#!/usr/bin/env python3 """ Test de téléchargement d'une vidéo Instagram via l'API GraphQL publique """ import subprocess import json import logging import os import time import re import random from urllib.parse import urlencode # Configuration du logging logging.basicConfig(level=logging.DEBUG) logger = logging.getLogger(__name__) def generate_uuid(): """Génère un UUID pour la simulation de session""" hexdigits = '0123456789abcdef' uuid = ''.join(random.choice(hexdigits) for _ in range(32)) return f"{uuid[:8]}-{uuid[8:12]}-{uuid[12:16]}-{uuid[16:20]}-{uuid[20:]}" def extract_post_id(url): """Extrait l'ID du post Instagram depuis l'URL""" patterns = [ r'instagram\.com/p/([^/]+)', r'instagram\.com/reel/([^/]+)', ] for pattern in patterns: match = re.search(pattern, url) if match: return match.group(1).split('/')[0] return None def get_instagram_session(): """Récupère une session Instagram valide""" # User-Agent moderne et réaliste user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36" # Headers de base headers = { 'User-Agent': user_agent, 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8', 'Accept-Language': 'en-US,en;q=0.9', 'Accept-Encoding': 'gzip, deflate', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache', 'Sec-Ch-Ua': '"Not A(Brand";v="24", "Chromium";v="121"', 'Sec-Ch-Ua-Mobile': '?0', 'Sec-Ch-Ua-Platform': '"Windows"', 'Sec-Fetch-Dest': 'document', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-Site': 'none', 'Sec-Fetch-User': '?1', 'Dnt': '1', 'Upgrade-Insecure-Requests': '1' } # Première requête pour initialiser la session init_cmd = [ 'curl', 'https://www.instagram.com/', '-H', f'User-Agent: {headers["User-Agent"]}', '-H', f'Accept: {headers["Accept"]}', '-H', f'Accept-Language: {headers["Accept-Language"]}', '-H', f'Sec-Ch-Ua: {headers["Sec-Ch-Ua"]}', '-H', f'Sec-Ch-Ua-Mobile: {headers["Sec-Ch-Ua-Mobile"]}', '-H', f'Sec-Ch-Ua-Platform: {headers["Sec-Ch-Ua-Platform"]}', '-H', f'Sec-Fetch-Dest: {headers["Sec-Fetch-Dest"]}', '-H', f'Sec-Fetch-Mode: {headers["Sec-Fetch-Mode"]}', '-H', f'Sec-Fetch-Site: {headers["Sec-Fetch-Site"]}', '-H', f'Sec-Fetch-User: {headers["Sec-Fetch-User"]}', '-H', f'Dnt: {headers["Dnt"]}', '-H', f'Upgrade-Insecure-Requests: {headers["Upgrade-Insecure-Requests"]}', '-c', 'instagram_cookies.txt', '-s' ] logger.debug("Initialisation de la session...") process = subprocess.Popen(init_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout, stderr = process.communicate() if process.returncode != 0: logger.error(f"Erreur lors de l'initialisation: {stderr.decode()}") return None html_content = stdout.decode() # Extraire le token CSRF et l'App ID csrf_match = re.search(r'"csrf_token":"([^"]+)"', html_content) appid_match = re.search(r'"appId":"(\d+)"', html_content) if not csrf_match or not appid_match: logger.error("Impossible de trouver les tokens nécessaires") return None csrf_token = csrf_match.group(1) app_id = appid_match.group(1) # Générer un device ID device_id = generate_uuid() # Retourner la session return { 'cookies_file': 'instagram_cookies.txt', 'csrf_token': csrf_token, 'app_id': app_id, 'device_id': device_id, 'user_agent': user_agent } def download_instagram_video(url, output_dir="downloads"): """Télécharge une vidéo Instagram via l'API GraphQL publique""" logger.info(f"🔄 Téléchargement depuis Instagram: {url}") if not os.path.exists(output_dir): os.makedirs(output_dir) post_id = extract_post_id(url) if not post_id: logger.error("❌ URL Instagram invalide") return None try: session = get_instagram_session() if not session: logger.error("❌ Impossible d'obtenir une session valide") return None # Headers pour l'API GraphQL headers = { 'Authority': 'www.instagram.com', 'Accept': '*/*', 'Accept-Language': 'en-US,en;q=0.9', 'Content-Type': 'application/x-www-form-urlencoded', 'Origin': 'https://www.instagram.com', 'Referer': f'https://www.instagram.com/reel/{post_id}/', 