
35        },
36    });
37
38    await crawler.run([pageurl]);
39}
40
41if(type === 'asin' && service === 'amazon'){
42    const crawler = new CheerioCrawler({
43        maxRequestRetries: 5,
44        proxyConfiguration,
45        maxRequestsPerCrawl,
46        async requestHandler({ request, $, log }) {
47            log.info('enqueueing new URLs');
48
49            const image = $('#aod-asin-image-id').attr('src');
50            log.info('Log', { url: request.loadedUrl, image });
51
52            await Dataset.pushData({ image })
53        },
54    });
55
56    await crawler.run([`https://www.amazon.in/gp/aod/ajax?asin=${asincode}&ref=auto_load_aod&pc=dp`]);
57}
58
59if(type === 'search' && service === 'flipkart'){
60    const crawler = new CheerioCrawler({
61        maxRequestRetries: 5,
62        proxyConfiguration,
63        maxRequestsPerCrawl,
64        async requestHandler({ request, $, log }) {
65            log.info('enqueueing new URLs');
66            
67            const ogImage = $('meta[property="og:image"]').attr('content');
68            const addToCartButton = $('button:contains("Add to cart")');
69            const buyNowButton = $('button:contains("Buy Now")');
70    
71            if (ogImage) {
72                log.info('Log', { url: request.loadedUrl });
73
74                await Dataset.pushData({ image: ogImage });
75            } else if(addToCartButton.length == 0 && buyNowButton.length == 0) {
76                // get the first image from the search result
77
78                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');
79                const image = images[0];
80
81                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")
82                const categoryImage = category[0];
83
84                if(image){
85                    log.info('Log', { url: request.loadedUrl });
86
87                    await Dataset.pushData({ image: image.attribs.src });
88                }else if(categoryImage){
89                    log.info('Log', { url: request.loadedUrl });
90
91                    await Dataset.pushData({ image: categoryImage.attribs.src });
92                }
93            } else if(addToCartButton.length > 0 && buyNowButton.length > 0){
94                // get the landing page image
95
96                const image = $('img[loading="eager"]')[0];
97                if(image){
98                    log.info('Log', { url: request.loadedUrl });
99
100                    await Dataset.pushData({ image: image.attribs.src });
101                }
102            } else {
103                // If no Open Graph image is found, use a fallback (e.g., favicon)
104
105                const favicon = $('link[rel="icon"]').attr('href');
106                if (favicon) {
107                    log.info('Log', { url: request.loadedUrl });
108
109                    await Dataset.pushData({ image: favicon });
110                }
111            }
112        },
113    });
114
115    await crawler.run([pageurl]);
116}
117
118// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
119await Actor.exit();

.dockerignore

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.git

.editorconfig

1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf

.eslintrc

1{
2    "extends": "@apify",
3    "root": true
4}

.gitignore

1# This file tells Git which files shouldn't be added to source control
2
3.DS_Store
4.idea
5dist
6node_modules
7apify_storage
8storage

oldmain.js

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();

package.json

1{
2    "name": "crawlee-cheerio-javascript",
3    "version": "0.0.1",
4    "type": "module",
5    "description": "This is a boilerplate of an Apify actor.",
6    "engines": {
7        "node": ">=18.0.0"
8    },
9    "dependencies": {
10        "apify": "^3.1.10",
11        "crawlee": "^3.5.4"
12    },
13    "devDependencies": {
14        "@apify/eslint-config": "^0.4.0",
15        "eslint": "^8.50.0"
16    },
17    "scripts": {
18        "start": "node src/main.js",
19        "lint": "eslint ./src --ext .js,.jsx",
20        "lint:fix": "eslint ./src --ext .js,.jsx --fix",
21        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
22    },
23    "author": "It's not you it's me",
24    "license": "ISC"
25}
Developer
Maintained by Community
Actor metrics
  • 9 monthly users
  • 100.0% runs succeeded
  • days response time
  • Created in Feb 2024
  • Modified 14 days ago
Categories