Cainiao Tracking Actor

# 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" ]

{
    "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"
    }
}

1const Apify = require('apify');
2const request = require('request-promise');
3
4Apify.main(async () => {
5    // Get input of your actor
6    const input = await Apify.getInput();
7    console.log('Tracking Code:');
8    console.dir(input.trackingCode);
9
10    const requestList = new Apify.RequestList({
11        sources: [{ url: 'https://global.cainiao.com/detail.htm?mailNoList='+input.trackingCode }],
12    });
13    await requestList.initialize();
14
15    const crawler = new Apify.PuppeteerCrawler({
16        requestList,
17        handlePageFunction: async ({ page, request }) => {
18            // This function is called to extract data from a single web page
19            // 'page' is an instance of Puppeteer.Page with page.goto(request.url) already called
20            // 'request' is an instance of Request class with information about the page to load
21            await page
22            .waitForSelector('#waybill_list_val_box');
23            const element = await page.$("#waybill_list_val_box");
24            const trackingRaw = await page.evaluate(element => element.textContent, element);
25            console.log('Tracking Raw:');
26            console.dir(trackingRaw);
27            
28            const parsedTracking = JSON.parse(trackingRaw);
29        
30            console.log('Tracking Detail:');
31            console.dir(parsedTracking);
32            // Save the data to dataset.
33            await Apify.setValue('OUTPUT', parsedTracking);
34        },
35        handleFailedRequestFunction: async ({ request }) => {
36            // This function is called when the crawling of a request failed too many times
37            await Apify.pushData({
38                url: request.url,
39                succeeded: false,
40                errors: request.errorMessages,
41            });
42        },
43    });
44
45    await crawler.run();
46});