import sqlite3 import json import os from datetime import datetime, timedelta # ==================== CONFIGURATION ==================== CONFIG_PATH = "config.json" DB_PATH = "database/jobs.db" DASHBOARD_DIR = "outputs/dashboard" # Charger la configuration with open(CONFIG_PATH, "r", encoding="utf-8") as f: config = json.load(f) # Créer le dossier du dashboard os.makedirs(DASHBOARD_DIR, exist_ok=True) # ==================== RÉCUPÉRATION DES DONNÉES ==================== def get_jobs_from_db(days=30): """Récupérer les offres des derniers jours.""" conn = sqlite3.connect(DB_PATH) cursor = conn.cursor() start_date = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%d %H:%M:%S") cursor.execute(""" SELECT title, company, location, salary, url, source, date, first_seen FROM jobs WHERE first_seen >= ? ORDER BY first_seen DESC """, (start_date,)) jobs = [] for row in cursor.fetchall(): jobs.append({ "title": row[0], "company": row[1], "location": row[2], "salary": row[3], "url": row[4], "source": row[5], "date": row[6], "first_seen": row[7] }) conn.close() return jobs def get_stats(jobs): """Calculer les statistiques.""" total_jobs = len(jobs) sources = {} for job in jobs: sources[job["source"]] = sources.get(job["source"], 0) + 1 locations = {} for job in jobs: locations[job["location"]] = locations.get(job["location"], 0) + 1 new_jobs = [job for job in jobs if datetime.strptime(job["first_seen"], "%Y-%m-%d %H:%M:%S") > (datetime.now() - timedelta(hours=24))] return { "total": total_jobs, "new_today": len(new_jobs), "sources": sources, "locations": dict(sorted(locations.items(), key=lambda x: x[1], reverse=True)[:10]) } # ==================== GÉNÉRATION HTML ==================== def generate_html(jobs, stats): """Générer le fichier index.html.""" dashboard_config = config["dashboard_settings"] html = f""" {dashboard_config['title']} - {dashboard_config['subtitle']}

{dashboard_config['title']}

{dashboard_config['subtitle']}

{datetime.now().strftime("%d/%m/%Y à %H:%M")}

{stats['total']} Offres totales

{stats['new_today']} Nouvelles aujourd'hui

{len(stats['sources'])} Sources actives

Filtres

Dernières offres

{"".join([ f'

' + f'

{job["title"]}

' + f'{job["source"]}

' + f'

{job["company"]}

' + f'

{job["location"]}

' + f'

{job["salary"] if job["salary"] else "Non spécifié"}

' + f'

{datetime.strptime(job["first_seen"], "%Y-%m-%d %H:%M:%S").strftime("%d/%m/%Y")}

' + f'

' + f'' + f' Voir l\'offre' + f'

