-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #88 from peviitor-ro/Laurentiu
Fixed Regnology scraper
- Loading branch information
Showing
1 changed file
with
52 additions
and
42 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,43 +1,53 @@ | ||
"use strict"; | ||
const scraper = require("../peviitor_scraper.js"); | ||
const uuid = require("uuid"); | ||
|
||
const url = "https://www.regnology.net/en/careers/?city=Romania#jobs"; | ||
|
||
const company = { company: "Regnology" }; | ||
let finalJobs = []; | ||
|
||
const s = new scraper.Scraper(url); | ||
|
||
s.soup | ||
.then((soup) => { | ||
const jobs = soup.find("ul", { class: "link-list" }).findAll("li"); | ||
|
||
jobs.forEach((job) => { | ||
const id = uuid.v4(); | ||
const job_title = job.find("a").text.trim(); | ||
const job_link = "https://www.regnology.net" + job.find("a").attrs.href; | ||
|
||
finalJobs.push({ | ||
id: id, | ||
job_title: job_title, | ||
job_link: job_link, | ||
city: "Romania", | ||
country: "Romania", | ||
company: company.company, | ||
}); | ||
}); | ||
}) | ||
.then(() => { | ||
console.log(JSON.stringify(finalJobs, null, 2)); | ||
|
||
scraper.postApiPeViitor(finalJobs, company); | ||
|
||
let logo = "https://www.regnology.net/project/frontend/build/logo-regnology.7537d456.svg"; | ||
|
||
let postLogo = new scraper.ApiScraper( | ||
"https://api.peviitor.ro/v1/logo/add/" | ||
); | ||
postLogo.headers.headers["Content-Type"] = "application/json"; | ||
postLogo.post(JSON.stringify([{ id: company.company, logo: logo }])); | ||
const { Scraper, postApiPeViitor } = require("peviitor_jsscraper"); | ||
|
||
const generateJob = (job_title, job_link) => ({ | ||
job_title, | ||
job_link, | ||
country: "Romania", | ||
city: "Sibiu", | ||
county: "Sibiu", | ||
remote: [], | ||
}); | ||
|
||
const getJobs = async () => { | ||
let url = | ||
"https://www.regnology.net/en/careers/?city=Romania#jobs"; | ||
const jobs = []; | ||
const scraper = new Scraper(url); | ||
|
||
let res = await scraper.get_soup("HTML"); | ||
let items = res.find("ul", { class: "link-list" }).findAll("li"); | ||
|
||
items.forEach((item) => { | ||
const job_title = item.find("h3").text.trim(); | ||
const job_link = "https://www.regnology.net" + item.find("a").attrs.href; | ||
|
||
jobs.push(generateJob(job_title, job_link)); | ||
}); | ||
return jobs; | ||
}; | ||
|
||
const getParams = () => { | ||
const company = "Regnology"; | ||
const logo = | ||
"https://www.regnology.net/project/frontend/build/logo-regnology.7537d456.svg"; | ||
const apikey = process.env.APIKEY; | ||
const params = { | ||
company, | ||
logo, | ||
apikey, | ||
}; | ||
return params; | ||
}; | ||
|
||
const run = async () => { | ||
const jobs = await getJobs(); | ||
const params = getParams(); | ||
postApiPeViitor(jobs, params); | ||
}; | ||
|
||
if (require.main === module) { | ||
run(); | ||
} | ||
|
||
module.exports = { run, getJobs, getParams }; // this is needed for our unit test job |