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>
155 lines
6.0 KiB
Python
155 lines
6.0 KiB
Python
"""Ashby: `ashby:<job board name>`, the whole board in one JSON answer. A
|
|
board name may carry a dot (`jimdo.com`) or be a uuid.
|
|
|
|
The field map is ported from `openings.go` in
|
|
[jobhunt-hq](https://github.com/rembrandtreyes/jobhunt-hq) (MIT).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import logging
|
|
from collections.abc import Callable
|
|
from typing import Any
|
|
|
|
|
|
from ._contract import Ask, Fields, Place, Reads, Row
|
|
from ._shared import add_place, html_text, is_web_url, num, only, parse_dt, path_slug_ok, pay_line, place, yearly_amount
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
NAME = "ashby"
|
|
LABEL = "Ashby"
|
|
RANK = 30
|
|
PATTERNS = (
|
|
r"jobs\.ashbyhq\.com/([A-Za-z0-9_.-]+)",
|
|
r"api\.ashbyhq\.com/posting-api/job-board/([A-Za-z0-9_.-]+)",
|
|
)
|
|
|
|
READS = Reads(
|
|
scope="board", listing="whole", text="listing", complete="whole",
|
|
places="many", empty="suspect",
|
|
fields=Fields(pay="figures", posted="trusted", remote="stated", employment="stated"),
|
|
robots=("read: api.ashbyhq.com answers /robots.txt with 401 and no rules, so "
|
|
"/posting-api/job-board/<slug> is not disallowed (checked 2026-09-30)"),
|
|
)
|
|
|
|
_API = "api.ashbyhq.com"
|
|
|
|
|
|
|
|
def slug_ok(slug: str) -> bool:
|
|
return path_slug_ok(slug)
|
|
|
|
|
|
def allowed(slug: str) -> Callable[[str], bool]:
|
|
return only(_API)
|
|
|
|
|
|
def careers_url(slug: str) -> str:
|
|
return f"https://jobs.ashbyhq.com/{slug}"
|
|
|
|
|
|
def feed_url(slug: str, ask: Ask) -> str:
|
|
return f"https://{_API}/posting-api/job-board/{slug}?includeCompensation=true"
|
|
|
|
|
|
def probe_url(slug: str) -> str:
|
|
return f"https://{_API}/posting-api/job-board/{slug}"
|
|
|
|
|
|
def probe_ok(body: bytes) -> bool:
|
|
"""Ashby answers an empty listing for an unknown name, so a listing
|
|
without jobs counts as no board."""
|
|
return b'"jobs":[' in body and b'"jobs":[]' not in body
|
|
|
|
|
|
def _salary(components: list[dict[str, Any]]) -> tuple[int | None, int | None, str]:
|
|
"""The yearly range from `compensation.summaryComponents` (needs
|
|
`?includeCompensation=true` on the feed URL, see `feed_url`): the first
|
|
`Salary` component, yearly or monthly (a monthly one multiplied by 12);
|
|
an hourly one is left out rather than annualised."""
|
|
for component in components:
|
|
if component.get("compensationType") != "Salary":
|
|
continue
|
|
return yearly_amount(component.get("minValue"), component.get("maxValue"),
|
|
component.get("currencyCode"), component.get("interval"),
|
|
{"1 YEAR": 1, "1 MONTH": 12})
|
|
return None, None, ""
|
|
|
|
|
|
def _salary_text(compensation: dict[str, Any]) -> str:
|
|
"""One line per `summaryComponents` entry that states a bound, labelled
|
|
by the board's own `compensationType` when more than one does (a salary
|
|
range beside a bonus range, say); with just the one, the label is left
|
|
off, the same as Greenhouse's. `interval` is "<n> <PERIOD>" ("1 YEAR",
|
|
"1 HOUR"); the last word, lowered, is the period. With nothing to build
|
|
a line from, Ashby's own prose summary (`compensationTierSummary`, else
|
|
`scrapeableCompensationSalarySummary`) is what is left to show."""
|
|
components = compensation.get("summaryComponents") or []
|
|
stated = [c for c in components if num(c.get("minValue")) is not None
|
|
or num(c.get("maxValue")) is not None]
|
|
lines = []
|
|
for component in stated:
|
|
period = str(component.get("interval") or "").split(" ")[-1].lower()
|
|
line = pay_line(num(component.get("minValue")), num(component.get("maxValue")),
|
|
component.get("currencyCode"), period)
|
|
if not line:
|
|
continue
|
|
if len(stated) > 1:
|
|
label = str(component.get("compensationType") or "").strip()
|
|
line = f"{label}: {line}" if label else line
|
|
lines.append(line)
|
|
if lines:
|
|
return "; ".join(lines)
|
|
return str(compensation.get("compensationTierSummary")
|
|
or compensation.get("scrapeableCompensationSalarySummary") or "")
|
|
|
|
|
|
def _places(j: dict[str, Any], workplace: str) -> list[Place]:
|
|
"""The primary `location`, then each of `secondaryLocations`, in the host's
|
|
words. The primary is remote or an office as `workplaceType` says; a
|
|
place that names itself remote is remote."""
|
|
primary = (j.get("location") or "").strip()
|
|
named = [(primary, {"remote": True, "hybrid": False, "onsite": False}.get(workplace.lower()))]
|
|
named += [(str((s or {}).get("location") or "").strip(), None)
|
|
for s in j.get("secondaryLocations") or []]
|
|
out: list[Place] = []
|
|
for text, remote in named:
|
|
add_place(out, place(text, remote))
|
|
return out
|
|
|
|
|
|
def parse(body: bytes, slug: str) -> list[Row]:
|
|
data = json.loads(body)
|
|
rows = []
|
|
for j in data.get("jobs") or []:
|
|
title = (j.get("title") or "").strip()
|
|
url = (j.get("jobUrl") or j.get("applyUrl") or "").strip()
|
|
if not title or not is_web_url(url):
|
|
continue
|
|
description = j.get("descriptionHtml") or j.get("descriptionPlain") or ""
|
|
compensation = j.get("compensation") or {}
|
|
salary_min, salary_max, currency = _salary(compensation.get("summaryComponents") or [])
|
|
workplace = str(j.get("workplaceType") or "").strip()
|
|
places = _places(j, workplace)
|
|
row: Row = {
|
|
"source_id": str(j.get("id") or ""),
|
|
"title": title,
|
|
"places": places,
|
|
"location": "; ".join(p["text"] for p in places),
|
|
"url": url,
|
|
"posted": parse_dt(j.get("publishedAt")),
|
|
"department": (j.get("department") or j.get("team") or "").strip(),
|
|
"description": html_text(description),
|
|
"remote": workplace or j.get("isRemote"), # `isRemote` is true for hybrid too
|
|
"salary_text": _salary_text(compensation),
|
|
"salary_min": salary_min,
|
|
"salary_max": salary_max,
|
|
"currency": currency,
|
|
}
|
|
if employment := str(j.get("employmentType") or "").strip():
|
|
row["employment"] = employment
|
|
rows.append(row)
|
|
return rows
|