Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bugs/misc #18

Merged
merged 2 commits into from
Mar 18, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

5 changes: 3 additions & 2 deletions package.json
Original file line number Diff line number Diff line change
Expand Up @@ -31,9 +31,10 @@
"json2csv": "^5.0.7",
"puppeteer-extra": "^3.3.6",
"puppeteer-extra-plugin-adblocker": "^2.13.6",
"puppeteer-extra-plugin-block-resources": "^2.4.3"
"puppeteer-extra-plugin-block-resources": "^2.4.3",
"rand-user-agent": "^2.0.4"
},
"devDependencies": {
"eslint": "^8.36.0"
}
}
}
16 changes: 13 additions & 3 deletions scrapers/hotel.js
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
// Dependencies
import { Chalk } from 'chalk';
import randUserAgent from "rand-user-agent";



// Environment variables
let { IS_PROVISIONER } = process.env;
Expand All @@ -25,9 +28,13 @@ const customChalk = new Chalk({ level: colorLevel });
*/
const extractAllReviewPageUrls = async (hotelUrl, position, browser) => {
try {
// Open a new page

// Generate a random user agent
const agent = randUserAgent("desktop");

// Open a new page with the generated user agent
const page = await browser.getNewPage()
await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3419.0 Safari/537.36');
await page.setUserAgent(agent);

// Navigate to the hotel page
await page.goto(hotelUrl);
Expand Down Expand Up @@ -129,9 +136,12 @@ const extractAllReviewPageUrls = async (hotelUrl, position, browser) => {
const scrape = async (totalReviewCount, reviewPageUrls, position, hotelName, hotelId, browser) => {
try {

// Generate a random user agent
const agent = randUserAgent("desktop");

// Open a new page
const page = await browser.getNewPage()
await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3419.0 Safari/537.36');
await page.setUserAgent(agent);

// Array to hold the review info
const allReviews = [];
Expand Down
10 changes: 8 additions & 2 deletions scrapers/resto.js
Original file line number Diff line number Diff line change
Expand Up @@ -24,10 +24,12 @@ const customChalk = new Chalk({ level: colorLevel });
const extractAllReviewPageUrls = async (restoUrl, position, language, browser) => {
try {

// Generate a random user agent
const agent = randUserAgent("desktop");

// Open a new page
const page = await browser.getNewPage()
await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3419.0 Safari/537.36');
await page.setUserAgent(agent);

// Navigate to the resto page
await page.goto(restoUrl);
Expand Down Expand Up @@ -203,9 +205,13 @@ const extractAllReviewPageUrls = async (restoUrl, position, language, browser) =
const scrape = async (totalReviewCount, reviewPageUrls, position, restoName, restoId, language, browser) => {
try {

// Generate a random user agent
const agent = randUserAgent("desktop");


// Open a new page
const page = await browser.getNewPage()
await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3419.0 Safari/537.36');
await page.setUserAgent(agent);

// Array to hold all the reviews
const allReviews = [];
Expand Down