Actor picture

Cainiao Tracking Actor

nguyennk91/cainiao-tracking-actor

No credit card required

Author's avatarKen Nguyen
  • Modified
  • Users22
  • Runs585
Actor picture
Cainiao Tracking Actor

Dockerfile

# This is a template for a Dockerfile used to run acts in Actor system.
# The base image name below is set during the act build, based on user settings.
# IMPORTANT: The base image must set a correct working directory, such as /usr/src/app or /home/user
FROM apify/actor-node-chrome:v0.21.10

# Second, copy just package.json and package-lock.json since it should be
# the only file that affects "npm install" in the next step, to speed up the build
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 --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && (npm list --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# Copy source code to container
# Do this in the last step, to have fast build if only the source code changed
COPY --chown=myuser:myuser . ./

# NOTE: The CMD is already defined by the base image.
# Uncomment this for local node inspector debugging:
# CMD [ "node", "--inspect=0.0.0.0:9229", "main.js" ]

package.json

{
    "name": "apify-project",
    "version": "0.0.1",
    "description": "",
    "author": "It's not you it's me",
    "license": "ISC",
    "dependencies": {
        "apify": "0.21.10",
        "request-promise": "latest"
    },
    "scripts": {
        "start": "node main.js"
    }
}

main.js

const Apify = require('apify');
const request = require('request-promise');

Apify.main(async () => {
    // Get input of your actor
    const input = await Apify.getInput();
    console.log('Tracking Code:');
    console.dir(input.trackingCode);

    const requestList = new Apify.RequestList({
        sources: [{ url: 'https://global.cainiao.com/detail.htm?mailNoList='+input.trackingCode }],
    });
    await requestList.initialize();

    const crawler = new Apify.PuppeteerCrawler({
        requestList,
        handlePageFunction: async ({ page, request }) => {
            // This function is called to extract data from a single web page
            // 'page' is an instance of Puppeteer.Page with page.goto(request.url) already called
            // 'request' is an instance of Request class with information about the page to load
            await page
            .waitForSelector('#waybill_list_val_box');
            const element = await page.$("#waybill_list_val_box");
            const trackingRaw = await page.evaluate(element => element.textContent, element);
            console.log('Tracking Raw:');
            console.dir(trackingRaw);
            
            const parsedTracking = JSON.parse(trackingRaw);
        
            console.log('Tracking Detail:');
            console.dir(parsedTracking);
            // Save the data to dataset.
            await Apify.setValue('OUTPUT', parsedTracking);
        },
        handleFailedRequestFunction: async ({ request }) => {
            // This function is called when the crawling of a request failed too many times
            await Apify.pushData({
                url: request.url,
                succeeded: false,
                errors: request.errorMessages,
            });
        },
    });

    await crawler.run();
});