' for job in jobs ])}

Statistiques

Répartition par source

Répartition par localisation

""" with open(f"{DASHBOARD_DIR}/index.html", "w", encoding="utf-8") as f: f.write(html) print("✅ index.html généré") # ==================== GÉNÉRATION CSS ==================== def generate_css(): """Générer le fichier style.css.""" css = """ :root { --primary: #3498db; --secondary: #2980b9; --success: #2ecc71; --warning: #f39c12; --danger: #e74c3c; --dark: #2c3e50; --light: #ecf0f1; --bg: #f8f9fa; --text: #333; --card-bg: #ffffff; --border-radius: 8px; --shadow: 0 4px 6px rgba(0, 0, 0, 0.1); --transition: all 0.3s ease; } [data-theme="dark"] { --bg: #1a1a1a; --text: #e0e0e0; --card-bg: #2c3e50; --shadow: 0 4px 6px rgba(0, 0, 0, 0.3); } * { margin: 0; padding: 0; box-sizing: border-box; } body { font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; background: var(--bg); color: var(--text); line-height: 1.6; min-height: 100vh; } .container { max-width: 1200px; margin: 0 auto; padding: 20px; } header { display: flex; justify-content: space-between; align-items: center; margin-bottom: 30px; padding: 20px 0; border-bottom: 1px solid var(--primary); flex-wrap: wrap; gap: 15px; } .header-content h1 { color: var(--primary); font-size: 1.8rem; margin-bottom: 5px; } .header-content .subtitle { color: var(--secondary); font-size: 1rem; } .header-actions { display: flex; align-items: center; gap: 15px; } .btn-theme { background: var(--card-bg); border: 1px solid var(--primary); color: var(--primary); padding: 8px 12px; border-radius: var(--border-radius); cursor: pointer; transition: var(--transition); } .btn-theme:hover { background: var(--primary); color: white; } .last-update { color: var(--text); font-size: 0.9rem; opacity: 0.8; display: flex; align-items: center; gap: 5px; } .stats { display: flex; justify-content: space-around; flex-wrap: wrap; gap: 20px; margin-bottom: 40px; } .stat-card { background: var(--card-bg); border-radius: var(--border-radius); padding: 20px; min-width: 200px; flex: 1; box-shadow: var(--shadow); display: flex; align-items: center; gap: 15px; transition: var(--transition); } .stat-card:hover { transform: translateY(-5px); box-shadow: 0 6px 12px rgba(0, 0, 0, 0.15); } .stat-icon { font-size: 2rem; width: 50px; height: 50px; border-radius: 50%; display: flex; align-items: center; justify-content: center; } .stat-icon.total { background: rgba(52, 152, 219, 0.2); color: var(--primary); } .stat-icon.new { background: rgba(46, 204, 113, 0.2); color: var(--success); } .stat-icon.sources { background: rgba(243, 156, 18, 0.2); color: var(--warning); } .stat-info { text-align: center; } .stat-value { display: block; font-size: 1.8rem; font-weight: bold; color: var(--primary); } .stat-label { display: block; font-size: 0.85rem; opacity: 0.8; margin-top: 5px; } .filters { background: var(--card-bg); border-radius: var(--border-radius); padding: 20px; margin-bottom: 30px; box-shadow: var(--shadow); } .filters h2 { color: var(--primary); margin-bottom: 15px; font-size: 1.3rem; display: flex; align-items: center; gap: 10px; } .filter-group { display: flex; flex-wrap: wrap; gap: 15px; } .filter-item { display: flex; flex-direction: column; gap: 5px; flex: 1; min-width: 150px; } .filter-item label { font-weight: 600; font-size: 0.9rem; display: flex; align-items: center; gap: 5px; } .filter-item select { padding: 8px 12px; border: 1px solid var(--primary); border-radius: var(--border-radius); background: var(--card-bg); color: var(--text); font-size: 0.95rem; } .filter-item select:focus { outline: none; border-color: var(--secondary); } .jobs-section { margin-bottom: 40px; } .jobs-section h2 { color: var(--primary); margin-bottom: 20px; font-size: 1.5rem; display: flex; align-items: center; gap: 10px; } .jobs-container { display: grid; grid-template-columns: repeat(auto-fill, minmax(350px, 1fr)); gap: 20px; } .job-card { background: var(--card-bg); border-radius: var(--border-radius); padding: 20px; box-shadow: var(--shadow); transition: var(--transition); border-left: 4px solid var(--primary); animation: fadeIn 0.5s ease forwards; } .job-card:hover { transform: translateY(-3px); box-shadow: 0 8px 16px rgba(0, 0, 0, 0.15); } .job-header { margin-bottom: 10px; } .job-title-source { display: flex; justify-content: space-between; align-items: flex-start; } .job-title { color: var(--primary); font-size: 1.1rem; margin-bottom: 5px; flex: 1; line-height: 1.3; } .job-source { background: var(--primary); color: white; padding: 4px 8px; border-radius: 4px; font-size: 0.7rem; font-weight: 600; white-space: nowrap; } .job-company { color: var(--text); font-weight: 600; margin-bottom: 15px; font-size: 0.95rem; display: flex; align-items: center; gap: 8px; } .job-details { display: flex; flex-direction: column; gap: 8px; margin-bottom: 15px; } .job-detail { display: flex; align-items: center; font-size: 0.85rem; color: var(--text); opacity: 0.9; } .job-detail i { margin-right: 8px; color: var(--secondary); width: 16px; } .job-actions { display: flex; justify-content: flex-end; } .btn-view { background: var(--primary); color: white; padding: 8px 16px; border-radius: var(--border-radius); text-decoration: none; font-weight: 600; transition: var(--transition); display: inline-flex; align-items: center; gap: 5px; font-size: 0.9rem; } .btn-view:hover { background: var(--secondary); transform: translateY(-2px); } .charts-section { margin-bottom: 40px; } .charts-section h2 { color: var(--primary); margin-bottom: 20px; font-size: 1.5rem; display: flex; align-items: center; gap: 10px; } .charts-container { display: grid; grid-template-columns: repeat(auto-fit, minmax(400px, 1fr)); gap: 20px; } .chart-card { background: var(--card-bg); border-radius: var(--border-radius); padding: 20px; box-shadow: var(--shadow); } .chart-card h3 { color: var(--primary); margin-bottom: 15px; font-size: 1.1rem; display: flex; align-items: center; gap: 8px; } footer { text-align: center; padding: 20px; margin-top: 30px; border-top: 1px solid var(--primary); color: var(--text); opacity: 0.7; } footer a { color: var(--primary); text-decoration: none; } footer a:hover { text-decoration: underline; } @keyframes fadeIn { from { opacity: 0; transform: translateY(20px); } to { opacity: 1; transform: translateY(0); } } .no-jobs { text-align: center; padding: 40px; color: var(--text); opacity: 0.7; grid-column: 1 / -1; } @media (max-width: 768px) { .container { padding: 10px; } header { flex-direction: column; text-align: center; } .header-actions { flex-direction: column; } .stats { flex-direction: column; } .stat-card { min-width: 100%; } .jobs-container { grid-template-columns: 1fr; } .charts-container { grid-template-columns: 1fr; } .filter-group { flex-direction: column; } .filter-item { width: 100%; } } ::-webkit-scrollbar { width: 10px; } ::-webkit-scrollbar-track { background: var(--light); } ::-webkit-scrollbar-thumb { background: var(--primary); border-radius: 5px; } """ with open(f"{DASHBOARD_DIR}/style.css", "w", encoding="utf-8") as f: f.write(css) print("✅ style.css généré") def generate_javascript(): """Générer le fichier script.js.""" js = """ const allJobs = jobsData; const stats = statsData; function filterJobs() { const sourceFilter = document.getElementById('source-filter').value; const locationFilter = document.getElementById('location-filter').value; const sortFilter = document.getElementById('sort-filter').value; let filteredJobs = [...allJobs]; if (sourceFilter !== 'all') filteredJobs = filteredJobs.filter(job => job.source === sourceFilter); if (locationFilter !== 'all') filteredJobs = filteredJobs.filter(job => job.location === locationFilter); if (sortFilter === 'date-desc') filteredJobs.sort((a, b) => new Date(b.first_seen) - new Date(a.first_seen)); else if (sortFilter === 'date-asc') filteredJobs.sort((a, b) => new Date(a.first_seen) - new Date(b.first_seen)); else if (sortFilter === 'title-asc') filteredJobs.sort((a, b) => a.title.localeCompare(b.title)); else if (sortFilter === 'title-desc') filteredJobs.sort((a, b) => b.title.localeCompare(a.title)); displayJobs(filteredJobs); } function displayJobs(jobs) { const container = document.getElementById('jobs-container'); if (jobs.length === 0) { container.innerHTML = '

