Skip to content

Refactor Infineon scraper to update job listing URL and improve data … #665

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 2 commits into from
Nov 13, 2025
Merged

Refactor Infineon scraper to update job listing URL and improve data … #665

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bf94e93
Refactor Infineon scraper to update job listing URL and improve data …
lalalaurentiu Nov 12, 2025
d239012
Fix remote job type extraction to ensure consistent formatting
lalalaurentiu Nov 13, 2025
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
27 changes: 16 additions & 11 deletions sites/infineon.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,29 +1,34 @@
from scraper.Scraper import Scraper
from utils import publish_or_update, publish_logo, show_jobs, translate_city, get_jobtype
from utils import publish_or_update, publish_logo, show_jobs, translate_city
from getCounty import GetCounty

_counties = GetCounty()

start = 0
num = 10

url = f"https://jobs.infineon.com/api/apply/v2/jobs?domain=infineon.com&start={start}&num={num}&location=Romania&pid=563808958979269&domain=infineon.com&sort_by=relevance&triggerGoButton=false"
url = f"https://jobs.infineon.com/api/pcsx/search?domain=infineon.com&query=&location=Romania&start={start}&sort_by=distance&"

company = {"company": "Infineon"}
finaljobs = list()

scraper = Scraper()

scraper.get_from_url(url=url,type= "JSON", verify=False)
jobs = scraper.markup.get("positions")
jobs = scraper.markup.get("data").get("positions")

while len(jobs) > 0:
for job in jobs:
job_title = job.get("name")
job_link = job.get("canonicalPositionUrl")
city = translate_city(job.get("location").split(" ")[0].strip())
county = _counties.get_county(city)
remote = get_jobtype(job.get("work_location_option"))
job_link = "https://jobs.infineon.com" + job.get("positionUrl")
city = [
translate_city(location.split(",")[0])
for location in job.get("standardizedLocations", [])
]
county = [
c for city_name in city for c in _counties.get_county(city_name) or []
]
remote = [
type.lower() for type in job.get("efcustomTextWorkplaceType", [])
]

finaljobs.append({
"job_title": job_title,
Expand All @@ -36,9 +41,9 @@
})

start += 10
url = f"https://jobs.infineon.com/api/apply/v2/jobs?domain=infineon.com&start={start}&num={num}&location=Romania&pid=563808958979269&domain=infineon.com&sort_by=relevance&triggerGoButton=false"
url = f"https://jobs.infineon.com/api/pcsx/search?domain=infineon.com&query=&location=Romania&start={start}&sort_by=distance&"
scraper.get_from_url(url=url,type= "JSON", verify=False)
jobs = scraper.markup.get("positions")
jobs = scraper.markup.get("data").get("positions")

publish_or_update(finaljobs)

Expand Down