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
5.8 KiB
Python
155 lines
5.8 KiB
Python
"""Lever: `lever:<site>`, or `lever:eu/<site>` for a board on Lever's EU
|
|
instance, the whole board in one JSON answer.
|
|
|
|
Lever runs two instances that share nothing but the API: `api.lever.co` and
|
|
`api.eu.lever.co`, with the pages on `jobs.lever.co` and `jobs.eu.lever.co`.
|
|
A site exists on one of them only (TomTom and Prima answer 404 on the other,
|
|
2026-09-29), and the same name on both would be two companies, so the region
|
|
is part of the slug. It is a prefix a plain site name cannot carry, since a
|
|
Lever site name has no slash, which leaves every `lever:<site>` target as it
|
|
was.
|
|
|
|
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__)
|
|
|
|
READS = Reads(
|
|
scope="board", listing="whole", text="listing", complete="whole",
|
|
places="many",
|
|
fields=Fields(pay="figures", posted="trusted", remote="stated", country="stated",
|
|
employment="stated"),
|
|
robots=("read: robots.txt of api.lever.co and api.eu.lever.co allows /, so "
|
|
"/v0/postings/<site>, with crawl-delay 1, one request a board (checked 2026-09-30)"),
|
|
)
|
|
|
|
NAME = "lever"
|
|
LABEL = "Lever"
|
|
RANK = 20
|
|
#: Two groups on the EU hosts, `eu` and the site, which discovery joins into
|
|
#: the slug `eu/<site>`.
|
|
PATTERNS = (
|
|
r"jobs\.lever\.co/([A-Za-z0-9_-]+)",
|
|
r"api\.lever\.co/v0/postings/([A-Za-z0-9_-]+)",
|
|
r"jobs\.(eu)\.lever\.co/([A-Za-z0-9_-]+)",
|
|
r"api\.(eu)\.lever\.co/v0/postings/([A-Za-z0-9_-]+)",
|
|
)
|
|
|
|
#: The region prefixes a slug may carry, to the infix of both host names.
|
|
_REGIONS = {"eu": "eu."}
|
|
|
|
|
|
def _split(slug: str) -> tuple[str, str]:
|
|
"""`(host infix, site)`: `("eu.", "tomtom")` for `eu/tomtom`, `("", "acme")`
|
|
for `acme`."""
|
|
region, sep, site = slug.partition("/")
|
|
return (_REGIONS.get(region, "?"), site) if sep else ("", slug)
|
|
|
|
|
|
def slug_ok(slug: str) -> bool:
|
|
infix, site = _split(slug)
|
|
return infix != "?" and path_slug_ok(site)
|
|
|
|
|
|
def allowed(slug: str) -> Callable[[str], bool]:
|
|
return only(f"api.{_split(slug)[0]}lever.co")
|
|
|
|
|
|
def careers_url(slug: str) -> str:
|
|
infix, site = _split(slug)
|
|
return f"https://jobs.{infix}lever.co/{site}"
|
|
|
|
|
|
def feed_url(slug: str, ask: Ask) -> str:
|
|
infix, site = _split(slug)
|
|
return f"https://api.{infix}lever.co/v0/postings/{site}?mode=json"
|
|
|
|
|
|
def probe_url(slug: str) -> str:
|
|
infix, site = _split(slug)
|
|
return f"https://api.{infix}lever.co/v0/postings/{site}?limit=1&mode=json"
|
|
|
|
|
|
def probe_slugs(guess: str) -> tuple[str, ...]:
|
|
"""A name is tried on both instances, the US one first, since a site that
|
|
names neither leaves no other way to tell which one it is on."""
|
|
return (guess, *(f"{region}/{guess}" for region in _REGIONS))
|
|
|
|
|
|
def _salary_text(salary_range: dict[str, Any]) -> str:
|
|
"""One line from `salaryRange`, whatever its `interval` — including an
|
|
hourly or daily one, which `yearly_amount` drops from the columns.
|
|
Lever's interval is "per-<period>-<kind>" ("per-year-salary",
|
|
"per-hour-wage"); the middle word is the period."""
|
|
interval = str(salary_range.get("interval") or "")
|
|
parts = interval.split("-")
|
|
period = parts[1] if len(parts) >= 3 else ""
|
|
return pay_line(num(salary_range.get("min")), num(salary_range.get("max")),
|
|
salary_range.get("currency"), period)
|
|
|
|
|
|
def _places(categories: dict[str, Any]) -> list[Place]:
|
|
"""`categories.allLocations` (every place of the role, the first being
|
|
`location`), or `location` alone when the list is missing."""
|
|
names = [categories.get("location"), *(categories.get("allLocations") or [])]
|
|
out: list[Place] = []
|
|
for name in names:
|
|
text = str(name or "").strip()
|
|
add_place(out, place(text))
|
|
return out
|
|
|
|
|
|
def parse(body: bytes, slug: str) -> list[Row]:
|
|
data = json.loads(body)
|
|
if not isinstance(data, list):
|
|
return []
|
|
rows = []
|
|
for j in data:
|
|
title = (j.get("text") or "").strip()
|
|
url = (j.get("hostedUrl") or "").strip()
|
|
if not title or not is_web_url(url):
|
|
continue
|
|
categories = j.get("categories") or {}
|
|
description = j.get("description") or j.get("descriptionPlain") or ""
|
|
salary_range = j.get("salaryRange") or {}
|
|
salary_min, salary_max, currency = yearly_amount(
|
|
salary_range.get("min"), salary_range.get("max"), salary_range.get("currency"),
|
|
salary_range.get("interval"), {"per-year-salary": 1, "per-month-salary": 12})
|
|
places = _places(categories)
|
|
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("createdAt")),
|
|
"department": (categories.get("department") or categories.get("team") or "").strip(),
|
|
"description": html_text(description),
|
|
"remote": (j.get("workplaceType") or "").strip() or None,
|
|
"salary_text": _salary_text(salary_range),
|
|
"salary_min": salary_min,
|
|
"salary_max": salary_max,
|
|
"currency": currency,
|
|
}
|
|
# `country` is one code, for a role at one place; over several it would
|
|
# gate the others by the first's country.
|
|
country = str(j.get("country") or "").strip()
|
|
if len(places) == 1 and country:
|
|
row["country"] = country
|
|
if employment := str(categories.get("commitment") or "").strip():
|
|
row["employment"] = employment
|
|
rows.append(row)
|
|
return rows
|