Aucune offre ne correspond à vos filtres.

'; return; } container.innerHTML = jobs.map((job, index) => `

${job.title}

${job.source}

${job.company}

${job.location}

${job.salary || 'Non spécifié'}

${new Date(job.first_seen).toLocaleDateString('fr-FR')}

Voir l'offre

`).join(''); } function initCharts() { const chartColors = ['#3498db', '#2ecc71', '#f39c12', '#e74c3c', '#9b59b6', '#1abc9c', '#16a085', '#27ae60']; const sourcesCtx = document.getElementById('sourcesChart'); if (sourcesCtx) { const sources = Object.entries(stats.sources); new Chart(sourcesCtx, { type: 'doughnut', data: { labels: sources.map(([k, v]) => k), datasets: [{ data: sources.map(([k, v]) => v), backgroundColor: chartColors.slice(0, sources.length), borderWidth: 1 }] }, options: { responsive: true, plugins: { legend: { position: 'bottom' } } } }); } const locationsCtx = document.getElementById('locationsChart'); if (locationsCtx) { const locations = Object.entries(stats.locations); new Chart(locationsCtx, { type: 'bar', data: { labels: locations.map(([k, v]) => k), datasets: [{ label: 'Nombre d\'offres', data: locations.map(([k, v]) => v), backgroundColor: chartColors.slice(0, locations.length) }] }, options: { responsive: true, plugins: { legend: { display: false } }, scales: { y: { beginAtZero: true } } } }); } } function toggleTheme() { const html = document.documentElement; const currentTheme = html.getAttribute('data-theme'); const newTheme = currentTheme === 'dark' ? 'light' : 'dark'; html.setAttribute('data-theme', newTheme); localStorage.setItem('theme', newTheme); document.getElementById('theme-toggle').innerHTML = newTheme === 'dark' ? '' : ''; } if (localStorage.getItem('theme') === 'dark') { document.documentElement.setAttribute('data-theme', 'dark'); document.getElementById('theme-toggle').innerHTML = ''; } if (document.getElementById('source-filter')) document.getElementById('source-filter').addEventListener('change', filterJobs); if (document.getElementById('location-filter')) document.getElementById('location-filter').addEventListener('change', filterJobs); if (document.getElementById('sort-filter')) document.getElementById('sort-filter').addEventListener('change', filterJobs); if (document.getElementById('theme-toggle')) document.getElementById('theme-toggle').addEventListener('click', toggleTheme); window.addEventListener('DOMContentLoaded', () => { filterJobs(); initCharts(); }); """ with open(f"{DASHBOARD_DIR}/script.js", "w", encoding="utf-8") as f: f.write(js) print("✅ script.js généré") # ==================== FONCTION PRINCIPALE ==================== def main(): print("📊 Génération du dashboard...") jobs = get_jobs_from_db(days=30) stats = get_stats(jobs) generate_html(jobs, stats) generate_css() generate_javascript() print(f"✅ Dashboard généré dans {DASHBOARD_DIR}/") print(f" - {len(jobs)} offres affichées") print(f" - {stats['new_today']} nouvelles aujourd'hui") if __name__ == "__main__": main() """ --- ## 📤 **Fichier 4 : `upload_to_ftp.py`** > **Upload le dashboard vers ton serveur FTP automatiquement.** ```python import os import json from ftplib import FTP, FTP_TLS import ssl # ==================== CONFIGURATION ==================== CONFIG_PATH = "config.json" DASHBOARD_DIR = "outputs/dashboard" # Charger la configuration with open(CONFIG_PATH, "r", encoding="utf-8") as f: config = json.load(f) ftp_config = config["ftp_settings"] # ==================== UPLOAD FTP ==================== def upload_to_ftp(): """Uploader le dossier dashboard vers le serveur FTP.""" if not ftp_config.get("enabled", False): print("⚠️ Upload FTP désactivé dans la configuration") return print("📤 Début de l'upload FTP...") try: # Créer une connexion FTP if ftp_config.get("port") == 21: ftp = FTP() else: ftp = FTP_TLS(context=ssl._create_default_https_context()) # Connexion au serveur ftp.connect( host=ftp_config["host"], port=ftp_config.get("port", 21), timeout=10 ) print(f"✅ Connecté à {ftp_config['host']}:{ftp_config.get('port', 21)}") # Authentification ftp.login( user=ftp_config["username"], passwd=ftp_config["password"] ) print("✅ Authentification réussie") # Changer de répertoire distant remote_path = ftp_config["remote_path"] try: ftp.cwd(remote_path) print(f"✅ Répertoire distant: {remote_path}") except Exception as e: print(f"⚠️ Répertoire {remote_path} introuvable, création...") # Créer