Skip to content

Refactor Inetum scraper to streamline pagination and improve job data extraction #671

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.

Sign up for GitHub

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

Merged
lalalaurentiu merged 1 commit into from
Dec 12, 2025
Merged

Refactor Inetum scraper to streamline pagination and improve job data extraction #671

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
36 changes: 22 additions & 14 deletions sites/inetum.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,40 +1,40 @@
from scraper.Scraper import Scraper
import json
from getCounty import GetCounty
from utils import translate_city, publish_logo, publish_or_update, show_jobs
from math import ceil

_counties = GetCounty()
url = "https://www.inetum.com/en/jobs?f%5B0%5D=region%3A1068"

company = {"company": "Inetum"}
finalJobs = list()

headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
}

scraper = Scraper()
scraper.set_headers(headers)
scraper.get_from_url(url)

totalJobs = int(scraper.find("li", {"id": "1068"}).find("span", {"class":"facet-item__count"}).text.replace("(", "").replace(")", "").strip())

paginations = ceil(totalJobs / 9)
page = 1

for page in range(paginations):
scraper.get_from_url("https://www.inetum.com/en/jobs?f%5B0%5D=region%3A1068&page=" + str(page))

jobs = scraper.find_all("div", {"class": "node node-job node-teaser"})
jobs = scraper.find_all("div", {"class": "node node-job node-teaser"})

while jobs:
page += 1
for job in jobs:
job_title = job.find("h3", {"class":"card-title"}).text.strip()
job_title = job.find("h3", {"class": "card-title"}).text.strip()
job_link = "https://www.inetum.com" + job.find("a").get("href")
city = translate_city(job.find("p", {"class": "card-text"}).text.split("-")[-1].split("/")[0].strip())
city = translate_city(job.find(
"p", {"class": "card-text"}).text.split("-")[-1].split("/")[0].strip())
county = _counties.get_county(city)
remote = []

jobs_types = ["remote", "hybrid"]


for types in jobs_types:
if types in job.find("p", {"class": "card-text"}).text.split("-")[-1].strip():
remote.append(types)
remote.append(types)

finalJobs.append({
"job_title": job_title,
Expand All @@ -46,10 +46,18 @@
"remote": remote,
})

scraper = Scraper()
scraper.set_headers(headers)
scraper.get_from_url(
"https://www.inetum.com/en/jobs?f%5B0%5D=region%3A1068&page=" +
str(page)
)
jobs = scraper.find_all("div", {"class": "node node-job node-teaser"})


publish_or_update(finalJobs)

logoUrl = "https://vtlogo.com/wp-content/uploads/2021/05/inetum-vector-logo-small.png"
publish_logo(company.get("company"), logoUrl)

show_jobs(finalJobs)
show_jobs(finalJobs)