iCIMS Jobs API.

import requests
import xml.etree.ElementTree as ET

company = "careers-bcore"
sitemap_url = f"https://{company}.icims.com/sitemap.xml"

response = requests.get(sitemap_url, timeout=30)
response.raise_for_status()

root = ET.fromstring(response.content)
namespaces = {'ns': 'http://www.sitemaps.org/schemas/sitemap/0.9'}

job_urls = []
for url in root.findall('ns:url', namespaces):
    loc = url.find('ns:loc', namespaces)
    lastmod = url.find('ns:lastmod', namespaces)
    if loc is not None and '/jobs/' in loc.text:
        job_urls.append({
            'url': loc.text,
            'lastmod': lastmod.text if lastmod is not None else None
        })

print(f"Found {len(job_urls)} job URLs in sitemap")

import requests
from bs4 import BeautifulSoup
import re

company = "careers-bcore"
listings_url = f"https://{company}.icims.com/jobs/search?in_iframe=1"

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
    'Accept': 'text/html',
}

response = requests.get(listings_url, headers=headers, timeout=30)
soup = BeautifulSoup(response.content, 'html.parser')

jobs = []
for link in soup.select('a.iCIMS_Anchor[href*="/jobs/"]'):
    href = link.get('href', '')
    title = link.get('title') or link.get_text(strip=True)

    # Extract job ID from URL pattern /jobs/{id}/
    job_id_match = re.search(r'/jobs/(\d+)/', href)
    job_id = job_id_match.group(1) if job_id_match else None

    # Skip login / apply / referral links
    if job_id and title and not any(x in href.lower() for x in ('/login', 'mode=apply', '/referral')):
        jobs.append({
            'id': job_id,
            'title': title,
            'url': href
        })

print(f"Found {len(jobs)} jobs on listing page")

import requests
import json
from bs4 import BeautifulSoup

job_url = "https://careers-bcore.icims.com/jobs/2931/applications-developer/job"
detail_url = f"{job_url}?in_iframe=1"

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
}

response = requests.get(detail_url, headers=headers, timeout=30)
soup = BeautifulSoup(response.content, 'html.parser')

job = {}

# Preferred path: parse the embedded JobPosting JSON-LD
for script in soup.find_all('script', type='application/ld+json'):
    try:
        data = json.loads(script.string or '')
    except (json.JSONDecodeError, TypeError):
        continue
    if isinstance(data, dict) and data.get('@type') == 'JobPosting':
        job['title'] = data.get('title')
        job['description'] = data.get('description')
        job['employment_type'] = data.get('employmentType')
        job['posted_at'] = data.get('datePosted')
        job['closes_at'] = data.get('validThrough')
        job['apply_url'] = data.get('url')
        job['company'] = (data.get('hiringOrganization') or {}).get('name')
        salary_value = (data.get('baseSalary') or {}).get('value') or {}
        job['salary_min'] = salary_value.get('minValue')
        job['salary_max'] = salary_value.get('maxValue')
        break

# Fallback: parse server-rendered HTML when JSON-LD is absent or blank
if not job.get('title'):
    heading = soup.select_one('h1.iCIMS_Header') or soup.select_one('h1')
    job['title'] = heading.get_text(strip=True) if heading else None

if not job.get('description'):
    sections = [s.get_text('\n', strip=True)
                for s in soup.select('.iCIMS_InfoMsg_Job .iCIMS_Expandable_Text')]
    job['description'] = '\n'.join(filter(None, sections)) or None

if not job.get('apply_url'):
    apply_link = (soup.select_one('a[href*="mode=apply"]')
                  or soup.select_one('a.iCIMS_ApplyOnlineButton'))
    job['apply_url'] = apply_link.get('href') if apply_link else None

print(job)

import requests
from bs4 import BeautifulSoup
import re
import time

company = "careers-bcore"
all_jobs = []
seen = set()
page = 0

while True:
    url = f"https://{company}.icims.com/jobs/search?pr={page}&in_iframe=1"

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
    }

    response = requests.get(url, headers=headers, timeout=30)
    soup = BeautifulSoup(response.content, 'html.parser')

    job_links = soup.select('a.iCIMS_Anchor[href*="/jobs/"]')

    new_count = 0
    for link in job_links:
        href = link.get('href', '')
        title = link.get('title') or link.get_text(strip=True)
        job_id_match = re.search(r'/jobs/(\d+)/', href)

        if job_id_match and job_id_match.group(1) not in seen:
            seen.add(job_id_match.group(1))
            new_count += 1
            all_jobs.append({
                'id': job_id_match.group(1),
                'title': title,
                'url': href
            })

    # Stop when a page adds no new records (defensive termination)
    if new_count == 0:
        break

    print(f"Page {page}: +{new_count} jobs (total: {len(all_jobs)})")
    page += 1

    # Be respectful - add delay between requests
    time.sleep(1)

    # Safety limit
    if page > 100:
        break

print(f"Total jobs found: {len(all_jobs)}")

import requests

company = "careers-bcore"
robots_url = f"https://{company}.icims.com/robots.txt"

response = requests.get(robots_url, timeout=30)
robots_content = response.text

# Parse sitemap URL from robots.txt
sitemap_url = None
for line in robots_content.split('\n'):
    if line.lower().startswith('sitemap:'):
        sitemap_url = line.split(':', 1)[1].strip()
        print(f"Sitemap found: {sitemap_url}")
        break

# Note disallowed paths (e.g. /jobs/*login, /jobs/*referral, /jobs/*candidate)
disallowed = []
for line in robots_content.split('\n'):
    if line.lower().startswith('disallow:'):
        path = line.split(':', 1)[1].strip()
        if path:
            disallowed.append(path)

print(f"Disallowed paths: {disallowed}")