les répertoires for dir_name in remote_path.split('/')[1:]: if dir_name: try: ftp.cwd(dir_name) except: ftp.mkd(dir_name) ftp.cwd(dir_name) # Lister les fichiers locaux à uploader local_dir = ftp_config.get("local_dashboard_dir", DASHBOARD_DIR) for root, dirs, files in os.walk(local_dir): for file in files: local_path = os.path.join(root, file) relative_path = os.path.relpath(local_path, local_dir) # Naviguer vers le bon répertoire distant remote_file_path = os.path.join(remote_path, relative_path) remote_dir = os.path.dirname(remote_file_path) # Créer les sous-répertoires si nécessaire if remote_dir != remote_path: try: ftp.cwd(remote_dir) except: # Créer le chemin complet current = remote_path for part in remote_dir.replace(remote_path, '').split('/'): if part: try: ftp.cwd(os.path.join(current, part)) except: ftp.mkd(os.path.join(current, part)) ftp.cwd(os.path.join(current, part)) current = os.path.join(current, part) # Uploader le fichier with open(local_path, 'rb') as f: ftp.storbinary(f'STOR {os.path.basename(remote_file_path)}', f) print(f"✅ Upload: {relative_path}") # Fermer la connexion ftp.quit() print("✅ Upload FTP terminé avec succès !") domain = ftp_config["host"].replace("ftp.", "").replace("http://", "").replace("https://", "") print(f"🌐 Dashboard accessible à: https://{domain}{remote_path}") except Exception as e: print(f"❌ Erreur FTP: {e}") if 'ftp' in locals(): try: ftp.quit() except: pass if __name__ == "__main__": upload_to_ftp() """ --- ## 🐍 **Fichier 5 : `job_scanner.py` (version finale)** > **Script principal mis à jour pour générer le dashboard et l'uploader.** ```python import json import sqlite3 import smtplib import os import subprocess import requests from email.mime.text import MIMEText from email.mime.multipart import MIMEMultipart from bs4 import BeautifulSoup import pandas as pd from datetime import datetime, timedelta import re import hashlib # ==================== CONFIGURATION ==================== CONFIG_PATH = "config.json" DB_PATH = "database/jobs.db" OUTPUT_DIR = "outputs" DASHBOARD_DIR = "outputs/dashboard" # Charger la configuration with open(CONFIG_PATH, "r", encoding="utf-8") as f: config = json.load(f) # Créer les dossiers os.makedirs("database", exist_ok=True) os.makedirs(OUTPUT_DIR, exist_ok=True) os.makedirs(DASHBOARD_DIR, exist_ok=True) # ==================== BASE DE DONNÉES ==================== def init_db(): conn = sqlite3.connect(DB_PATH) cursor = conn.cursor() cursor.execute(""" CREATE TABLE IF NOT EXISTS jobs ( id TEXT PRIMARY KEY, title TEXT, company TEXT, location TEXT, salary TEXT, url TEXT UNIQUE, source TEXT, date TEXT, description TEXT, first_seen TEXT ) """) conn.commit() return conn def generate_job_id(title, company, url): return hashlib.md5(f"{title}{company}{url}".encode("utf-8")).hexdigest() def is_near_location(location, cities): if not location: return False location_lower = location.lower() for city in cities: if city.lower() in location_lower: return True nearby_keywords = ["antibes", "sophia antipolis", "valbonne", "biot", "mougins", "cannes", "nice", "cagnes", "vallauris", "le cannet"] for keyword in nearby_keywords: if keyword in location_lower: return True return False def contains_job_title(text, titles): if not text: return False text_lower = text.lower() for title in titles: normalized = title.lower() for a, r in [('é','e'),('è','e'),('ê','e'),('à','a'),('â','a'),('î','i'),('ï','i'),('ô','o'),('ö','o'),('ù','u'),('û','u'),('ç','c')]: normalized = normalized.replace(a, r) if normalized in text_lower: return True return False def contains_excluded_keywords(text, exclude_keywords): if not text or not exclude_keywords: return False text_lower = text.lower() for keyword in exclude_keywords: if keyword.lower() in text_lower: return True return False def get_current_date(): return datetime.now().strftime("%Y-%m-%d") def get_current_datetime(): return datetime.now().strftime("%Y-%m-%d %H:%M:%S") # ==================== SCAN DES PLATEFORMES ==================== def scan_platform(platform_name, base_url, search_params, criteria): """Fonction générique de scan pour une plateforme.""" jobs = [] try: headers = {"User-Agent": criteria["user_agent"]} response = requests.get(search_params["url"], headers=headers, timeout=10) if response.status_code != 200: return jobs soup = BeautifulSoup(response.text, "html.parser") job_cards = soup.find_all("div", class_=re.compile(search_params["card_class"])) for card in job_cards[:criteria["max_results_per_platform"]]: try: title_elem = card.find(search_params["title_tag"], class_=re.compile(search_params["title_class"])) title = title_elem.get_text(strip=True) if title_elem else "" company_elem = card.find(search_params["company_tag"], class_=re.compile(search_params["company_class"])) company = company_elem.get_text(strip=True) if company_elem else "" location_elem = card.find(search_params["location_tag"], class_=re.compile(search_params["location_class"])) location = location_elem.get_text(strip=True) if location_elem else "" salary_elem = card.find(search_params["salary_tag"], class_=re.compile(search_params["salary_class"])) salary = salary_elem.get_text(strip=True) if salary_elem else "" link_elem = card.find("a", href=True) url = base_url + link_elem["href"] if link_elem else "" date_elem = card.find(search_params["date_tag"], class_=re.compile(search_params["date_class"])) date = date_elem.get_text(strip=True) if date_elem else "" if not contains_job_title(title, criteria["job_titles_fr"] + criteria["job_titles_en"]): continue if not is_near_location(location, criteria["cities_nearby"]): continue if contains_excluded_keywords(title + " " + company, criteria["exclude_keywords"]): continue jobs.append({ "title": title, "company": company, "location": location, "salary": salary, "url": url, "source": platform_name, "date": date, "description": "" }) except Exception as e: print(f"⚠️ Erreur parsing {platform_name}: {e}") continue except Exception as e: print(f"⚠️ Erreur scan {platform_name}: {e}") return jobs def scan_indeed(): criteria = config["search_criteria"] base_url = "https://fr.indeed.com" jobs = [] for title in criteria["job_titles_fr"] + criteria["job_titles_en"]: search_query = f"{title} {criteria['location']}".replace(" ", "+") url = f"{base_url}/jobs?q={search_query}&l=Antibes%2C+Alpes-Maritimes" jobs.extend(scan_platform("Indeed", base_url, { "url": url, "card_class": r"job_seen_beacon", "title_tag": "h2", "title_class": r"jobTitle", "company_tag": "span", "company_class": r"companyName", "location_tag": "div", "location_class": r"companyLocation", "salary_tag": "div", "salary_class": r"salary-snippet", "date_tag": "span", "date_class": r"date" }, config["scan_settings"])) return jobs def scan_ape(): criteria = config["search_criteria"] base_url = "https://www.apec.fr" jobs = [] for title in criteria["job_titles_fr"]: search_query = f"{title} {criteria['location']}".replace(" ", "+") url = f"{base_url}/candidat/recherche-emploi.html?motscles={search_query}&lieux=Antibes%2C+Sophia+Antipolis" jobs.extend(scan_platform("APEC", base_url, { "url": url, "card_class": r"offre", "title_tag": "h2", "title_class": r".*", "company_tag": "span", "company_class": r"entreprise", "location_tag": "span", "location_class": r"localite", "salary_tag": "span", "salary_class": r"salaire", "date_tag": "span", "date_class": r"date" }, config["scan_settings"])) return jobs def scan_linkedin(): criteria = config["search_criteria"] jobs = [] try: from googlesearch import search except ImportError: print("⚠️ Installation de googlesearch-python...") os.system("pip install googlesearch-python") from googlesearch import search for title in criteria["job_titles_fr"] + criteria["job_titles_en"]: try: query = f"site:linkedin.com/jobs {title} {criteria['location']}" for result in search(query, num_results=10, stop=10, pause=2): if "linkedin.com/jobs/view/" in result: jobs.append({ "title": title, "company": "", "location": criteria["location"], "salary": "", "url": result, "source": "LinkedIn", "date": get_current_date(), "description": "" }) except Exception as e: print(f"⚠️ Erreur scan LinkedIn: {e}") # Récupérer les détails detailed_jobs = [] for job in jobs: try: headers = {"User-Agent": criteria["user_agent"]} response = requests.get(job["url"], headers=headers, timeout=10) if response.status_code != 200: continue soup = BeautifulSoup(response.text, "html.parser") title_elem = soup.find("h1", class_=re.compile(r"top-card-layout__title")) title = title_elem.get_text(strip=True) if title_elem else job["title"] company_elem = soup.find("a", class_=re.compile(r"topcard__org-name-link")) company = company_elem.get_text(strip=True) if company_elem else "" location_elem = soup.find("span", class_=re.compile(r"topcard__flavor-row-item")) location = location_elem.get_text(strip=True) if location_elem else "" if not contains_job_title(title, criteria["job_titles_fr"] + criteria["job_titles_en"]): continue if not is_near_location(location, criteria["cities_nearby"]): continue if contains_excluded_keywords(title + " " + company, criteria["exclude_keywords"]): continue detailed_jobs.append({ "title": title, "company": company, "location": location, "salary": "", "url": job["url"], "source": "LinkedIn", "date": get_current_date(), "description": "" }) except Exception as e: print(f"⚠️ Erreur détails LinkedIn: {e}") return detailed_jobs def scan_welcome_to_the_jungle(): criteria = config["search_criteria"] base_url = "https://www.welcometothejungle.com" jobs = [] for title in criteria["job_titles_fr"] + criteria["job_titles_en"]: search_query = title.replace(" ", "-") url = f"{base_url}/fr/jobs?query={search_query}&location=Antibes%2C+Sophia+Antipolis" jobs.extend(scan_platform("Welcome to the Jungle", base_url, { "url": url, "card_class": r"job-card", "title_tag": "h3", "title_class": r".*", "company_tag": "span", "company_class": r"company-name", "location_tag": "span", "location_class": r"location", "salary_tag": "span", "salary_class": r"salary", "date_tag": "div", "date_class": r".*" }, config["scan_settings"])) return jobs def scan_monster(): criteria = config["search_criteria"] base_url = "https://www.monster.fr" jobs = [] for title in criteria["job_titles_fr"] + criteria["job_titles_en"]: search_query = f"{title} {criteria['location']}".replace(" ", "+") url = f"{base_url}/emploi/recherche/?q={search_query}&where=Antibes" jobs.extend(scan_platform("Monster", base_url, { "url": url, "card_class": r"job-card", "title_tag": "h2", "title_class": r".*", "company_tag": "span", "company_class": r"company-name", "location_tag": "span", "location_class": r"location", "salary_tag": "span", "salary_class": r"salary", "date_tag": "span", "date_class": r"date" }, config["scan_settings"])) return jobs def scan_pole_emploi(): criteria = config["search_criteria"] base_url = "https://candidat.pole-emploi.fr" jobs = [] for title in criteria["job_titles_fr"]: search_query = title.replace(" ", "+") url = f"{base_url}/offres/recherche?motsCle={search_query}&lieux=Antibes%2C+Sophia+Antipolis" jobs.extend(scan_platform("Pôle Emploi", base_url, { "url": url, "card_class": r"offre", "title_tag": "h2", "title_class": r".*", "company_tag": "span", "company_class": r"entreprise", "location_tag": "span", "location_class": r"lieu", "salary_tag": "span", "salary_class": r"salaire", "date_tag": "span", "date_class": r"date" }, config["scan_settings"])) return jobs def scan_all_platforms(): all_jobs = [] criteria = config["search_criteria"] platforms = criteria["platforms"] print(f"[{get_current_datetime()}] Début du scan...") if platforms.get("indeed", True): print(f"[{get_current_datetime()}] Scan Indeed...") all_jobs.extend(scan_indeed()) print(f"[{get_current_datetime()}] Indeed: {len([j for j in all_jobs if j['source'] == 'Indeed'])} offres") if platforms.get("ape", True): print(f"[{get_current_datetime()}] Scan APEC...") all_jobs.extend(scan_ape()) print(f"[{get_current_datetime()}] APEC: {len([j for j in all_jobs if j['source'] == 'APEC'])} offres") if platforms.get("linkedin", True): print(f"[{get_current_datetime()}] Scan LinkedIn...") all_jobs.extend(scan_linkedin()) print(f"[{get_current_datetime()}] LinkedIn: {len([j for j in all_jobs if j['source'] == 'LinkedIn'])} offres") if platforms.get("welcome_to_the_jungle", True): print(f"[{get_current_datetime()}] Scan Welcome to the Jungle...") all_jobs.extend(scan_welcome_to_the_jungle()) print(f"[{get_current_datetime()}] WTTJ: {len([j for j in all_jobs if j['source'] == 'Welcome to the Jungle'])} offres") if platforms.get("monster", True): print(f"[{get_current_datetime()}] Scan Monster...") all_jobs.extend(scan_monster()) print(f"[{get_current_datetime()}] Monster: {len([j for j in all_jobs if j['source'] == 'Monster'])} offres") if platforms.get("pole_emploi", True): print(f"[{get_current_datetime()}] Scan Pôle Emploi...") all_jobs.extend(scan_pole_emploi()) print(f"[{get_current_datetime()}] Pôle Emploi: {len([j for j in