Files
jobboard/plugins/readers/hibob.py
T
WolfandClaude Opus 5.5 c497fe965d Keep a description's headings, bullets and paragraphs, and draw them in the reader
The readers flattened a posting's HTML into one line with strip_html, so
sections and bullets ran together. _shared.html_text gives a line per
paragraph, '• ' before a list item and '## ' before a heading; every
reader's description goes through it, sections read per role get their
own headings, and the reader pane draws the lines as h3, ul and p.
Excerpts leave the marks out.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 21:40:12 +02:00

127 lines
5.4 KiB
Python

"""HiBob: `hibob:<subdomain>` for <subdomain>.careers.hibob.com, the whole
board in one JSON answer.
Written from Dixa's board (two general-application ads) and Liquidia's (14
roles) on 2026-09-29. The careers site's own API,
`<subdomain>.careers.hibob.com/api/job-ad`, answers 401 unless the request
carries the header `companyIdentifier: <subdomain>`. That header is the
company's public subdomain and no key or token, but it is why this is a paged
module, whose `page` may send headers, although it reads one page. Every ad
comes with its texts, so there is no `detail`. Pay is read from the
`payTransparency*` fields as they are named; no board seen so far had them
filled, so the period's spelling is a guess.
"""
from __future__ import annotations
import json
import logging
from collections.abc import Callable
from typing import Any
from ._contract import Ask, Fields, Reads, Row
from ._shared import Get, Page, html_text, label_slug_ok, num, only, parse_dt, pay_line, yearly_amount
log = logging.getLogger(__name__)
# One ad names one site: a company that hires at two sites posts two ads with
# their own ids (Dixa's "Expression of interest" at Copenhagen and London), so
# the host publishes one posting per place.
READS = Reads(
scope="board", listing="paged", text="listing", complete="end",
places="copies",
fields=Fields(pay="figures", posted="listed", remote="stated", employment="stated"),
robots=("read: /api/job-ad on <slug>.careers.hibob.com, whose /robots.txt answers the "
"single-page app's index page, no rules (dixa, checked 2026-09-30)"),
)
NAME = "hibob"
LABEL = "HiBob"
PATTERNS = (r"https?://([a-z0-9-]+)\.careers\.hibob\.com",)
#: The texts of an ad, in the order the ad shows them.
_SECTIONS = ("description", "responsibilities", "requirements", "benefits")
#: A pay period's spellings, as the word `pay_line` and `yearly_amount` take.
_PERIODS = {"year": "year", "yearly": "year", "annual": "year", "annually": "year",
"month": "month", "monthly": "month", "hour": "hour", "hourly": "hour",
"day": "day", "daily": "day", "week": "week", "weekly": "week"}
def _host(slug: str) -> str:
return f"{slug.lower()}.careers.hibob.com"
def slug_ok(slug: str) -> bool:
return label_slug_ok(slug)
def allowed(slug: str) -> Callable[[str], bool]:
return only(_host(slug))
def careers_url(slug: str) -> str:
return f"https://{_host(slug)}/"
def page(get: Get, slug: str, cursor: Any, ask: Ask) -> Page:
"""The one page: every ad, and no total or cursor, so the board is
complete when the answer parses. The host's robots.txt is its single-page
app's index page (a 200 with no rules), which allows."""
data = json.loads(get(f"https://{_host(slug)}/api/job-ad",
headers={"companyIdentifier": slug.lower(), "Accept": "application/json"}))
ads = data.get("jobAdDetails")
if not isinstance(ads, list):
raise ValueError("not a HiBob board: no jobAdDetails")
return data, [{"id": ad.get("id")} for ad in ads], None, None
def parse(body: bytes, slug: str) -> list[Row]:
return rows(json.loads(body), slug)
def rows(data: dict[str, Any], slug: str) -> list[Row]:
"""One answer -> one row per ad. `location` is the site with its country
(the country left off where the site already names it). `posted` is
`publishedAt`, which has nanoseconds. The description joins the ad's
texts, which are HTML in the ads with sections and plain text elsewhere."""
out = []
for ad in data.get("jobAdDetails") or []:
title = (ad.get("title") or "").strip()
ad_id = str(ad.get("id") or "").strip()
if not title or not ad_id:
continue
site = str(ad.get("site") or "").strip()
country = str(ad.get("country") or "").strip()
location = f"{site}, {country}" if site and country and country.lower() not in site.lower() \
else site or country
text = "\n".join(part for key in _SECTIONS
if (part := html_text(ad.get(key))))
lo, hi = num(ad.get("payTransparencyMinSalary")), num(ad.get("payTransparencyMaxSalary"))
currency = ad.get("payTransparencySalaryCurrency")
period = _PERIODS.get(str(ad.get("payTransparencySalaryPayPeriod") or "").strip().lower(), "")
salary_min, salary_max, code = yearly_amount(lo, hi, currency, period,
{"year": 1, "month": 12})
remote = {"remote": True, "hybrid": False, "on_site": False, "onsite": False}.get(
str(ad.get("workspaceTypeId") or "").strip().lower())
row: Row = {
"source_id": ad_id,
"title": title,
"places": [{"text": location, "remote": remote}] if location else [],
"location": location,
"url": f"https://{_host(slug)}/jobs/{ad_id}",
"posted": parse_dt(ad.get("publishedAt")),
"department": str(ad.get("department") or "").strip(),
"description": text,
"remote": str(ad.get("workspaceTypeId") or "").strip() or None,
"salary_text": pay_line(lo, hi, currency, period),
"salary_min": salary_min,
"salary_max": salary_max,
"currency": code,
}
if employment := str(ad.get("employmentType") or "").strip():
row["employment"] = employment
out.append(row)
return out