'Sec-Ch-Ua': '"Not A(Brand";v="24", "Chromium";v="121"', 'Sec-Ch-Ua-Mobile': '?0', 'Sec-Ch-Ua-Platform': '"Windows"', 'Sec-Fetch-Dest': 'empty', 'Sec-Fetch-Mode': 'cors', 'Sec-Fetch-Site': 'same-origin', 'User-Agent': session['user_agent'], 'X-Asbd-Id': '129477', 'X-Csrftoken': session['csrf_token'], 'X-Ig-App-Id': session['app_id'], 'X-Ig-Www-Claim': '0', 'X-Requested-With': 'XMLHttpRequest' } # Variables pour la requête GraphQL variables = { "shortcode": post_id, "__typename": "GraphVideo", "doc_id": "3217533874971376" } # Paramètres de la requête params = { "doc_id": variables["doc_id"], "variables": json.dumps(variables) } # Construction de l'URL avec les paramètres query_string = urlencode(params) api_url = f"https://www.instagram.com/graphql/query/?{query_string}" logger.info("Récupération des informations via GraphQL...") api_cmd = [ 'curl', api_url, '-H', f'Authority: {headers["Authority"]}', '-H', f'Accept: {headers["Accept"]}', '-H', f'Accept-Language: {headers["Accept-Language"]}', '-H', f'Content-Type: {headers["Content-Type"]}', '-H', f'Origin: {headers["Origin"]}', '-H', f'Referer: {headers["Referer"]}', '-H', f'Sec-Ch-Ua: {headers["Sec-Ch-Ua"]}', '-H', f'Sec-Ch-Ua-Mobile: {headers["Sec-Ch-Ua-Mobile"]}', '-H', f'Sec-Ch-Ua-Platform: {headers["Sec-Ch-Ua-Platform"]}', '-H', f'Sec-Fetch-Dest: {headers["Sec-Fetch-Dest"]}', '-H', f'Sec-Fetch-Mode: {headers["Sec-Fetch-Mode"]}', '-H', f'Sec-Fetch-Site: {headers["Sec-Fetch-Site"]}', '-H', f'User-Agent: {headers["User-Agent"]}', '-H', f'X-Asbd-Id: {headers["X-Asbd-Id"]}', '-H', f'X-Csrftoken: {headers["X-Csrftoken"]}', '-H', f'X-Ig-App-Id: {headers["X-Ig-App-Id"]}', '-H', f'X-Ig-Www-Claim: {headers["X-Ig-Www-Claim"]}', '-H', f'X-Requested-With: {headers["X-Requested-With"]}', '-b', session['cookies_file'], '--compressed', '-s' ] logger.debug(f"Requête GraphQL: {api_url}") process = subprocess.Popen(api_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout, stderr = process.communicate() if process.returncode != 0: logger.error(f"❌ Erreur lors de la requête GraphQL: {stderr.decode()}") return None try: response = json.loads(stdout) logger.debug(f"Réponse GraphQL: {json.dumps(response, indent=2)}") # Extraire l'URL de la vidéo video_data = response.get('data', {}).get('shortcode_media', {}) if not video_data: logger.error("❌ Pas de données média dans la réponse") return None if not video_data.get('is_video', False): logger.error("❌ Ce post n'est pas une vidéo") return None video_url = video_data.get('video_url') if not video_url: logger.error("❌ URL de la vidéo non trouvée") return None # Télécharger la vidéo output_file = os.path.join(output_dir, f"video_{int(time.time())}.mp4") logger.info("🔄 Téléchargement de la vidéo...") download_cmd = [ 'curl', video_url, '-L', '-o', output_file, '-H', f'User-Agent: {headers["User-Agent"]}', '-H', 'Accept: */*', '-H', f'Referer: {headers["Referer"]}', '-b', session['cookies_file'], '--compressed', '-s' ] download_process = subprocess.Popen(download_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout, stderr = download_process.communicate() if download_process.returncode == 0 and os.path.exists(output_file): logger.info(f"✅ Vidéo téléchargée: {output_file}") return output_file else: logger.error(f"❌ Erreur lors du téléchargement: {stderr.decode()}") return None except json.JSONDecodeError: logger.error("❌ Erreur de décodage JSON de la réponse GraphQL") logger.error(f"Réponse reçue: {stdout.decode()}") return None except Exception as e: logger.error(f"❌ Erreur: {str(e)}") return None finally: # Nettoyer les fichiers temporaires if os.path.exists('instagram_cookies.txt'): os.remove('instagram_cookies.txt') if __name__ == "__main__": url = "https://www.instagram.com/reel/C2_Kh6mPmGl/" result = download_instagram_video(url) if result: print(f"\n✅ Vidéo téléchargée avec succès: {result}") else: print("\n❌ Échec du téléchargement")