# -*- coding: utf-8 -*- #!/usr/bin/env python3 import os import json import re import datetime import argparse from jinja2 import Template from bs4 import BeautifulSoup # --- CONFIGURATION --- MAIN_DOMAIN = "https://rowjobs.site " def slugify(title): slug = title.lower() slug = re.sub(r'[^a-z0-9\s-]', '', slug) slug = re.sub(r'[\s-]+', '-', slug).strip('-') return slug def professional_cleaner(text): if not text: return "We are looking for a qualified candidate to join our remote team. Apply for full details." # Remove HTML tags soup = BeautifulSoup(text, "html.parser") # Remove any unwanted source links or common scraper footprints for scrap in soup.find_all(['a', 'script', 'style']): scrap.decompose() clean_text = soup.get_text(separator=' ') # Professional string cleaning clean_text = clean_text.replace('"', "'").replace('\n', ' ').replace('\r', '').strip() # Remove common "source" phrases found in scraped data clean_text = re.sub(r'(?i)source\s*:\s*\S+', '', clean_text) clean_text = re.sub(r'(?i)click here to apply', 'apply below', clean_text) # Limit to a clean paragraph format if it's too messy clean_text = ' '.join(clean_text.split()) return clean_text # --- PREMIUM MINIMALIST DESIGN --- template_html = """ {{ job_title }} | Remote Careers

RemoteVerifiedFull-Time

Professional Summary

""" def main(ndjson_file, output_dir): job_dir = os.path.join(output_dir, "job") if not os.path.exists(job_dir): os.makedirs(job_dir) today_dt = datetime.date.today() date_posted_str = today_dt.strftime("%B %d, %Y") iso_date = today_dt.isoformat() valid_through = (today_dt + datetime.timedelta(days=60)).isoformat() # The 4-Way Variation List prefixes = [ "", # Standard Version "Urgent Hiring: ", # Version 2 "Remote Work - ", # Version 3 "New Opening: " # Version 4 ] file_counter = 0 with open(ndjson_file, 'r', encoding='utf-8') as f: for line in f: if not line.strip(): continue try: job = json.loads(line) except: continue base_title = job.get("title", "Job Opportunity") raw_desc = job.get("description", "") cleaned_desc = professional_cleaner(raw_desc) # MULTIPLIER LOOP for prefix in prefixes: file_counter += 1 full_title = f"{prefix}{base_title}".strip() slug = f"{slugify(full_title)}-{file_counter}" context = { "job_title": full_title, "date_posted": date_posted_str, "iso_date": iso_date, "valid_through": valid_through, "job_description": raw_desc, # Raw for the HTML content "job_description_clean": cleaned_desc, # Cleaned for Schema SEO "full_job_url": f"{MAIN_DOMAIN}/job/{slug}", "main_domain": MAIN_DOMAIN, "apply_url": job.get("apply_url", "#") } template = Template(template_html) output_path = os.path.join(job_dir, f"{slug}.html") with open(output_path, "w", encoding="utf-8") as out: out.write(template.render(context)) print(f"DONE! Generated {file_counter} unique pages.") print(f"Total jobs processed: {file_counter // 4}") if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("ndjson_file", help="Input NDJSON file") parser.add_argument("output_dir", help="Main output directory") args = parser.parse_args() main(args.ndjson_file, args.output_dir)