#!/usr/bin/env python3 """ Script pour tester différentes approches Instagram """ import requests import re import json from bs4 import BeautifulSoup import logging import time # Configuration du logging logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) def test_instagram_api(): """Test de différentes approches pour Instagram""" # URL de test url = "https://www.instagram.com/reel/DMpc37-tJdF/" print(f"🔍 Test différentes approches Instagram: {url}") # Headers pour simuler un navigateur mobile headers = { 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 14_7_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Mobile/15E148 Safari/604.1', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'fr-FR,fr;q=0.9,en;q=0.8', 'Accept-Encoding': 'gzip, deflate', 'Connection': 'keep-alive' } session = requests.Session() session.headers.update(headers) try: # Test 1: URL mobile print("\n📱 Test 1: URL mobile") mobile_url = url.replace('instagram.com', 'm.instagram.com') response = session.get(mobile_url, timeout=30) print(f"Status: {response.status_code}") print(f"Content length: {len(response.text)}") if response.status_code == 200: with open('instagram_mobile.html', 'w', encoding='utf-8') as f: f.write(response.text) print("✅ Contenu mobile sauvegardé") # Analyser le contenu mobile soup = BeautifulSoup(response.text, 'html.parser') # Chercher les métadonnées meta_tags = soup.find_all('meta') for meta in meta_tags: property_attr = meta.get('property', '') content_attr = meta.get('content', '') if 'description' in property_attr.lower(): print(f"✅ Mobile description: {content_attr[:100]}...") elif 'duration' in property_attr.lower(): print(f"✅ Mobile duration: {content_attr}") # Test 2: API publique Instagram (si disponible) print("\n🔌 Test 2: API publique") shortcode = url.split('/reel/')[1].split('/')[0] api_url = f"https://www.instagram.com/api/v1/media/{shortcode}/info/" api_headers = headers.copy() api_headers.update({ 'X-Requested-With': 'XMLHttpRequest', 'Referer': url }) response_api = session.get(api_url, headers=api_headers, timeout=30) print(f"API Status: {response_api.status_code}") if response_api.status_code == 200: try: api_data = response_api.json() print(f"✅ API data: {str(api_data)[:200]}...") # Sauvegarder les données API with open('instagram_api.json', 'w', encoding='utf-8') as f: json.dump(api_data, f, indent=2) print("✅ Données API sauvegardées") except Exception as e: print(f"❌ Erreur parsing API: {e}") else: print(f"❌ API non accessible: {response_api.status_code}") # Test 3: GraphQL endpoint print("\n📊 Test 3: GraphQL endpoint") graphql_url = "https://www.instagram.com/graphql/query/" graphql_headers = headers.copy() graphql_headers.update({ 'X-Requested-With': 'XMLHttpRequest', 'Referer': url, 'Content-Type': 'application/json' }) # Query GraphQL pour récupérer les infos du media graphql_query = { "query_hash": "9f8827793ef34641b2fb195d4d41151c", "variables": json.dumps({ "shortcode": shortcode }) } response_graphql = session.get(graphql_url, params=graphql_query, headers=graphql_headers, timeout=30) print(f"GraphQL Status: {response_graphql.status_code}") if response_graphql.status_code == 200: try: graphql_data = response_graphql.json() print(f"✅ GraphQL data: {str(graphql_data)[:200]}...") # Sauvegarder les données GraphQL with open('instagram_graphql.json', 'w', encoding='utf-8') as f: json.dump(graphql_data, f, indent=2) print("✅ Données GraphQL sauvegardées") except Exception as e: print(f"❌ Erreur parsing GraphQL: {e}") else: print(f"❌ GraphQL non accessible: {response_graphql.status_code}") # Test 4: Essayer avec un User-Agent différent print("\n🤖 Test 4: User-Agent différent") headers_bot = { 'User-Agent': 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'en-US,en;q=0.5', 'Accept-Encoding': 'gzip, deflate', 'Connection': 'keep-alive' } session_bot = requests.Session() session_bot.headers.update(headers_bot) response_bot = session_bot.get(url, timeout=30) print(f"Bot Status: {response_bot.status_code}") print(f"Bot Content length: {len(response_bot.text)}") if response_bot.status_code == 200: with open('instagram_bot.html', 'w', encoding='utf-8') as f: f.write(response_bot.text) print("✅ Contenu bot sauvegardé") # Analyser le contenu bot soup_bot = BeautifulSoup(response_bot.text, 'html.parser') # Chercher les métadonnées meta_tags = soup_bot.find_all('meta') for meta in meta_tags: property_attr = meta.get('property', '') content_attr = meta.get('content', '') if 'description' in property_attr.lower(): print(f"✅ Bot description: {content_attr[:100]}...") elif 'duration' in property_attr.lower(): print(f"✅ Bot duration: {content_attr}") # Test 5: Analyser les fichiers sauvegardés print("\n📊 Test 5: Analyse des fichiers sauvegardés") files_to_check = ['instagram_mobile.html', 'instagram_api.json', 'instagram_graphql.json', 'instagram_bot.html'] for filename in files_to_check: try: with open(filename, 'r', encoding='utf-8') as f: content = f.read() print(f"\n🔍 Analyse de {filename}:") # Chercher des patterns spécifiques patterns = [ r'"duration":\s*"?(\d+)"?', r'"video_duration":\s*"?(\d+)"?', r'"media_duration":\s*"?(\d+)"?', r'"caption":\s*"([^"]*)"', r'"text":\s*"([^"]*)"', r'"description":\s*"([^"]*)"', r'"title":\s*"([^"]*)"' ] for pattern in patterns: matches = re.findall(pattern, content, re.IGNORECASE | re.DOTALL) if matches: print(f" ✅ Pattern '{pattern}' trouvé: {matches[0][:100]}...") except FileNotFoundError: print(f" ❌ Fichier {filename} non trouvé") except Exception as e: print(f" ❌ Erreur lecture {filename}: {e}") except Exception as e: print(f"❌ Erreur générale: {e}") import traceback traceback.print_exc() if __name__ == "__main__": test_instagram_api()