import os
import json
import argparse
import re
from jinja2 import Template
def slugify(text):
"""Converts job titles into clean lowercase url slugs"""
if not text:
return ""
text = text.lower()
text = re.sub(re.compile(r'[^a-z0-9\s-]'), '', text)
text = re.sub(re.compile(r'[\s-]+'), '-', text)
return text.strip('-')
def load_jobs_from_json(json_file):
"""Reads the ndjson file and gets the latest jobs."""
job_list = []
if not os.path.exists(json_file):
print(f"Error: {json_file} not found.")
return job_list
with open(json_file, 'r', encoding='utf-8') as f:
for line in f:
try:
job_list.append(json.loads(line))
except:
continue
return job_list[::-1]
def main(json_file, output_dir):
all_jobs = load_jobs_from_json(json_file)
selected_jobs = all_jobs[:60] # Show latest 60
# 1. Scan your actual server folder to see exactly what files exist
job_folder = os.path.join(output_dir, "job")
existing_html_files = []
if os.path.exists(job_folder):
existing_html_files = [f for f in os.listdir(job_folder) if f.endswith('.html')]
# 2. Match each job listing to its real filename on the server
for job in selected_jobs:
job_title_slug = slugify(job.get('title', ''))
matched_slug = ""
# Look for the file that starts with this title slug
for file_name in existing_html_files:
clean_file_base = file_name.replace('.html', '')
if clean_file_base.startswith(job_title_slug) or job_title_slug in clean_file_base:
matched_slug = clean_file_base
break
# Fallback if a perfect match isn't found in the directory scan
if not matched_slug:
job_id = job.get('id', 'job')
matched_slug = f"{job_title_slug}-{job_id}" if job_title_slug else str(job_id)
job['clean_url'] = matched_slug
template_home = """
JobHoga | Find Your Next Remote JobJobHoga
Advertisement
Find your next cozy remote job.
A curated list of the best work-from-home opportunities in tech, support, and more.