Export every open job from a Workday career site as JSON or CSV

curl -s https://mastercard.wd1.myworkdayjobs.com/robots.txt

curl -s -X POST "https://mastercard.wd1.myworkdayjobs.com/wday/cxs/mastercard/CorporateCareers/jobs" \
  -H "Content-Type: application/json" -H "Accept: application/json" \
  -d '{"appliedFacets":{},"limit":2,"offset":0,"searchText":""}' | python3 -m json.tool

{
    "total": 1037,
    "jobPostings": [
        {
            "title": "Manager, Software Engineering",
            "externalPath": "/job/Ramat-Gan-Israel/Manager--Software-Engineering_R-279658",
            "locationsText": "Ramat-Gan, Israel",
            "postedOn": "Posted Today",
            "bulletFields": [
                "R-279658"
            ]
        },
        {
            "title": "Manager, Accounting",
            "externalPath": "/job/Pune-India/Manager--Accounting_R-291473",
            "locationsText": "Pune, India",
            "postedOn": "Posted Today",
            "bulletFields": [
                "R-291473"
            ]
        }
    ],
    "facets": [
        {
            "facetParameter": "jobFamilyGroup",
            "descriptor": "Job Category",
            "values": [
                {
                    "descriptor": "Engineering",
                    "id": "189119ebe266100103737c3d6a6e0000",
                    "count": 260
                },

for offset in 0 1980 2000; do
  curl -s -X POST "https://nvidia.wd5.myworkdayjobs.com/wday/cxs/nvidia/NVIDIAExternalCareerSite/jobs" \
    -H "Content-Type: application/json" \
    -d "{\"appliedFacets\":{},\"limit\":20,\"offset\":$offset,\"searchText\":\"\"}" |
  python3 -c "import json,sys; d=json.load(sys.stdin); print($offset, d['total'], [p['bulletFields'][0] for p in d['jobPostings'][:2]])"
  sleep 1
done

curl -s -X POST "https://nvidia.wd5.myworkdayjobs.com/wday/cxs/nvidia/NVIDIAExternalCareerSite/jobs" \
  -H "Content-Type: application/json" \
  -d '{"appliedFacets":{},"limit":1,"offset":0,"searchText":""}' |
python3 -c "
import json, sys
d = json.load(sys.stdin)
f = next(f for f in d['facets'] if f['facetParameter'] == 'jobFamilyGroup')
for v in f['values'][:4]:
    print(v['count'], v['descriptor'], v['id'])
print('sum of all', len(f['values']), 'groups:', sum(v['count'] for v in f['values']))"

curl -s -X POST "https://nvidia.wd5.myworkdayjobs.com/wday/cxs/nvidia/NVIDIAExternalCareerSite/jobs" \
  -H "Content-Type: application/json" \
  -d '{"appliedFacets":{"jobFamilyGroup":["0c40f6bd1d8f10ae43ffaefd46dc7e78"]},"limit":20,"offset":0,"searchText":""}' |
python3 -c "import json,sys; print(json.load(sys.stdin)['total'])"

import json
jobs = json.load(open("jobs.json"))
print(len(jobs), "jobs")
print(sum((j["location"] or "").endswith("Locations") for j in jobs), 'say "N Locations" instead of a place')
print(sum(not j["location"] for j in jobs), "have no location text")
print(sum(j["posted"] == "Posted 30+ Days Ago" for j in jobs), 'say "Posted 30+ Days Ago"')

curl -s "https://mastercard.wd1.myworkdayjobs.com/wday/cxs/mastercard/CorporateCareers/job/Dublin-Ireland/Director--Product-Management--Developer-Experience_R-279947" \
  -H "Accept: application/json" |
python3 -c "
import json, sys
info = json.load(sys.stdin)['jobPostingInfo']
for k in ('title', 'jobReqId', 'location', 'additionalLocations', 'postedOn', 'startDate', 'timeType'):
    print(k, '=', info.get(k))
print('jobDescription =', len(info['jobDescription']), 'characters of HTML')"

"""Export every open job of one public Workday career site to jobs.json and jobs.csv.
Usage: python3 workday_jobs.py https://mastercard.wd1.myworkdayjobs.com/en-US/CorporateCareers"""
import csv, json, re, sys, time, urllib.request, urllib.robotparser

UA = "my-job-export/1.0 (contact: [email protected])"  # say who you are

def parse(url):
    m = re.match(r"https://([a-z0-9-]+)\.(wd\d+)\.myworkdayjobs\.com/(?:[a-z]{2}-[A-Z]{2}/)?([A-Za-z0-9_.-]+)", url)
    if not m:
        sys.exit("Not a myworkdayjobs.com career-site URL")
    return m.groups()  # tenant, data centre, site

tenant, wd, site = parse(sys.argv[1])
host = f"https://{tenant}.{wd}.myworkdayjobs.com"
api = f"{host}/wday/cxs/{tenant}/{site}/jobs"

robots = urllib.robotparser.RobotFileParser(f"{host}/robots.txt")
robots.read()
if not robots.can_fetch(UA, api):
    sys.exit(f"robots.txt of {host} does not allow {api}")

jobs, seen, offset, total = [], set(), 0, None
while True:
    body = json.dumps({"appliedFacets": {}, "limit": 20, "offset": offset, "searchText": ""}).encode()
    req = urllib.request.Request(api, data=body, headers={
        "Content-Type": "application/json", "Accept": "application/json", "User-Agent": UA})
    with urllib.request.urlopen(req, timeout=30) as r:
        page = json.load(r)
    if total is None:
        total = page["total"]  # only the first page reports the total
    posts = page.get("jobPostings") or []
    for p in posts:
        if p.get("externalPath") in seen:
            continue
        seen.add(p.get("externalPath"))
        jobs.append({
            "title": p.get("title"),
            "jobId": (p.get("bulletFields") or [""])[0],
            "location": p.get("locationsText"),
            "posted": p.get("postedOn"),
            "url": host + "/" + site + p.get("externalPath", ""),
        })
    offset += 20
    if not posts or offset >= min(total, 2000):  # the list stops at 2,000
        break
    time.sleep(1)  # one request a second

json.dump(jobs, open("jobs.json", "w"), indent=2)
with open("jobs.csv", "w", newline="") as f:
    w = csv.DictWriter(f, fieldnames=list(jobs[0]))
    w.writeheader()
    w.writerows(jobs)
print(f"{site}: {total} listed, {len(jobs)} exported")

python3 workday_jobs.py https://mastercard.wd1.myworkdayjobs.com/en-US/CorporateCareers
head -3 jobs.csv