Files
jobboard/plugins/readers/hrmanager.py
T
WolfandClaude Opus 5.5 73dec9028e Rename plugins/atshosts to plugins/readers
Every import, test and live doc follows the new path; behaviour is unchanged.
tests/test_atshosts.py becomes tests/test_readers.py. plan-readers.md and
review-ingest.md keep the old name, since they describe the state before.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 08:48:30 +02:00

115 lines
4.1 KiB
Python

"""HR Manager (Talentech): `hrmanager:<customer>`, the public RSS of a
company's job portal, paged by `skip` and `take` with no stated total.
Written from four real boards on 2026-09-29: STS Group (6 roles), Flying
Tiger and KPMG (25 or more), and NNIT (none). The feed is
`api.hr-manager.net/JobPortal.svc/<customer>/PositionList/rss/?incads=true`;
without `take` it answers the first 25 roles whatever the board holds, and
`skip` and `take` were seen to page it (25 more with `skip=25`, 100 with
`take=100`). The customer is not case-sensitive (`FLYINGTIGER` answers as
`flyingtiger` does).
robots.txt: the portal's own pages on candidate.hr-manager.net disallow
everything for `*` except the application form, and so `robots_page` is the
feed's URL, on the API host, which has no robots.txt (a 404, which allows).
The feed is the interface HR Manager publishes for readers like this one; the
portal's HTML list, which the robots.txt does shut out, is never read. The
role's link is the application form the robots.txt names as allowed, and is
only shown, not fetched.
"""
from __future__ import annotations
import html
import re
import xml.etree.ElementTree as ET
from collections.abc import Callable
from typing import Any
from desk.sources import strip_html
from ._shared import Get, Page, Row, is_web_url, only, parse_dt
NAME = "hrmanager"
LABEL = "HR Manager"
PATTERNS = (
r"hr-manager\.net/vacancies/list\.aspx\?(?:[^\"'\s#<>]*?[&;])?customer=([A-Za-z0-9][A-Za-z0-9_-]*)",
r"api\.hr-manager\.net/JobPortal\.svc/([A-Za-z0-9][A-Za-z0-9_-]*)/",
)
_API = "api.hr-manager.net"
#: The roles asked for in one page. 100 were served at once at Flying Tiger; the
#: cursor moves on by what a page returned, so a smaller cap on the host's
#: side would not skip a role, and the read ends on an empty page.
PAGE_SIZE = 100
_SLUG = re.compile(r"[A-Za-z0-9][A-Za-z0-9_-]*")
def slug_ok(slug: str) -> bool:
return bool(_SLUG.fullmatch(slug))
def allowed(slug: str) -> Callable[[str], bool]:
return only(_API)
def careers_url(slug: str) -> str:
return f"https://candidate.hr-manager.net/vacancies/list.aspx?customer={slug}"
def _feed(slug: str, skip: int) -> str:
return (f"https://{_API}/JobPortal.svc/{slug}/PositionList/rss/"
f"?incads=true&skip={skip}&take={PAGE_SIZE}")
def robots_page(slug: str) -> str:
return _feed(slug, 0)
def page(get: Get, slug: str, cursor: Any) -> Page:
skip = int(cursor or 0)
items = _items(get(_feed(slug, skip), headers={"Accept": "application/rss+xml"}))
results = [{"id": item.findtext("guid") or item.findtext("link") or ""} for item in items]
return items, results, None, skip + len(items) if items else None
def parse(body: bytes, slug: str) -> list[Row]:
return rows(_items(body), slug)
def _items(body: bytes) -> list[ET.Element]:
"""`<rss><channel><item>...`. A board with no open roles is a channel
with no items, which is an empty board; an answer without a channel is
not a feed, and raises."""
channel = ET.fromstring(body).find("channel")
if channel is None:
raise ValueError("not an HR Manager feed: no channel")
return channel.findall("item")
def rows(items: list[ET.Element], slug: str) -> list[Row]:
"""One page of items. An item has the `guid` (the position's id), `link`
(its application form), `title`, the whole advertisement as escaped HTML
in `description` and `pubDate`. It names no place, department or pay: the
place, where there is one, is in the title or the text."""
out = []
for item in items:
title = (item.findtext("title") or "").strip()
url = (item.findtext("link") or "").strip()
if not title or not is_web_url(url):
continue
out.append({
"source_id": (item.findtext("guid") or url).strip(),
"title": title,
"location": "",
"url": url,
"posted": parse_dt(item.findtext("pubDate")),
"department": "",
"description": html.unescape(strip_html(item.findtext("description") or "")),
"remote": None,
"salary_text": "",
})
return out