all_jobs if j['source'] == 'Pôle Emploi'])} offres") print(f"[{get_current_datetime()}] Scan terminé. Total: {len(all_jobs)} offres brutes") return all_jobs # ==================== FILTRAGE ET SAUVEGARDE ==================== def filter_and_save_jobs(all_jobs): conn = init_db() cursor = conn.cursor() new_jobs = [] updated_jobs = [] for job in all_jobs: job_id = generate_job_id(job["title"], job["company"], job["url"]) cursor.execute("SELECT id FROM jobs WHERE id = ?", (job_id,)) exists = cursor.fetchone() if not exists: cursor.execute(""" INSERT INTO jobs (id, title, company, location, salary, url, source, date, description, first_seen) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?) """, (job_id, job["title"], job["company"], job["location"], job["salary"], job["url"], job["source"], job["date"], job["description"], get_current_datetime())) new_jobs.append(job) else: cursor.execute("SELECT first_seen FROM jobs WHERE id = ?", (job_id,)) first_seen = cursor.fetchone()[0] first_seen_date = datetime.strptime(first_seen, "%Y-%m-%d %H:%M:%S") if (datetime.now() - first_seen_date).days >= 7: cursor.execute("UPDATE jobs SET first_seen = ? WHERE id = ?", (get_current_datetime(), job_id)) updated_jobs.append(job) conn.commit() conn.close() return new_jobs, updated_jobs def export_to_csv(jobs, filename=None): if not filename: filename = f"{OUTPUT_DIR}/offres_{get_current_date()}.csv" df = pd.DataFrame(jobs) df.to_csv(filename, index=False, encoding="utf-8-sig") return filename # ==================== NOTIFICATIONS EMAIL ==================== def send_email_notification(new_jobs, updated_jobs): email_config = config["email_settings"] user = config["user"] if not new_jobs and not updated_jobs: print(f"[{get_current_datetime()}] Aucune nouvelle offre à notifier") return subject = f"[Job Scanner] {len(new_jobs)} nouvelles offres ({get_current_date()})" if updated_jobs: subject += f" + {len(updated_jobs)} mises à jour" body = f"Bonjour {user['name']},\n\n" body += f"Voici les nouvelles offres pour aujourd'hui, {get_current_date()} :\n\n" if new_jobs: body += f"--- NOUVELLES OFFRES ({len(new_jobs)}) ---\n\n" for i, job in enumerate(new_jobs, 1): body += f"{i}. {job['title']}\n" body += f" Entreprise : {job['company']}\n" body += f" Localisation : {job['location']}\n" body += f" Salaire : {job['salary']}\n" body += f" Source : {job['source']}\n" body += f" Lien : {job['url']}\n\n" if updated_jobs: body += f"--- MISES À JOUR ({len(updated_jobs)}) ---\n\n" for i, job in enumerate(updated_jobs, 1): body += f"{i}. {job['title']}\n" body += f" Lien : {job['url']}\n\n" body += f"Dashboard: https://{config['ftp_settings']['host'].replace('ftp.', '')}{config['ftp_settings']['remote_path']}\n" body += "Bonne recherche !\n" msg = MIMEMultipart() msg["From"] = email_config["from_email"] msg["To"] = email_config["to_email"] msg["Subject"] = subject msg.attach(MIMEText(body, "plain", "utf-8")) try: with smtplib.SMTP(email_config["smtp_server"], email_config["smtp_port"]) as server: server.starttls() server.login(email_config["smtp_username"], email_config["smtp_password"]) server.send_message(msg) print(f"[{get_current_datetime()}] Email envoyé à {email_config['to_email']}") except Exception as e: print(f"[{get_current_datetime()}] Échec email: {e}") # ==================== FONCTION PRINCIPALE ==================== def main(): print("=" * 60) print("JOB SCANNER - IT Operations/Infrastructure") print("=" * 60) all_jobs = scan_all_platforms() new_jobs, updated_jobs = filter_and_save_jobs(all_jobs) print(f"[{get_current_datetime()}] {len(new_jobs)} nouvelles offres, {len(updated_jobs)} mises à jour") if new_jobs or updated_jobs: export_to_csv(new_jobs + updated_jobs) send_email_notification(new_jobs, updated_jobs) # Générer le dashboard print(f"[{get_current_datetime()}] Génération du dashboard...") subprocess.run(["python3", "generate_dashboard.py"]) # Upload vers FTP if config["ftp_settings"].get("enabled", False): print(f"[{get_current_datetime()}] Upload vers FTP...") subprocess.run(["python3", "upload_to_ftp.py"]) print(f"[{get_current_datetime()}] Tâche terminée") if __name__ == "__main__": main() """ --- ## 📌 **Instructions d'installation et d'utilisation** ### 🔧 **Étape 1 : Préparation sur ton serveur** 1. **Crée un dossier** sur ton serveur FTP :ftp.cluster129.hosting.ovh.net