#!/usr/bin/env python3 """ Modified j3.py for joblegi.xyz Features: 1. Automatic daily date updates (via script execution) 2. SEO Slugs (wfh.hstn.me style) 3. Advanced Global Job Schema """ import os import json import re import datetime import argparse from jinja2 import Template from bs4 import BeautifulSoup # Define the main domain MAIN_DOMAIN = "https://joblegi.xyz" def slugify(title): """Creates a URL-friendly slug from the job title.""" slug = title.lower() slug = re.sub(r'[^a-z0-9\s-]', '', slug) slug = re.sub(r'\s+', '-', slug).strip('-') return slug def clean_visible_body(html): """Cleans HTML for the job description display.""" soup = BeautifulSoup(html, "html.parser") for a_tag in soup.find_all('a'): a_tag.unwrap() for span in soup.find_all('span'): span.unwrap() for tag in soup.find_all(True): tag.attrs.pop('class', None) return str(soup) # UPDATED TEMPLATE: Matching wfh.hstn.me style template_html = r""" {{ job_title }} | Remote Job

Remote Jobs USA

REMOTE 📍 {{ location }} 🕒 Posted: {{ date_posted }}

Apply Now

""" def process_job(job_record, force_company=None): job_title = job_record.get("job_title", "Untitled Job") slug = slugify(job_title) # Filename matches slug exactly file_name = f"{slug}.html" job_full_url = f"{MAIN_DOMAIN}/job/{file_name}" raw_body = "".join(job_record.get("body_parts", [])) visible_body = clean_visible_body(raw_body) company_name = force_company if force_company else job_record.get("company_name", "Wfh") # AUTOMATIC DATE LOGIC: Uses current date every time script runs date_today = datetime.date.today().isoformat() expiry_date = (datetime.date.today() + datetime.timedelta(days=30)).isoformat() # Global Countries List for Schema countries = [ "United States", "Japan", "India", "United Kingdom", "Brazil", "Australia", "Indonesia", "Germany", "Netherlands", "Sweden", "Canada", "Mexico", "France", "Spain", "South Korea", "Kenya", "Nigeria", "South Africa", "Singapore", "United Arab Emirates", "Philippines", "Italy", "Switzerland", "Denmark", "Norway", "Ireland", "Poland", "Malaysia", "Thailand", "Vietnam", "Bangladesh", "Saudi Arabia", "Qatar", "Argentina", "Chile", "Colombia" ] job_schema = { "@context": "https://schema.org", "@type": "JobPosting", "title": job_title, "datePosted": date_today, "validThrough": expiry_date, "description": visible_body, "url": job_full_url, "jobLocationType": "TELECOMMUTE", "applicantLocationRequirements": [{"@type": "Country", "name": c} for c in countries], "employmentType": "FULL_TIME", "hiringOrganization": { "@type": "Organization", "name": company_name, "sameAs": MAIN_DOMAIN }, "jobLocation": {"@type": "Place", "address": {"@type": "PostalAddress", "addressCountry": "US"}}, "directApply": True } return { "job_title": job_title, "file_name": file_name, "job_url": job_full_url, "apply_url": job_record.get("apply_url", job_full_url), "job_body": visible_body, "company_name": company_name, "location": "Remote", "date_posted": date_today, "schema_json": json.dumps(job_schema, indent=2) } def main(ndjson_file, output_dir, force_company): if not os.path.exists(output_dir): os.makedirs(output_dir) with open(ndjson_file, "r", encoding="utf-8") as f: for line in f: if not line.strip(): continue try: job_data = process_job(json.loads(line), force_company) template = Template(template_html) html_content = template.render(**job_data) output_path = os.path.join(output_dir, job_data['file_name']) with open(output_path, "w", encoding="utf-8") as out_f: out_f.write(html_content) print(f"Generated: {job_data['file_name']} with date {job_data['date_posted']}") except Exception as e: print(f"Error: {e}") if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("ndjson_file") parser.add_argument("output_dir") parser.add_argument("--force-company", default=None) args = parser.parse_args() main(args.ndjson_file, args.output_dir, args.force_company)