# First, specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:16

# Second, copy just package.json and package-lock.json since those are the only
# files that affect "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 || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# 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 . ./

# Optionally, specify how to launch the source code of your actor.
# By default, Apify's base Docker images define the CMD instruction
# that runs the Node.js source code using the command specified
# in the "scripts.start" section of the package.json file.
# In short, the instruction looks something like this:
#
# CMD npm start


Dockerfile

To update crawler to another site, you need to change startUrls options!

The maximum number of times the scraper will retry to load each web page on error, in case of a page load error or an exception thrown by Page function. If set to <code>0</code>, the page will be considered failed right after the first error.

Max page retries

A static list of URLs to scrape. It is recommended to only use one start url. Just navigate to a company/product page and grab the url like so (ex: https://www.softwareadvice.com/fleet-management/gps-insight-profile/) and use that as the start URL. For details, see <a href='https://apify.com/apify/web-scraper#start-urls' target='_blank' rel='noopener'>Start URLs</a> in README.

Start URLs

Input Schema

INPUT_SCHEMA.json

// This is the main Node.js source code file of your actor.
// It is referenced from the "scripts" section of the package.json file.

const Apify = require('apify');

Apify.main(async () => {
 // Get input of the actor. Input fields can be modified in INPUT_SCHEMA.json file.
 // For more information, see https://docs.apify.com/actors/development/input-schema
 const input = await Apify.getInput();
 console.log('Input:');
 console.dir(input);

 // Here you can prepare your input for actor apify/web-scraper this input is based on a actor
 // task you used as the starting point.
 const metamorphInput = {
 "breakpointLocation": "NONE",
 "browserLog": false,
 "debugLog": false,
 "downloadCss": true,
 "downloadMedia": true,
 "ignoreCorsAndCsp": false,
 "ignoreSslErrors": false,
 "injectJQuery": true,
 "keepUrlFragments": false,
 "maxRequestRetries": input.maxRequestRetries,
 "pageFunction": // The function accepts a single argument: the "context" object.
 // For a complete list of its properties and functions,
 // see https://apify.com/apify/web-scraper#page-function 
 async function pageFunction(context) {
 // This statement works as a breakpoint when you're trying to debug your code. Works only with Run mode: DEVELOPMENT!
 // debugger; 
 // jQuery is handy for finding DOM elements and extracting data from them.
 // To use it, make sure to enable the "Inject jQuery" option.
 const $ = context.jQuery;
 
 let timeoutMillis; // undefined
 await context.waitFor(1000);
 // 2 sec timeout after the first.
 // get elements contained the wrapper class
 var node = document.querySelector(".wrapper")
 var href = "";
 // if this is not the reviews page, check to see if it has a full reviews page
 if (!context.request.url.endsWith("/reviews/")){
 context.log.info(context.request.url);
 
 for (let i= 0; i < node.childNodes.length; i++)
 {
 if(node.childNodes[i].childNodes[0].innerText == 'Reviews'){
 
 try{
 href = node.childNodes[i].childNodes[0].href;
 }catch{}
 break;
 }
 }
 context.log.info(href)
 // if the a tag had an href attribute, that means this has a full reviews page, so we will navigate there to get all the reviews
 if(href != ""){
 await context.enqueueRequest({ url: href });
 return;
 }
 }
 
 await context.waitFor(1500);
 // scrape all the reviews
 var fullReviewData = $("[data-testid='reviews-container']");
 
 
 var results = [];
 do{
 for (let i = 0; i < fullReviewData.length; i++ )
 {
 var score = "";
 var companySize = "";
 var industry = "";
 var timeUsed = "";
 var reviewSource = "";
 var date = "";
 var title = "";
 var summary = "";
 var pros = "";
 var cons = "";
 var date = "";
 
 try{
 score = fullReviewData[i].querySelectorAll("[data-testid='reviewers-rating'] .OverallStarRatingComponent .fullStar").length;
 }catch(error){}
 
 try{
 companySize = fullReviewData[i].querySelector('div.review-company > p > strong').innerText;
 }
 catch(error){}
 
 
 
 try{
 industry = fullReviewData[i].querySelector('div.review-gdm-industry > p > strong').innerText
 }
 catch(error){
 
 }
 try{
 timeUsed = fullReviewData[i].querySelector('div.review-profile-time-used > p > strong').innerText
 }
 catch(error){}
 try{
 reviewSource = fullReviewData[i].querySelector('div.tooltip > p').innerText
 }
 catch(error){}
 try{ 
 date = fullReviewData[i].querySelector("#reviews-list .review-date").innerText
 }
 catch(error){}
 try{ 
 title = fullReviewData[i].querySelector("[data-testid='review-title']").innerText
 }
 catch(error){}
 try{
 summary = fullReviewData[i].querySelector("[data-testid='review-summary']").innerText
 }
 catch(error){}
 try{
 pros = fullReviewData[i].querySelector("[data-testid='review-pros']").innerText
 }
 catch(error){}
 try{
 cons = fullReviewData[i].querySelector("[data-testid='review-cons']").innerText
 }
 catch(error){}
 results.push({"score":score,"companySize":companySize,"industry":industry,"timeUsed":timeUsed,"reviewSource":reviewSource,"date":date,"title":title,"summary":summary,"pros":pros,"cons":cons});
 
 }
 var button = document.getElementsByClassName("next");
 if (button == null || button.length != 1){
 button = null;
 }
 else {
 button[0].click();
 await context.waitFor(1500);
 }
 console.log("Hi");
 }while(button != null && results.length <= 250) // putting a limit on this so it does not time out
 
 
 // Print some information to actor log
 
 
 // Manually add a new page to the queue for scraping
 
 // Return an object with the data extracted from the page.
 // It will be stored to the resulting dataset.
 return {
 results: results
 };
 },
 "postNavigationHooks": `// We need to return array of (possibly async) functions here.
 // The functions accept a single argument: the "crawlingContext" object.
 [
 async (crawlingContext) => {
 // ...
 },
 ]`,
 "preNavigationHooks": `// We need to return array of (possibly async) functions here.
 // The functions accept two arguments: the "crawlingContext" object
 // and "gotoOptions".
 [
 async (crawlingContext, gotoOptions) => {
 // ...
 },
 ]`,
 "proxyConfiguration": {
 "useApifyProxy": true,
 "apifyProxyCountry": "US"
 },
 "startUrls": input.startUrls,
 "runMode": "PRODUCTION",
 "useChrome": false,
 "waitUntil": [
 "networkidle2"
 ]
 };

 // Now let's metamorph into actor apify/web-scraper using the created input.
 await Apify.metamorph('apify/web-scraper', metamorphInput);
});

Softwareadvicescrapereviews

Where next?