Connexys Recruitment Jobs API.

from urllib.parse import urlparse, parse_qs

SUFFIX = ".my.salesforce-sites.com"
PAGES = {"cxsrec__cxssearch", "cxsrec__cxssearchdetail"}

def parse_connexys(url: str) -> dict | None:
    parsed = urlparse(url)
    host = parsed.netloc.lower()
    if parsed.scheme != "https" or not host.endswith(SUFFIX):
        return None

    path = parsed.path
    slash = path.rfind("/")
    page = path[slash + 1:] if slash >= 0 else path.lstrip("/")
    if page.lower() not in PAGES:
        return None

    site_path = path[:slash] if slash > 0 else ""
    query = {k.lower(): v[0] for k, v in parse_qs(parsed.query).items()}
    media = query.get("mediachannel")
    board = f"https://{host}{site_path}/cxsrec__cxsSearch"
    if media:
        board = f"{board}?mediaChannel={media}"

    return {
        "org": host.split(".")[0],
        "site_path": site_path,
        "media_channel": media,
        "board_url": board,
        "position_id": query.get("id"),
    }

print(parse_connexys("https://dunea.my.salesforce-sites.com/dunearecruitment/apex/"
                     "cxsrec__cxsSearch?mediaChannel=a0o090000016dv9AAA"))

import re
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse, quote

SHOW_POSITION = re.compile(
    "showPosition[(][ ]*'([A-Za-z0-9]{15,18})'[ ]*,[ ]*'([^']*)'", re.IGNORECASE)
ARTIFACTS = re.compile("cxsrec__cxsSearch|@connexys[.]com", re.IGNORECASE)

def parse_rows(html: str, page_url: str) -> list[dict]:
    if not ARTIFACTS.search(html):
        raise RuntimeError("page did not contain Connexys package artifacts")

    parsed = urlparse(page_url)
    directory = parsed.path[: parsed.path.rfind("/") + 1]
    origin = f"{parsed.scheme}://{parsed.netloc}"

    soup = BeautifulSoup(html, "html.parser")
    rows = []
    for row in soup.select("tr.dataRow"):
        anchor = row.select_one("a[href*='showPosition']")
        if not anchor:
            continue
        match = SHOW_POSITION.search(anchor.get("href") or "")
        title = anchor.get_text(strip=True)
        if not match or not title:
            continue

        position_id, media = match.group(1), match.group(2)
        detail = f"{origin}{directory}cxsrec__cxsSearchDetail?id={quote(position_id)}"
        if media:
            detail = f"{detail}&mediaChannel={quote(media)}"

        location = row.select_one(".cxsrec__Location__c")
        rows.append({
            "id": position_id,
            "title": title,
            "media_channel": media or None,
            "location": location.get_text(strip=True) if location else None,
            "url": detail,
        })
    return rows

session = requests.Session()
board = "https://ortec.my.salesforce-sites.com/cxsrec__cxsSearch?mediaChannel=a0o2p00000Zdm21AAB"
resp = session.get(board, timeout=30)
resp.raise_for_status()
rows = parse_rows(resp.text, board)

from urllib.parse import urljoin
import time

NEXT_LABELS = {"volgende", "next"}

def next_page_url(html: str, page_url: str) -> str | None:
    soup = BeautifulSoup(html, "html.parser")
    for anchor in soup.select("a.pageLink[href]"):
        if anchor.get_text(strip=True).lower() in NEXT_LABELS:
            candidate = urljoin(page_url, anchor["href"])
            if parse_connexys(candidate):
                return candidate
    return None

def scrape_board(session, board_url: str, max_pages: int = 20) -> list[dict]:
    url, jobs, seen = board_url, [], set()
    for _ in range(max_pages):
        resp = session.get(url, timeout=30)
        resp.raise_for_status()
        for row in parse_rows(resp.text, url):
            if row["id"] not in seen:
                seen.add(row["id"])
                jobs.append(row)

        url = next_page_url(resp.text, url)
        if not url:
            break
        time.sleep(0.3)
    return jobs

import codecs

ENCODED_VALUE = re.compile(
    "var[ ]+preDecodedValue[ ]*=[ ]*'((?:[^'])*)'[ ]*;", re.IGNORECASE | re.DOTALL)

NARRATIVE_FIELDS = [
    ".cxsrec__Company_information__c",
    ".cxsrec__Job_description__c",
    ".cxsrec__Job_requirements__c",
    ".cxsrec__Compensation_benefits__c",
]

def decode(value: str) -> str:
    try:
        return codecs.decode(value, "unicode_escape")
    except (UnicodeDecodeError, ValueError):
        return value

def fetch_detail(session, listing: dict) -> dict | None:
    resp = session.get(listing["url"], timeout=30)
    if resp.status_code in (404, 410):
        return None
    resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")
    sections = []
    for selector in NARRATIVE_FIELDS:
        element = soup.select_one(selector)
        if element is None:
            continue
        raw = element.decode_contents()
        match = ENCODED_VALUE.search(raw)
        text = decode(match.group(1)) if match else raw
        if len(BeautifulSoup(text, "html.parser").get_text(strip=True)) >= 30:
            sections.append(text.strip())

    heading = soup.select_one("h1.cxsPageTitle")
    apply_anchor = soup.select_one("a[href*='cxsSearchApply']")
    location = soup.select_one(".cxsrec__Location__c p, .cxsrec__Location__c")

    return {
        "id": listing["id"],
        "title": heading.get_text(strip=True) if heading else listing["title"],
        "description_html": "".join(sections),
        "location": location.get_text(strip=True) if location else listing.get("location"),
        "url": listing["url"],
        "apply_url": (urljoin(listing["url"], apply_anchor["href"])
                      if apply_anchor else listing["url"]),
    }